Tootfinder

Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases
Bufan Gao, Elisa Kreiss
https://arxiv.org/abs/2509.04373 https://

Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases
As LLMs are increasingly applied in socially impactful settings, concerns about gender bias have prompted growing efforts both to measure and mitigate such bias. These efforts often rely on evaluation tasks that differ from natural language distributions, as they typically involve carefully constructed task prompts that overtly or covertly signal the presence of gender bias-related content. In this paper, we examine how signaling the evaluative purpose of a task impacts measured gender bias in …

The Bias of Subspace-based Data-Driven Predictive Control
Keith Moffat, Florian D\"orfler, Alessandro Chiuso
https://arxiv.org/abs/2507.02468 https://…

The Bias of Subspace-based Data-Driven Predictive Control
This paper quantifies and addresses the bias of subspace-based Data-Driven Predictive Control (DDPC) for linear, time-invariant (LTI) systems. The primary focus is the bias that arises when the training data is gathered with a feedback controller in closed-loop with the system. First, the closed-loop bias of Subspace Predictive Control is quantified using the training data innovations. Next, the bias of direct, subspace-based DDPC methods DeePC and $γ$-DDPC is shown to consist of two parts--th…

Temporal Exposure Dependence Bias in Vaccine Efficacy Trials
Hiroyasu Ando, A. James O'Malley, Akihiro Nishi
https://arxiv.org/abs/2509.03476 https://a…

Temporal Exposure Dependence Bias in Vaccine Efficacy Trials
Using time-to-event methods such as Cox proportional hazards models, it is well established that unmeasured heterogeneity in exposure or infection risk can lead to downward bias in point estimates of the per-contact vaccine efficacy (VE) in infectious disease trials. In this study, we explore an unreported source of bias-arising from temporally correlated exposure status-that is typically unmeasured and overlooked in standard analyses. Although this form of bias can plausibly affect a wide rang…

Systematic Evaluation of Attribution Methods: Eliminating Threshold Bias and Revealing Method-Dependent Performance Patterns
Serra Aksoy
https://arxiv.org/abs/2509.03176 https:/…

Systematic Evaluation of Attribution Methods: Eliminating Threshold Bias and Revealing Method-Dependent Performance Patterns
Attribution methods explain neural network predictions by identifying influential input features, but their evaluation suffers from threshold selection bias that can reverse method rankings and undermine conclusions. Current protocols binarize attribution maps at single thresholds, where threshold choice alone can alter rankings by over 200 percentage points. We address this flaw with a threshold-free framework that computes Area Under the Curve for Intersection over Union (AUC-IoU), capturing …

#KINutzen #Retröt
Können KI-Modelle für medizinische #Röntgenbilder unbewusst diskriminieren? Eine neue Studie zeigt, dass selbst auf Expertenniveau arbeitende Systeme wie

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.

Exploring Gender Bias Beyond Occupational Titles
Ahmed Sabir, Rajesh Sharama
https://arxiv.org/abs/2507.02679 https://arxiv.org/pdf/2…

Exploring Gender Bias Beyond Occupational Titles
In this work, we investigate the correlