Tootfinder

Two House Republicans open a probe into alleged organized efforts to inject bias into Wikipedia, citing an ADL report about anti-Israel bias on the site (Emily Brooks/The Hill)
https://thehill.com/homenews/house/5473331-wikipedia-bias-probe-republicans/

RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation
Enguang Liu, Siyuan Liang, Liming Lu, Xiyu Zeng, Xiaochun Cao, Aishan Liu, Shuchao Pang
https://arxiv.org/abs/2509.22356

RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation
The safety and reliability of embodied agents rely on accurate and unbiased visual perception. However, existing benchmarks mainly emphasize generalization and robustness under perturbations, while systematic quantification of visual bias remains scarce. This gap limits a deeper understanding of how perception influences decision-making stability. To address this issue, we propose RoboView-Bias, the first benchmark specifically designed to systematically quantify visual bias in robotic manipula…

Two House Republicans open a probe into alleged organized efforts to inject bias into Wikipedia, citing an ADL report about anti-Israel bias on the site (Emily Brooks/The Hill)
https://thehill.com/homenews/house/5473331-wikipedia-bias-probe-republicans/
http://mediagazer.com/250828/p8#a250828p8

Understanding Bias in Perceiving Dimensionality Reduction Projections
Seoyoung Doh, Hyeon Jeon, Sungbok Shin, Ghulam Jilani Quadri, Nam Wook Kim, Jinwook Seo
https://arxiv.org/abs/2507.20805

Understanding Bias in Perceiving Dimensionality Reduction Projections
Selecting the dimensionality reduction technique that faithfully represents the structure is essential for reliable visual communication and analytics. In reality, however, practitioners favor projections for other attractions, such as aesthetics and visual saliency, over the projection's structural faithfulness, a bias we define as visual interestingness. In this research, we conduct a user study that (1) verifies the existence of such bias and (2) explains why the bias exists. Our study sugge…

Republicans investigate Wikipedia over allegations of organized bias (Emily Brooks/The Hill)
https://thehill.com/homenews/house/5473331-wikipedia-bias-probe-republicans/
http://www.memeorandum.com/250828/p138#a250828p138

Addressing Personalized Bias for Unbiased Learning to Rank
Zechun Niu, Lang Mei, Liu Yang, Ziyuan Zhao, Qiang Yan, Jiaxin Mao, Ji-Rong Wen
https://arxiv.org/abs/2508.20798 https…

Addressing Personalized Bias for Unbiased Learning to Rank
Unbiased learning to rank (ULTR), which aims to learn unbiased ranking models from biased user behavior logs, plays an important role in Web search. Previous research on ULTR has studied a variety of biases in users' clicks, such as position bias, presentation bias, and outlier bias. However, existing work often assumes that the behavior logs are collected from an ``average'' user, neglecting the differences between different users in their search and browsing behaviors. In this paper, we intro…

Bias Analysis for Synthetic Face Detection: A Case Study of the Impact of Facial Attribute
Asmae Lamsaf, Lucia Cascone, Hugo Proen\c{c}a, Jo\~ao Neves
https://arxiv.org/abs/2507.19705

Bias Analysis for Synthetic Face Detection: A Case Study of the Impact of Facial Attribute
Bias analysis for synthetic face detection is bound to become a critical topic in the coming years. Although many detection models have been developed and several datasets have been released to reliably identify synthetic content, one crucial aspect has been largely overlooked: these models and training datasets can be biased, leading to failures in detection for certain demographic groups and raising significant social, legal, and ethical issues. In this work, we introduce an evaluation framew…

TrueGradeAI: Retrieval-Augmented and Bias-Resistant AI for Transparent and Explainable Digital Assessments
Rakesh Thakur, Shivaansh Kaushik, Gauri Chopra, Harsh Rohilla
https://arxiv.org/abs/2509.22516

TrueGradeAI: Retrieval-Augmented and Bias-Resistant AI for Transparent and Explainable Digital Assessments
This paper introduces TrueGradeAI, an AI-driven digital examination framework designed to overcome the shortcomings of traditional paper-based assessments, including excessive paper usage, logistical complexity, grading delays, and evaluator bias. The system preserves natural handwriting by capturing stylus input on secure tablets and applying transformer-based optical character recognition for transcription. Evaluation is conducted through a retrieval-augmented pipeline that integrates faculty…

ConQuER: Modular Architectures for Control and Bias Mitigation in IQP Quantum Generative Models
Xiaocheng Zou, Shijin Duan, Charles Fleming, Gaowen Liu, Ramana Rao Kompella, Shaolei Ren, Xiaolin Xu
https://arxiv.org/abs/2509.22551

ConQuER: Modular Architectures for Control and Bias Mitigation in IQP Quantum Generative Models
Quantum generative models based on instantaneous quantum polynomial (IQP) circuits show great promise in learning complex distributions while maintaining classical trainability. However, current implementations suffer from two key limitations: lack of controllability over generated outputs and severe generation bias towards certain expected patterns. We present a Controllable Quantum Generative Framework, ConQuER, which addresses both challenges through a modular circuit architecture. ConQuER e…

Dynamics of Gender Bias in Software Engineering
Thomas J. Misa
https://arxiv.org/abs/2508.21050 https://arxiv.org/pdf/2508.21050

Dynamics of Gender Bias in Software Engineering
The field of software engineering is embedded in both engineering and computer science, and may embody gender biases endemic to both. This paper surveys software engineering's origins and its long-running attention to engineering professionalism, profiling five leaders; it then examines the field's recent attention to gender issues and gender bias. It next quantitatively analyzes women's participation as research authors in the field's leading International Conference of Software Engineering (1…

A Random Matrix Perspective of Echo State Networks: From Precise Bias--Variance Characterization to Optimal Regularization
Yessin Moakher, Malik Tiomoko, Cosme Louart, Zhenyu Liao
https://arxiv.org/abs/2509.22011

A Random Matrix Perspective of Echo State Networks: From Precise Bias--Variance Characterization to Optimal Regularization
We present a rigorous asymptotic analysis of Echo State Networks (ESNs) in a teacher student setting with a linear teacher with oracle weights. Leveraging random matrix theory, we derive closed form expressions for the asymptotic bias, variance, and mean-squared error (MSE) as functions of the input statistics, the oracle vector, and the ridge regularization parameter. The analysis reveals two key departures from classical ridge regression: (i) ESNs do not exhibit double descent, and (ii) ESNs …

Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
William Qian, Cengiz Pehlevan
https://arxiv.org/abs/2509.21504 https://

Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
Training recurrent neural networks (RNNs) to perform neuroscience-style tasks has become a popular way to generate hypotheses for how neural circuits in the brain might perform computations. Recent work has demonstrated that task-trained RNNs possess a strong simplicity bias. In particular, this inductive bias often causes RNNs trained on the same task to collapse on effectively the same solution, typically comprised of fixed-point attractors or other low-dimensional dynamical motifs. While suc…

Direct Bias-Correction Term Estimation for Propensity Scores and Average Treatment Effect Estimation
Masahiro Kato
https://arxiv.org/abs/2509.22122 https://

Direct Bias-Correction Term Estimation for Propensity Scores and Average Treatment Effect Estimation
This study considers the estimation of the average treatment effect (ATE). For ATE estimation, we estimate the propensity score through direct bias-correction term estimation. Let $\{(X_i, D_i, Y_i)\}_{i=1}^{n}$ be the observations, where $X_i \in \mathbb{R}^p$ denotes $p$-dimensional covariates, $D_i \in \{0, 1\}$ denotes a binary treatment assignment indicator, and $Y_i \in \mathbb{R}$ is an outcome. In ATE estimation, the bias-correction term $h_0(X_i, D_i) = \frac{1[D_i = 1]}{e_0(X_i)} - \f…

Uncovering the Spectral Bias in Diagonal State Space Models
Ruben Solozabal, Velibor Bojkovic, Hilal AlQuabeh, Kentaro Inui, Martin Tak\'a\v{c}
https://arxiv.org/abs/2508.20441

Uncovering the Spectral Bias in Diagonal State Space Models
Current methods for initializing state space models (SSMs) parameters mainly rely on the \textit{HiPPO framework}, which is based on an online approximation of orthogonal polynomials. Recently, diagonal alternatives have shown to reach a similar level of performance while being significantly more efficient due to the simplification in the kernel computation. However, the \textit{HiPPO framework} does not explicitly study the role of its diagonal variants. In this paper, we take a further step t…

Guarding Against Malicious Biased Threats (GAMBiT) Experiments: Revealing Cognitive Bias in Human-Subjects Red-Team Cyber Range Operations
Brandon Beltz, Jim Doty, Yvonne Fonken, Nikolos Gurney, Brett Israelsen, Nathan Lau, Stacy Marsella, Rachelle Thomas, Stoney Trent, Peggy Wu, Ya-Ting Yang, Quanyan Zhu
https://arxiv.org/abs/2508.20963…

Guarding Against Malicious Biased Threats (GAMBiT) Experiments: Revealing Cognitive Bias in Human-Subjects Red-Team Cyber Range Operations
We present three large-scale human-subjects red-team cyber range datasets from the Guarding Against Malicious Biased Threats (GAMBiT) project. Across Experiments 1-3 (July 2024-March 2025), 19-20 skilled attackers per experiment conducted two 8-hour days of self-paced operations in a simulated enterprise network (SimSpace Cyber Force Platform) while we captured multi-modal data: self-reports (background, demographics, psychometrics), operational notes, terminal histories, keylogs, network packe…

Correcting the fiber-aperture bias affecting galaxy stellar populations in the Sloan Digital Sky Survey. Aperture corrections to absorption indices based on CALIFA integral field observations
Stefano Zibetti (INAF-Arcetri Astrophysical Observatory, Firenze, Italy), Jacopo Pratesi (INAF-Arcetri Astrophysical Observatory, Firenze, Italy, Universit\`a degli Studi di Firenze, Italy), Anna R. Gallazzi (INAF-Arcetri Astrophysical Observatory, Firenze, Italy), Daniele Mattolini (Universit\`a …

Correcting the fiber-aperture bias affecting galaxy stellar populations in the Sloan Digital Sky Survey. Aperture corrections to absorption indices based on CALIFA integral field observations
Stellar population properties are crucial for understanding galaxy evolution. Their inference for statistically representative samples requires deep multi-object spectroscopy, typically obtained with fiber-fed spectrographs that integrate only a fraction of galaxy light. The most comprehensive local Universe dataset is the Sloan Digital Sky Survey (SDSS), whose fibers typically collected ~30% of total flux. Stellar population gradients, ubiquitously present in galaxies, systematically bias SDSS…

VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model
Junhyuk Choi, Ro-hoon Oh, Jihwan Seol, Bugeun Kim
https://arxiv.org/abs/2509.21108

VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model
We introduce VoiceBBQ, a spoken extension of the BBQ (Bias Benchmark for Question Answering) - a dataset that measures social bias by presenting ambiguous or disambiguated contexts followed by questions that may elicit stereotypical responses. Due to the nature of speech, social bias in Spoken Language Models (SLMs) can emerge from two distinct sources: 1) content aspect and 2) acoustic aspect. The dataset converts every BBQ context into controlled voice conditions, enabling per-axis accuracy, …

A note on the relation between one--step, outcome regression and IPW--type estimators of parameters with the mixed bias property
Andrea Rotnitzky, Ezequiel Smucler, James M. Robins
https://arxiv.org/abs/2509.22452

A note on the relation between one--step, outcome regression and IPW--type estimators of parameters with the mixed bias property
Bruns-Smith et al. (2025) established an algebraic identity between the one-step estimator and a specific outcome regression-type estimator for a class of parameters that forms a strict subset of the class introduced in Chernozhukov et al. (2022), assuming both nuisance functions are estimated as linear combinations of given features. They conjectured that this identity extends to the broader mixed bias class introduced in Rotnitzky et al. (2021). In this note, we prove their conjecture and fur…

DOJ probes CalEPA hiring for potential racial bias
https://thehill.com/policy/energy-environment/5473143-doj-california-epa-calepa-racial-equity-newsom-trump/

Ask Me Again Differently: GRAS for Measuring Bias in Vision Language Models on Gender, Race, Age, and Skin Tone
Shaivi Malik, Hasnat Md Abdullah, Sriparna Saha, Amit Sheth
https://arxiv.org/abs/2508.18989

Ask Me Again Differently: GRAS for Measuring Bias in Vision Language Models on Gender, Race, Age, and Skin Tone
As Vision Language Models (VLMs) become integral to real-world applications, understanding their demographic biases is critical. We introduce GRAS, a benchmark for uncovering demographic biases in VLMs across gender, race, age, and skin tone, offering the most diverse coverage to date. We further propose the GRAS Bias Score, an interpretable metric for quantifying bias. We benchmark five state-of-the-art VLMs and reveal concerning bias levels, with the least biased model attaining a GRAS Bias S…

Kurzen Hinweis auf Cory Doctorows Essay zur AI-Blase ins Blog gepackt.
https://blog.till-westermayer.de/index.php/2025/09/28/kurz-in-der-blase/

Kurz: In der Blase
Es gibt viele Gründe, "AI" zu kritisieren - das reicht von Bias in den zugrundeliegenden Daten über Umweltaspekte bis hin zu der Tatsache, dass große Sprachmodelle prinzipienbedingt eher plausibel klingende "Fakten" erfinden als keine Antwort zu geben. Nichtsdestotrotz scheint eine größere Zahl an M

"What then is the spirit of liberty? I cannot define it; I can only tell you my own faith. The spirit of liberty is the spirit which is not too sure that it is right; the spirit of liberty is the spirit which seeks to understand the mind of other men and women; the spirit of liberty is the spirit which weighs their interests alongside its own without bias; the spirit of liberty remembers that not even a sparrow falls to earth unheeded..." - Learned Hand

KI-Update kompakt: LLMs für Malware, Anti-Human-Bias, Sutton, Chatbots
Das "KI-Update" liefert werktäglich eine Zusammenfassung der wichtigsten KI-Entwicklungen.
https://www.

Speak Your Mind: The Speech Continuation Task as a Probe of Voice-Based Model Bias
Shree Harsha Bokkahalli Satish, Harm Lameris, Olivier Perrotin, Gustav Eje Henter, \'Eva Sz\'ekely
https://arxiv.org/abs/2509.22061

Speak Your Mind: The Speech Continuation Task as a Probe of Voice-Based Model Bias
Speech Continuation (SC) is the task of generating a coherent extension of a spoken prompt while preserving both semantic context and speaker identity. Because SC is constrained to a single audio stream, it offers a more direct setting for probing biases in speech foundation models than dialogue does. In this work we present the first systematic evaluation of bias in SC, investigating how gender and phonation type (breathy, creaky, end-creak) affect continuation behaviour. We evaluate three rec…

Forecasting the Future with Yesterday's Climate: Temperature Bias in AI Weather and Climate Models
Jacob B. Landsberg, Elizabeth A. Barnes
https://arxiv.org/abs/2509.22359 h…

Forecasting the Future with Yesterday's Climate: Temperature Bias in AI Weather and Climate Models
AI-based climate and weather models have rapidly gained popularity, providing faster forecasts with skill that can match or even surpass that of traditional dynamical models. Despite this success, these models face a key challenge: predicting future climates while being trained only with historical data. In this study, we investigate this issue by analyzing boreal winter land temperature biases in AI weather and climate models. We examine two weather models, FourCastNet V2 Small (FourCastNet) a…

SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation
Junyu Yan, Feng Chen, Yuyang Xue, Yuning Du, Konstantinos Vilouras, Sotirios A. Tsaftaris, Steven McDonagh
https://arxiv.org/abs/2508.18826

SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation
Recent studies have shown that Machine Learning (ML) models can exhibit bias in real-world scenarios, posing significant challenges in ethically sensitive domains such as healthcare. Such bias can negatively affect model fairness, model generalization abilities and further risks amplifying social discrimination. There is a need to remove biases from trained models. Existing debiasing approaches often necessitate access to original training data and need extensive model retraining; they also typ…

Risky Advice and Reputational Bias
Georgy Lukyanov, Anna Vlasova, Maria Ziskelevich
https://arxiv.org/abs/2508.19707 https://arxiv.org/pdf/2508.19707

Risky Advice and Reputational Bias
We study expert advice under reputational incentives, with sell-side equity research as the lead application. A long-lived analyst receives a continuous private signal about a binary payoff and recommends a risky (Buy) or safe action. Recommendations and outcomes are public, and clients' implementation effort depends on current reputation. In a recursive, belief-based equilibrium: (i) advice follows a cutoff in the signal; (ii) under a simple diagnosticity asymmetry, the cutoff is (weakly) incr…

FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing
Hossein Kashiani, Niloufar Alipour Talemi, Fatemeh Afghah
https://arxiv.org/abs/2509.22412

FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing
Deepfake detectors often struggle to generalize to novel forgery types due to biases learned from limited training data. In this paper, we identify a new type of model bias in the frequency domain, termed spectral bias, where detectors overly rely on specific frequency bands, restricting their ability to generalize across unseen forgeries. To address this, we propose FreqDebias, a frequency debiasing framework that mitigates spectral bias through two complementary strategies. First, we introduc…

The role of spatial perception in auditory looming bias: neurobehavioral evidence from impossible ears https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2025.1645936/full

Frontiers | The role of spatial perception in auditory looming bias: neurobehavioral evidence from impossible ears
IntroductionSpatial hearing enables both voluntary localization of sound sources and automatic monitoring of the surroundings. The auditory looming bias (ALB...

Your AI, Not Your View: The Bias of LLMs in Investment Analysis
Hoyoung Lee, Junhyuk Seo, Suhwan Park, Junhyeong Lee, Wonbin Ahn, Chanyeol Choi, Alejandro Lopez-Lira, Yongjae Lee
https://arxiv.org/abs/2507.20957

Your AI, Not Your View: The Bias of LLMs in Investment Analysis
In finance, Large Language Models (LLMs) face frequent knowledge conflicts due to discrepancies between pre-trained parametric knowledge and real-time market data. These conflicts become particularly problematic when LLMs are deployed in real-world investment services, where misalignment between a model's embedded preferences and those of the financial institution can lead to unreliable recommendations. Yet little research has examined what investment views LLMs actually hold. We propose an exp…

Communication Bias in Large Language Models: A Regulatory Perspective
Adrian Kuenzler, Stefan Schmid
https://arxiv.org/abs/2509.21075 https://arxiv.org/pdf…

Communication Bias in Large Language Models: A Regulatory Perspective
Large language models (LLMs) are increasingly central to many applications, raising concerns about bias, fairness, and regulatory compliance. This paper reviews risks of biased outputs and their societal impact, focusing on frameworks like the EU's AI Act and the Digital Services Act. We argue that beyond constant regulation, stronger attention to competition and design governance is needed to ensure fair, trustworthy AI. This is a preprint of the Communications of the ACM article of the same t…

Improving Community Detection in Academic Networks by Handling Publication Bias
Md Asaduzzaman Noor, John Sheppard, Jason Clark
https://arxiv.org/abs/2507.20449 https://

Improving Community Detection in Academic Networks by Handling Publication Bias
Finding potential research collaborators is a challenging task, especially in today's fast-growing and interdisciplinary research landscape. While traditional methods often rely on observable relationships such as co-authorships and citations to construct the research network, in this work, we focus solely on publication content to build a topic-based research network using BERTopic with a fine-tuned SciBERT model that connects and recommends researchers across disciplines based on shared topic…

Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics
Ayato Kitadai, Yusuke Fukasawa, Nariaki Nishino
https://arxiv.org/abs/2508.18600 https://…

Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics
Large language models (LLMs) are increasingly used to simulate human decision-making, but their intrinsic biases often diverge from real human behavior--limiting their ability to reflect population-level diversity. We address this challenge with a persona-based approach that leverages individual-level behavioral data from behavioral economics to adjust model biases. Applying this method to the ultimatum game--a standard but difficult benchmark for LLMs--we observe improved alignment between sim…

Berry Curvature Dipole-Induced Chiral Terahertz Gain and Lasing in Bulk Tellurium
Mounes Eslami, Amin Hakimi, Luis A. Jauregui, Filippo Capolino
https://arxiv.org/abs/2508.18677

Berry Curvature Dipole-Induced Chiral Terahertz Gain and Lasing in Bulk Tellurium
We investigate the use of Berry curvature dipole in $n$-doped Tellurium as a mechanism for achieving terahertz amplification and lasing by applying a DC electric field. When the electrical bias and wave vector are aligned along the trigonal $c$-axis, the right-handed circularly polarized mode experiences amplification at relatively low bias, while the left-handed mode is attenuated. Furthermore, when the electrical bias and wave vector are orthogonal to the $c$-axis, the structure supports elli…

Copas-Jackson-type bounds for publication bias over a general class of selection models
Taojun Hu, Yi Zhou, Xiao-Hua Zhou, Satoshi Hattori
https://arxiv.org/abs/2508.17716 https…

Copas-Jackson-type bounds for publication bias over a general class of selection models
Publication bias (PB) is one of the most vital threats to the accuracy of meta-analysis. Adjustment or sensitivity analysis based on selection models, which describe the probability of a study being published, provide a more objective evaluation of PB than widely-used simple graphical methods such as the trim-and-fill method. Most existing methods rely on parametric selection models. The Copas-Jackson bound (C-J bound) provides a worst-case bound of an analytical form over a nonparametric class…

Crosslisted article(s) found for cs.DC. https://arxiv.org/list/cs.DC/new
[1/1]:
- Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs
Md Abdullah Al Mamun, Ihsen Alouani, Nael Abu-Ghazaleh

Signatures and bias assessment of rotation in galaxy cluster members
Davide Castellani, Giovanni Ferrami, Claudio Grillo, Giuseppe Bertin
https://arxiv.org/abs/2508.18354 https:…

Signatures and bias assessment of rotation in galaxy cluster members
We investigate the possible presence of systematic rotation in the member galaxies of a sample of 17 nearby ($z<0.1$), rich (at least 80 identified members) Abell clusters. We also assess the extent to which low-number statistics may influence the recovery of the rotation parameters. Following the methods often used in the context of globular clusters and of clusters of galaxies, we estimate a representative value of the systematic rotation velocity and the position angle of the projected rotat…

A Machine Learning Approach to Volumetric Computations of Solid Pulmonary Nodules
Yihan Zhou, Haocheng Huang, Yue Yu, Jianhui Shang
https://arxiv.org/abs/2508.20127 https://

A Machine Learning Approach to Volumetric Computations of Solid Pulmonary Nodules
Early detection of lung cancer is crucial for effective treatment and relies on accurate volumetric assessment of pulmonary nodules in CT scans. Traditional methods, such as consolidation-to-tumor ratio (CTR) and spherical approximation, are limited by inconsistent estimates due to variability in nodule shape and density. We propose an advanced framework that combines a multi-scale 3D convolutional neural network (CNN) with subtype-specific bias correction for precise volume estimation. The mod…

How Quantization Shapes Bias in Large Language Models
Federico Marcuzzi, Xuefei Ning, Roy Schwartz, Iryna Gurevych
https://arxiv.org/abs/2508.18088 https://

How Quantization Shapes Bias in Large Language Models
This work presents a comprehensive evaluation of how quantization affects model bias, with particular attention to its impact on individual demographic subgroups. We focus on weight and activation quantization strategies and examine their effects across a broad range of bias types, including stereotypes, toxicity, sentiment, and fairness. We employ both probabilistic and generated text-based metrics across nine benchmarks and evaluate models varying in architecture family and reasoning ability.…

Unbiased Binning: Fairness-aware Attribute Representation
Abolfazl Asudeh (Mila), Zeinab (Mila), Asoodeh, Bita Asoodeh, Omid Asudeh
https://arxiv.org/abs/2509.21785 https://…

Unbiased Binning: Fairness-aware Attribute Representation
Discretizing raw features into bucketized attribute representations is a popular step before sharing a dataset. It is, however, evident that this step can cause significant bias in data and amplify unfairness in downstream tasks. In this paper, we address this issue by introducing the unbiased binning problem that, given an attribute to bucketize, finds its closest discretization to equal-size binning that satisfies group parity across different buckets. Defining a small set of boundary candi…

Experimental End-to-End Optimization of Directly Modulated Laser-based IM/DD Transmission
Sergio Hernandez, Christophe Peucheret, Francesco Da Ros, Darko Zibar
https://arxiv.org/abs/2508.19910

Experimental End-to-End Optimization of Directly Modulated Laser-based IM/DD Transmission
Directly modulated lasers (DMLs) are an attractive technology for short-reach intensity modulation and direct detection communication systems. However, their complex nonlinear dynamics make the modeling and optimization of DML-based systems challenging. In this paper, we study the end-to-end optimization of DML-based systems based on a data-driven surrogate model trained on experimental data. The end-to-end optimization includes the pulse shaping and equalizer filters, the bias current and the …

A Proposal for Yield Improvement with Power Tradeoffs in CMOS LNAs (English Version)
J. L. Gonz\'alez, J. C. Cruz, R. L. Moreno, D. V\'azquez
https://arxiv.org/abs/2508.20611

A Proposal for Yield Improvement with Power Tradeoffs in CMOS LNAs (English Version)
This paper studies an architecture with digitally controllable gain and power consumption to mitigate the impact of process variations on CMOS low-noise amplifiers (LNAs). A \SI{130}{nm}, \SI{1.2}{V} LNA implementing the proposed architecture is designed based on an analysis of variability in traditional LNAs under different bias currents and on the corresponding effects on the performance of a complete receiver. Two different adjustment strategies are evaluated, both of which are compatible wi…

Crosslisted article(s) found for cs.NE. https://arxiv.org/list/cs.NE/new
[1/1]:
- Discovering alternative solutions beyond the simplicity bias in recurrent neural networks
William Qian, Cengiz Pehlevan

Unveiling Obscured Accretion in the Local Universe
Indrani Pal, Stefano Marchesi, Ross Silver, Marco Ajello, Vittoria Gianolli, N\'uria Torres-Alb\`a, Isaiah Cox, Xiurui Zhao, Dhrubojyoti Sengupta, Anuvab Banerjee, Kouser Imam, Andrealuna Pizzetti
https://arxiv.org/abs/2509.21532

Unveiling Obscured Accretion in the Local Universe
Heavily obscured Active Galactic Nuclei (AGN), especially Compton-thick sources with line-of-sight column density ($N_{\rm H,los}$) $>$ 10$^{24}$ cm$^{-2}$, are critical to understanding supermassive black hole (SMBH) growth and the origin of the Cosmic X-ray Background (CXB). However, their observed fraction remains significantly below model predictions, due to strong absorption bias, even in the hard X-ray (i.e., above 10 keV) band. We analyze a sample of 26 nearby ($z < 0.1$) AGN from the Sw…

Attractive and Repulsive Perceptual Biases Naturally Emerge in Generative Adversarial Inference
Hyun-Jun Jeon, Hansol Choi, Oh-Sang Kwon
https://arxiv.org/abs/2507.19944 https:/…

Attractive and Repulsive Perceptual Biases Naturally Emerge in Generative Adversarial Inference
Human perceptual estimates exhibit a striking reversal in bias depending on uncertainty: they shift toward prior expectations under high sensory uncertainty, but away from them when internal noise is dominant. While Bayesian inference combined with efficient coding can explain this dual bias, existing models rely on handcrafted priors or fixed encoders, offering no account of how such representations and inferences could emerge through learning. We introduce a Generative Adversarial Inference (…

Polymer-based probabilistic bits for thermodynamic computing
Stephen H. Foulger, Yuriy Bandera, Igor Luzinov, Travis Wanless, Lubomir Kostal, Vojtech N\'adazdy, Petr Janovsk\'y, Jarmila Vil\v{c}\'akov\'a
https://arxiv.org/abs/2509.21372

Polymer-based probabilistic bits for thermodynamic computing
Probabilistic bits (p-bits) are stochastic hardware elements whose output probability can be tuned by an input bias, offering a route to energy-efficient architectures that exploit, rather than suppress, fluctuations. Here we report p-bit generation in an organic memristive device, establishing polymers as the first class of soft-matter systems to realize probabilistic hardware. The active element is a dithieno[3,2-b:2',3'-d]pyrrole (DTP)-backbone polymer with pendant triphenylamine (TPA) group…

Atomistic insights into hydrogen migration in IGZO from machine-learning interatomic potential: linking atomic diffusion to device performance
Hyunsung Cho, Minseok Moon, Jaehoon Kim, Eunkyung Koh, Hyeon-Deuk Kim, Rokyeon Kim, Gyehyun Park, Seungwu Han, Youngho Kang
https://arxiv.org/abs/2508.19674…

Atomistic insights into hydrogen migration in IGZO from machine-learning interatomic potential: linking atomic diffusion to device performance
Understanding hydrogen diffusion is critical for improving the reliability and performance of oxide thin-film transistors (TFTs), where hydrogen plays a key role in carrier modulation and bias instability. In this work, we investigate hydrogen diffusion in amorphous IGZO ($a$-IGZO) and $c$-axis aligned crystalline IGZO (CAAC-IGZO) using machine learning interatomic potential molecular dynamics (MLIP-MD) simulations. We construct accurate phase-specific MLIPs by fine-tuning SevenNet-0, a univers…

Probing Partonic Evolution and Hadronization via Balance Functions and Correlations of Charmed Hadrons
Oveis Sheibani, Claude Pruneau, Victor Gonzalez, Sumit Basu, Alexandru Florin Dobrin, Yash Patley, Basanta Nandi, Sadhana Dash
https://arxiv.org/abs/2507.21014

Probing Partonic Evolution and Hadronization via Balance Functions and Correlations of Charmed Hadrons
Predictions of charm correlation functions and more specifically balance functions are presented in proton--proton (pp) collisions at sqrt(s_NN) = 13 TeV based on the PYTHIA 8.3 event generator. Correlations are computed for identical and cross-species charmed hadrons in both minimum bias and high-pT biased collisions. We study the strength of correlations as a function of the number of balanced flavors and investigate the impact of variations of PYTHIA parameters controlling the Lund string fr…

Revisiting the adiabatic limit in ballistic multiterminal Josephson junctions
R\'egis M\'elin, Asmaul Smitha Rashid, Romain Danneau, Morteza Kayyalha
https://arxiv.org/abs/2508.17367

Revisiting the adiabatic limit in ballistic multiterminal Josephson junctions
Motivated by recent experiments on multiterminal Josephson junctions (MJJs) that probe different ranges of the size and bias voltage parameters, we introduce a two-dimensional (2D) cross-over diagram to map the relationship between device dimension (x-axis) and bias voltage (y-axis). This cross-over diagram conveniently separates the different physical regimes of the devices. This framework is used to explore the regime of increasing bias voltage in large-scale devices near the x-axis, where th…

Multi-Resolution Training-Enhanced Kolmogorov-Arnold Networks for Multi-Scale PDE Problems
Yu-Sen Yang, Ling Guo, Xiaodan Ren
https://arxiv.org/abs/2507.19888 https://

Multi-Resolution Training-Enhanced Kolmogorov-Arnold Networks for Multi-Scale PDE Problems
Multi-scale PDE problems present significant challenges in scientific computing. While conventional MLP-based deep learning methods exhibit spectral bias in resolving multi-scale features, the physics-informed Kolmogorov-Arnold network (PIKAN) mitigates this issue through its novel architecture, demonstrating certain advantages. On the other hand, insights from the information bottleneck theory suggest that high-resolution training points are essential for these hybrid methods to accurately cap…

KI-Systeme bevorzugen eigene Texte: Studie warnt vor "Anti-Human-Bias"
Wissenschaftler haben nachgewiesen, dass Large Language Models Inhalte anderer KI-Systeme bevorzugen. Was Menschen daraus lernen können.

$\Sigma^{ }$ production in pp collisions at $\sqrt{s} = 13$ TeV
ALICE Collaboration
https://arxiv.org/abs/2508.20808 https://arxiv.org/pdf/2508.20808

$Σ^{+}$ production in pp collisions at $\sqrt{s} = 13$ TeV
The measurement of $Σ^{+}$ production in pp collisions at $\sqrt{s} = 13$ TeV is presented. The measurement is performed at midrapidity in both minimum-bias and high-multiplicity pp collisions at $\sqrt{s} = 13$ TeV. The $Σ^{+}$ is reconstructed via its weak-decay topology in the decay channel $Σ^{+} \rightarrow {\rm p} + π^{0}$ with $π^{0} \rightarrow γ+ γ$. In a novel approach, the neutral pion is reconstructed by combining photons that convert in the detector material with photons mea…

#SteadySupporter
Wie neutral sind KI-Systeme bei der medizinischen Diagnostik?
Eine neue Studie zeigt, dass selbst auf Expertenniveau arbeitende Systeme #Krankheiten übersehen und dabei marginalisierte Gruppen benachteiligen können.

Bias in der Medizin: Wenn KI-Röntgen-Diagnostik nicht neutral ist
Wie fair ist KI in der Medizin wirklich? Diese Studie offenbart Verzerrungen in der Diagnose marginalisierter Gruppen.

Representative Random Sampling of Chemical Space
Diego J. Monterrubio-Chanca, Guido Falk von Rudorff
https://arxiv.org/abs/2508.20609 https://arxiv.org/pdf…

Representative Random Sampling of Chemical Space
The overwhelming majority of molecules remains unexplored. This is mostly due to the sheer number of them, which prohibits any enumeration of chemical space, the set of all such molecules. In practice, only subsets of chemical space are considered, but those subsets exhibit substantial bias, prohibiting data-driven characterization of chemical space itself. In this work, we provide a method produce unbiased representative random samples of chemical space without enumeration of constituent molec…

$\mathcal{PT}$-symmetric two-photon quantum Rabi models
Yi-Cheng Wang, Jiong Li, Qing-Hu Chen
https://arxiv.org/abs/2507.20508 https://arxiv.org/pdf/2507.2…

$\mathcal{PT}$-symmetric two-photon quantum Rabi models
We investigate two non-Hermitian two-photon quantum Rabi models (tpQRM) that exhibit $\mathcal{PT}$ symmetry: the biased tpQRM (btpQRM), in which the qubit bias is purely imaginary, and the dissipative tpQRM (dtpQRM), where the two-photon coupling is made imaginary to introduce dissipation. For both models, we derive exact solutions by employing Bogoliubov transformations. In the btpQRM, we identify spectral collapse at a critical coupling strength, with accompanying $\mathcal{PT}$ symmetry bre…

FlowDrive: moderated flow matching with data balancing for trajectory planning
Lingguang Wang, \"Omer \c{S}ahin Ta\c{s}, Marlon Steiner, Christoph Stiller
https://arxiv.org/abs/2509.21961

FlowDrive: moderated flow matching with data balancing for trajectory planning
Learning-based planners are sensitive to the long-tailed distribution of driving data. Common maneuvers dominate datasets, while dangerous or rare scenarios are sparse. This imbalance can bias models toward the frequent cases and degrade performance on critical scenarios. To tackle this problem, we compare balancing strategies for sampling training data and find reweighting by trajectory pattern an effective approach. We then present FlowDrive, a flow-matching trajectory planner that learns a c…

Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models
Pooja S. B. Rao, Laxminarayen Nagarajan Venkatesan, Mauro Cherubini, Dinesh Babu Jayagopi
https://arxiv.org/abs/2508.16673

Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models
Artificial Intelligence (AI) is increasingly used in hiring, with large language models (LLMs) having the potential to influence or even make hiring decisions. However, this raises pressing concerns about bias, fairness, and trust, particularly across diverse cultural contexts. Despite their growing role, few studies have systematically examined the potential biases in AI-driven hiring evaluation across cultures. In this study, we conduct a systematic analysis of how LLMs assess job interviews …

A profile of Wikipedia co-founder Larry Sanger, who left in 2002 and whose claims that Wikipedia has a liberal bias are fueling the right's campaign against it (Will Oremus/Washington Post)

A Wikipedia cofounder is fueling the right’s campaign against it
Larry Sanger’s claims of a liberal slant and mismanagement at the world’s dominant online encyclopedia are being enthusiastically embraced on the right.

Position Bias Mitigates Position Bias:Mitigate Position Bias Through Inter-Position Knowledge Distillation
Yifei Wang, Feng Xiong, Yong Wang, Linjing Li, Xiangxiang Chu, Daniel Dajun Zeng
https://arxiv.org/abs/2508.15709

Position Bias Mitigates Position Bias:Mitigate Position Bias Through Inter-Position Knowledge Distillation
Positional bias (PB), manifesting as non-uniform sensitivity across different contextual locations, significantly impairs long-context comprehension and processing capabilities. While prior work seeks to mitigate PB through modifying the architectures causing its emergence, significant PB still persists. To address PB effectively, we introduce \textbf{Pos2Distill}, a position to position knowledge distillation framework. Pos2Distill transfers the superior capabilities from advantageous position…

Opening the Black Box: Interpretable Remedies for Popularity Bias in Recommender Systems
Parviz Ahmadov, Masoud Mansoury
https://arxiv.org/abs/2508.17297 https://

Opening the Black Box: Interpretable Remedies for Popularity Bias in Recommender Systems
Popularity bias is a well-known challenge in recommender systems, where a small number of popular items receive disproportionate attention, while the majority of less popular items are largely overlooked. This imbalance often results in reduced recommendation quality and unfair exposure of items. Although existing mitigation techniques address this bias to some extent, they typically lack transparency in how they operate. In this paper, we propose a post-hoc method using a Sparse Autoencoder (S…

A profile of Wikipedia co-founder Larry Sanger, who left in 2002 and whose claims that Wikipedia has a liberal bias are fueling the right's campaign against it (Will Oremus/Washington Post)

A Wikipedia cofounder is fueling the right’s campaign against it
Larry Sanger’s claims of a liberal slant and mismanagement at the world’s dominant online encyclopedia are being enthusiastically embraced on the right.

Interpretable Scalar-on-Image Linear Regression Models via the Generalized Dantzig Selector
Sijia Liao, Xiaoxiao Sun, Ning Hao, Hao Helen Zhang
https://arxiv.org/abs/2508.20278 …

Interpretable Scalar-on-Image Linear Regression Models via the Generalized Dantzig Selector
The scalar-on-image regression model examines the association between a scalar response and a bivariate function (e.g., images) through the estimation of a bivariate coefficient function. Existing approaches often impose smoothness constraints to control the bias-variance trade-off, and thus prevent overfitting. However, such assumptions can hinder interpretability, especially when only certain regions of an image influence changes in the response. In such a scenario, interpretability can be be…

Crosslisted article(s) found for cs.GT. https://arxiv.org/list/cs.GT/new
[1/1]:
- Guarding Against Malicious Biased Threats (GAMBiT) Experiments: Revealing Cognitive Bias in Human...
Beltz, Doty, Fonken, Gurney, Israelsen, Lau, Marsella, Thomas, Trent, Wu, Yang, Zhu

Clustering of DESI galaxies split by thermal Sunyaev-Zeldovich effect
M. Rashkovetskyi, D. J. Eisenstein, J. Aguilar, S. Ahlen, A. Anand, D. Bianchi, D. Brooks, F. J. Castander, T. Claybaugh, A. Cuceu, K. S. Dawson, A. de la Macorra, Arjun Dey, P. Doel, S. Ferraro, A. Font-Ribera, J. E. Forero-Romero, E. Gazta\~naga, G. Gutierrez, H. K. Herrera-Alcantar, K. Honscheid, C. Howlett, M. Ishak, R. Joyce, R. Kehoe, T. Kisner, A. Kremin, O. Lahav, A. Lambert, M. Landriau, M. Manera, R. Miquel…

Clustering of DESI galaxies split by thermal Sunyaev-Zeldovich effect
The thermal Sunyaev-Zeldovich (tSZ) effect is associated with galaxy clusters - extremely large and dense structures tracing the dark matter with a higher bias than isolated galaxies. We propose to use the tSZ data to separate galaxies from redshift surveys into distinct subpopulations corresponding to different densities and biases independently of the redshift survey systematics. Leveraging the information from different environments, as in density-split and density-marked clustering, is know…

A bias test for heteroscedastic linear least-squares regression
Eric Blankmeyer
https://arxiv.org/abs/2508.15969 https://arxiv.org/pdf/2508.15969

A bias test for heteroscedastic linear least-squares regression
Linear least squares regression is subject to bias due to an omitted variable, a mismeasured regressor, or simultaneity. A simple test to detect the bias is proposed and explored in simulation and in real data sets.

Toward Responsible ASR for African American English Speakers: A Scoping Review of Bias and Equity in Speech Technology
Jay L. Cunningham, Adinawa Adjagbodjou, Jeffrey Basoah, Jainaba Jawara, Kowe Kadoma, Aaleyah Lewis
https://arxiv.org/abs/2508.18288

Toward Responsible ASR for African American English Speakers: A Scoping Review of Bias and Equity in Speech Technology
This scoping literature review examines how fairness, bias, and equity are conceptualized and operationalized in Automatic Speech Recognition (ASR) and adjacent speech and language technologies (SLT) for African American English (AAE) speakers and other linguistically diverse communities. Drawing from 44 peer-reviewed publications across Human-Computer Interaction (HCI), Machine Learning/Natural Language Processing (ML/NLP), and Sociolinguistics, we identify four major areas of inquiry: (1) how…

BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding
Xuan-Bac Nguyen, Thanh-Dat Truong, Pawan Sinha, Khoa Luu
https://arxiv.org/abs/2508.18187 https:…

BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding
Memory decay makes it harder for the human brain to recognize visual objects and retain details. Consequently, recorded brain signals become weaker, uncertain, and contain poor visual context over time. This paper presents one of the first vision-learning approaches to address this problem. First, we statistically and experimentally demonstrate the existence of inconsistency in brain signals and its impact on the Vision-Brain Understanding (VBU) model. Our findings show that brain signal repres…

Mitigating Strategy-Selection Bias in Reasoning for More Effective Test-Time Scaling
Zongqian Wu, Baoduo Xu, Tianyu Li, Zhu Sun, Xiaofeng Zhu, Lei Feng
https://arxiv.org/abs/2509.17905

Mitigating Strategy-Selection Bias in Reasoning for More Effective Test-Time Scaling
Test-time scaling (TTS) has been shown to improve the performance of large language models (LLMs) by sampling and aggregating diverse reasoning paths. However, existing research has overlooked a critical issue: selection bias of reasoning strategies during scaling. Specifically, when generating reasoning processes, LLMs tend to follow certain strategies (e.g., algebraic solutions for math problems) while neglecting other valid alternatives (e.g., geometric solutions), resulting in insufficient …

Fourier Feature Networks for High-Fidelity Prediction of Perturbed Optical Fields
Joshua R. Jandrell, Mitchell A. Cox
https://arxiv.org/abs/2508.19751 https://

Fourier Feature Networks for High-Fidelity Prediction of Perturbed Optical Fields
Modelling the effects of perturbations on optical fields often requires learning highly oscillatory complex-valued functions. Standard multi-layer perceptrons (MLPs) struggle with this task due to an inherent spectral bias, preventing them from fitting high-frequency sinusoids. To overcome this, we incorporate Fourier features - a set of predefined sinusoids dependent on the perturbation - as an additional network input. This reframes the learning problem from approximating a complex function t…

Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models
Ke Zhou, Marios Constantinides, Daniele Quercia
https://arxiv.org/abs/2508.19269 https://

Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models
Large language models (LLMs) are often trained on data that reflect WEIRD values: Western, Educated, Industrialized, Rich, and Democratic. This raises concerns about cultural bias and fairness. Using responses to the World Values Survey, we evaluated five widely used LLMs: GPT-3.5, GPT-4, Llama-3, BLOOM, and Qwen. We measured how closely these responses aligned with the values of the WEIRD countries and whether they conflicted with human rights principles. To reflect global diversity, we compar…

Which Cultural Lens Do Models Adopt? On Cultural Positioning Bias and Agentic Mitigation in LLMs
Yixin Wan, Xingrun Chen, Kai-Wei Chang
https://arxiv.org/abs/2509.21080 https://…

Which Cultural Lens Do Models Adopt? On Cultural Positioning Bias and Agentic Mitigation in LLMs
Large language models (LLMs) have unlocked a wide range of downstream generative applications. However, we found that they also risk perpetuating subtle fairness issues tied to culture, positioning their generations from the perspectives of the mainstream US culture while demonstrating salient externality towards non-mainstream ones. In this work, we identify and systematically investigate this novel culture positioning bias, in which an LLM's default generative stance aligns with a mainstream …

From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM
Olga Fink, Ismail Nejjar, Vinay Sharma, Keivan Faghih Niresi, Han Sun, Hao Dong, Chenghao Xu, Amaury Wei, Arthur Bizzi, Raffael Theiler, Yuan Tian, Leandro Von Krannichfeldt, Zhan Ma, Sergei Garmaev, Zepeng Zhang, Mengjie Zhao
https://arxiv.org/abs/…

From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM
Prognostics and Health Management ensures the reliability, safety, and efficiency of complex engineered systems by enabling fault detection, anticipating equipment failures, and optimizing maintenance activities throughout an asset lifecycle. However, real-world PHM presents persistent challenges: sensor data is often noisy or incomplete, available labels are limited, and degradation behaviors and system interdependencies can be highly complex and nonlinear. Physics-informed machine learning ha…

Angle-dependent chiral tunneling in biased twisted bilayer graphene
Nadia Benlakhouy, El Mustapha Feddi, Abdelouahed El Fatimy
https://arxiv.org/abs/2507.20391 https://

Angle-dependent chiral tunneling in biased twisted bilayer graphene
In twisted bilayer graphene (TBLG), chiral tunneling can be tuned by parameters such as the twist angle, barrier height, and Fermi energy. This differs from the tunneling behavior observed in monolayer and Bernal bilayer graphene, where electrons either pass completely through or are fully blocked due to the Klein paradox. Here we investigate the effect of a perpendicular interlayer bias on electron tunneling through electrostatic barriers in TBLG. Using a dual-gated model, which controls the c…

DoubleGen: Debiased Generative Modeling of Counterfactuals
Alex Luedtke, Kenji Fukumizu
https://arxiv.org/abs/2509.16842 https://arxiv.org/pdf/2509.16842…

DoubleGen: Debiased Generative Modeling of Counterfactuals
Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who receive the intervention and those who do not. Misspecification bias arises when methods attempt to address confounding through estimation of an auxiliary model, but specify it incorrectly. We introduce DoubleGen, a doubly robust framework that modifies generative modeling training objectives to mitigate these biases. Th…

A Multiplicative Instrumental Variable Model for Data Missing Not-at-Random
Yunshu Zhang, Chan Park, Jiewen Liu, Yonghoon Lee, Mengxin Yu, James M. Robins, Eric J. Tchetgen Tchetgen
https://arxiv.org/abs/2509.22499

A Multiplicative Instrumental Variable Model for Data Missing Not-at-Random
Instrumental variable (IV) methods offer a valuable approach to account for outcome data missing not-at-random. A valid missing data instrument is a measured factor which (i) predicts the nonresponse process and (ii) is independent of the outcome in the underlying population. For point identification, all existing IV methods for missing data including the celebrated Heckman selection model, a priori restrict the extent of selection bias on the outcome scale, therefore potentially understating u…

Debiasing inference in large-scale structure with non-flat volume measures
Alexander Reeves, Pierre Zhang, Henry Zheng
https://arxiv.org/abs/2507.20991 https://

Debiasing inference in large-scale structure with non-flat volume measures
Increasingly large parameter spaces, used to more accurately model precision observables in physics, can paradoxically lead to large deviations in the inferred parameters of interest -- a bias known as volume projection effects -- when marginalising over many nuisance parameters. For posterior distributions that admit a Laplace expansion, we show that this artefact of Bayesian inference can be mitigated by defining expectation values with respect to a non-flat volume measure, such that the post…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/5]:
- PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
Kwonyoung Kim, Jungin Park, Jiyoung Lee, Dongbo Min, Kwanghoon Sohn

AI Ethics Education in India: A Syllabus-Level Review of Computing Courses
Anshu M Mittal, P D Parthasarathy, Swaroop Joshi
https://arxiv.org/abs/2509.22329 https://

AI Ethics Education in India: A Syllabus-Level Review of Computing Courses
The pervasive integration of artificial intelligence (AI) across domains such as healthcare, governance, finance, and education has intensified scrutiny of its ethical implications, including algorithmic bias, privacy risks, accountability, and societal impact. While ethics has received growing attention in computer science (CS) education more broadly, the specific pedagogical treatment of {AI ethics} remains under-examined. This study addresses that gap through a large-scale analysis of 3,395 …

Non-equilibrium Dynamics of Two-level Systems directly after Cryogenic Alternating Bias
V. Iaia, E. S. Joseph, S. Im, N. Hagopian, S. O'Kelley, C. Kim, N. Materise, S. Patra, V. Lordi, M. A. Eriksson, P. M. Voyles, K. G. Ray, Y. J. Rosen
https://arxiv.org/abs/2509.19223

A Non-Parametric Choice Model That Learns How Users Choose Between Recommended Options
Thorsten Krause, Harrie Oosterhuis
https://arxiv.org/abs/2507.20035 https://

A Non-Parametric Choice Model That Learns How Users Choose Between Recommended Options
Choice models predict which items users choose from presented options. In recommendation settings, they can infer user preferences while countering exposure bias. In contrast with traditional univariate recommendation models, choice models consider which competitors appeared with the chosen item. This ability allows them to distinguish whether a user chose an item due to preference, i.e., they liked it; or competition, i.e., it was the best available option. Each choice model assumes specific u…

Closed-form $\ell_r$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $\ell_p$ bias
Shuofeng Zhang, Ard Louis
https://arxiv.org/abs/2509.21181

Closed-form $\ell_r$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $\ell_p$ bias
For overparameterized linear regression with isotropic Gaussian design and minimum-$\ell_p$ interpolator $p\in(1,2]$, we give a unified, high-probability characterization for the scaling of the family of parameter norms $ \\{ \lVert \widehat{w_p} \rVert_r \\}_{r \in [1,p]} $ with sample size. We solve this basic, but unresolved question through a simple dual-ray analysis, which reveals a competition between a signal *spike* and a *bulk* of null coordinates in $X^\top Y$, yielding closed-form …

BEFT: Bias-Efficient Fine-Tuning of Language Models
Baichuan Huang, Ananth Balashankar, Amir Aminifar
https://arxiv.org/abs/2509.15974 https://arxiv.org/pd…

BEFT: Bias-Efficient Fine-Tuning of Language Models
Fine-tuning all-bias-terms stands out among various parameter-efficient fine-tuning (PEFT) techniques, owing to its out-of-the-box usability and competitive performance, especially in low-data regimes. Bias-only fine-tuning has the potential for unprecedented parameter efficiency. However, the link between fine-tuning different bias terms (i.e., bias terms in the query, key, or value projections) and downstream performance remains unclear. The existing approaches, e.g., based on the magnitude o…

STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning
Chenghao Wu, Ruiyang Ren, Junjie Zhang, Ruirui Wang, Zhongrui Ma, Qi Ye, Wayne Xin Zhao
https://arxiv.org/abs/2508.18812

STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning
While modern recommender systems are instrumental in navigating information abundance, they remain fundamentally limited by static user modeling and reactive decision-making paradigms. Current large language model (LLM)-based agents inherit these shortcomings through their overreliance on heuristic pattern matching, yielding recommendations prone to shallow correlation bias, limited causal inference, and brittleness in sparse-data scenarios. We introduce STARec, a slow-thinking augmented agent …

Improving Recommendation Fairness via Graph Structure and Representation Augmentation
Tongxin Xu, Wenqiang Liu, Chenzhong Bin, Cihan Xiao, Zhixin Zeng, Tianlong Gu
https://arxiv.org/abs/2508.19547

Improving Recommendation Fairness via Graph Structure and Representation Augmentation
Graph Convolutional Networks (GCNs) have become increasingly popular in recommendation systems. However, recent studies have shown that GCN-based models will cause sensitive information to disseminate widely in the graph structure, amplifying data bias and raising fairness concerns. While various fairness methods have been proposed, most of them neglect the impact of biased data on representation learning, which results in limited fairness improvement. Moreover, some studies have focused on con…

Sex-based Bias Inherent in the Dice Similarity Coefficient: A Model Independent Analysis for Multiple Anatomical Structures
Hartmut H\"antze, Myrthe Buser, Alessa Hering, Lisa C. Adams, Keno K. Bressem
https://arxiv.org/abs/2509.19778

Sex-based Bias Inherent in the Dice Similarity Coefficient: A Model Independent Analysis for Multiple Anatomical Structures
Overlap-based metrics such as the Dice Similarity Coefficient (DSC) penalize segmentation errors more heavily in smaller structures. As organ size differs by sex, this implies that a segmentation error of equal magnitude may result in lower DSCs in women due to their smaller average organ volumes compared to men. While previous work has examined sex-based differences in models or datasets, no study has yet investigated the potential bias introduced by the DSC itself. This study quantifies sex-b…

Probing Gender Bias in Multilingual LLMs: A Case Study of Stereotypes in Persian
Ghazal Kalhor, Behnam Bahrak
https://arxiv.org/abs/2509.20168 https://arxi…

Probing Gender Bias in Multilingual LLMs: A Case Study of Stereotypes in Persian
Multilingual Large Language Models (LLMs) are increasingly used worldwide, making it essential to ensure they are free from gender bias to prevent representational harm. While prior studies have examined such biases in high-resource languages, low-resource languages remain understudied. In this paper, we propose a template-based probing methodology, validated against real-world data, to uncover gender stereotypes in LLMs. As part of this framework, we introduce the Domain-Specific Gender Skew I…

Bias is a Math Problem, AI Bias is a Technical Problem: 10-year Literature Review of AI/LLM Bias Research Reveals Narrow [Gender-Centric] Conceptions of 'Bias', and Academia-Industry Gap
Sourojit Ghosh, Kyra Wilson
https://arxiv.org/abs/2508.11067

Bias is a Math Problem, AI Bias is a Technical Problem: 10-year Literature Review of AI/LLM Bias Research Reveals Narrow [Gender-Centric] Conceptions of 'Bias', and Academia-Industry Gap
The rapid development of AI tools and implementation of LLMs within downstream tasks has been paralleled by a surge in research exploring how the outputs of such AI/LLM systems embed biases, a research topic which was already being extensively explored before the era of ChatGPT. Given the high volume of research around the biases within the outputs of AI systems and LLMs, it is imperative to conduct systematic literature reviews to document throughlines within such research. In this paper, we c…

A Case Study of Balanced Query Recommendation on Wikipedia
Harshit Mishra, Sucheta Soundarajan
https://arxiv.org/abs/2508.20399 https://arxiv.org/pdf/2508.…

A Case Study of Balanced Query Recommendation on Wikipedia
Modern IR systems are an extremely important tool for seeking information. In addition to search, such systems include a number of query reformulation methods, such as query expansion and query recommendations, to provide high quality results. However, results returned by such methods sometimes exhibit undesirable or wrongful bias with respect to protected categories such as gender or race. Our earlier work considered the problem of balanced query recommendation, where instead of re-ranking a l…

A Unified Lagrangian Framework for Galaxy Clustering: Consistent Modeling of Bias, Redshift-Space Distortions, and Reconstruction
Naonori Sugiyama
https://arxiv.org/abs/2508.17331

A Unified Lagrangian Framework for Galaxy Clustering: Consistent Modeling of Bias, Redshift-Space Distortions, and Reconstruction
We present \emph{Unified Lagrangian Perturbation Theory} (ULPT), a perturbative framework for consistently modeling galaxy density fluctuations across real space, redshift space, and post-reconstruction fields. Unlike existing approaches that treat these cases separately, ULPT provides a single theoretical structure that incorporates the three essential coordinate mappings: the Lagrangian-to-Eulerian transformation, the real-to-redshift mapping induced by peculiar velocities, and the remapping …

Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity
Kyra Wilson, Sourojit Ghosh, Aylin Caliskan
https://arxiv.org/abs/2508.17465

Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity
Text-to-image generators (T2Is) are liable to produce images that perpetuate social stereotypes, especially in regards to race or skin tone. We use a comprehensive set of 93 stigmatized identities to determine that three versions of Stable Diffusion (v1.5, v2.1, and XL) systematically associate stigmatized identities with certain skin tones in generated images. We find that SD XL produces skin tones that are 13.53% darker and 23.76% less red (both of which indicate higher likelihood of societal…

Frozen in Time: Parameter-Efficient Time Series Transformers via Reservoir-Induced Feature Expansion and Fixed Random Dynamics
Pradeep Singh, Mehak Sharma, Anupriya Dey, Balasubramanian Raman
https://arxiv.org/abs/2508.18130

Frozen in Time: Parameter-Efficient Time Series Transformers via Reservoir-Induced Feature Expansion and Fixed Random Dynamics
Transformers are the de-facto choice for sequence modelling, yet their quadratic self-attention and weak temporal bias can make long-range forecasting both expensive and brittle. We introduce FreezeTST, a lightweight hybrid that interleaves frozen random-feature (reservoir) blocks with standard trainable Transformer layers. The frozen blocks endow the network with rich nonlinear memory at no optimisation cost; the trainable layers learn to query this memory through self-attention. The design cu…

Bias in the Picture: Benchmarking VLMs with Social-Cue News Images and LLM-as-Judge Assessment
Aravind Narayanan, Vahid Reza Khazaie, Shaina Raza
https://arxiv.org/abs/2509.19659

Bias in the Picture: Benchmarking VLMs with Social-Cue News Images and LLM-as-Judge Assessment
Large vision-language models (VLMs) can jointly interpret images and text, but they are also prone to absorbing and reproducing harmful social stereotypes when visual cues such as age, gender, race, clothing, or occupation are present. To investigate these risks, we introduce a news-image benchmark consisting of 1,343 image-question pairs drawn from diverse outlets, which we annotated with ground-truth answers and demographic attributes (age, gender, race, occupation, and sports). We evaluate a…

Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM
Dariia Puhach, Amir H. Payberah, \'Eva Sz\'ekely
https://arxiv.org/abs/2508.13603 h…

Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM
Similar to text-based Large Language Models (LLMs), Speech-LLMs exhibit emergent abilities and context awareness. However, whether these similarities extend to gender bias remains an open question. This study proposes a methodology leveraging speaker assignment as an analytic tool for bias investigation. Unlike text-based models, which encode gendered associations implicitly, Speech-LLMs must produce a gendered voice, making speaker selection an explicit bias cue. We evaluate Bark, a Text-to-Sp…

STDiff: A State Transition Diffusion Framework for Time Series Imputation in Industrial Systems
Gary Simethy, Daniel Ortiz-Arroyo, Petar Durdevic
https://arxiv.org/abs/2508.19011

STDiff: A State Transition Diffusion Framework for Time Series Imputation in Industrial Systems
Most deep learning methods for imputing missing values treat the task as completing patterns within a fixed time window. This assumption often fails in industrial systems, where dynamics are driven by control actions, are highly non-stationary, and can experience long, uninterrupted gaps. We propose STDiff, which reframes imputation as learning how the system evolves from one state to the next. STDiff uses a conditional denoising diffusion model with a causal bias aligned to control theory, gen…

Reading Between the Lines: A Study of Thematic Bias in Book Recommender Systems
Nityaa Kalra, Savvina Daniil
https://arxiv.org/abs/2508.15643 https://arxiv…

Reading Between the Lines: A Study of Thematic Bias in Book Recommender Systems
Recommender systems help users discover new content, but can also reinforce existing biases, leading to unfair exposure and reduced diversity. This paper introduces and investigates thematic bias in book recommendations, defined as a disproportionate favouring or neglect of certain book themes. We adopt a multi-stage bias evaluation framework using the Book-Crossing dataset to evaluate thematic bias in recommendations and its impact on different user groups. Our findings show that thematic bi…

Text Takes Over: A Study of Modality Bias in Multimodal Intent Detection
Ankan Mullick, Saransh Sharma, Abhik Jana, Pawan Goyal
https://arxiv.org/abs/2508.16122 https://

Text Takes Over: A Study of Modality Bias in Multimodal Intent Detection
The rise of multimodal data, integrating text, audio, and visuals, has created new opportunities for studying multimodal tasks such as intent detection. This work investigates the effectiveness of Large Language Models (LLMs) and non-LLMs, including text-only and multi-modal models, in the multimodal intent detection task. Our study reveals that Mistral-7B, a text-only LLM, outperforms most competitive multimodal models by approximately 9% on MIntRec-1 and 4% on MIntRec2.0 datasets. This perfor…

EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
Haodi Zhong, Liuxin Zou, Di Wang, Bo Wang, Zhenxing Niu, Quan Wang
https://arxiv.org/abs/2508.15378 …

EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
Dynamic graph-level embedding aims to capture structural evolution in networks, which is essential for modeling real-world scenarios. However, existing methods face two critical yet under-explored issues: Structural Visit Bias, where random walk sampling disproportionately emphasizes high-degree nodes, leading to redundant and noisy structural representations; and Abrupt Evolution Blindness, the failure to effectively detect sudden structural changes due to rigid or overly simplistic temporal m…

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/2]:
- Toward Responsible ASR for African American English Speakers: A Scoping Review of Bias and Equity...
Jay L. Cunningham, Adinawa Adjagbodjou, Jeffrey Basoah, Jainaba Jawara, Kowe Kadoma, Aaleyah Lewis

Investigating Bias: A Multilingual Pipeline for Generating, Solving, and Evaluating Math Problems with LLMs
Mariam Mahran, Katharina Simbeck
https://arxiv.org/abs/2509.17701 htt…

Investigating Bias: A Multilingual Pipeline for Generating, Solving, and Evaluating Math Problems with LLMs
Large Language Models (LLMs) are increasingly used for educational support, yet their response quality varies depending on the language of interaction. This paper presents an automated multilingual pipeline for generating, solving, and evaluating math problems aligned with the German K-10 curriculum. We generated 628 math exercises and translated them into English, German, and Arabic. Three commercial LLMs (GPT-4o-mini, Gemini 2.5 Flash, and Qwen-plus) were prompted to produce step-by-step solu…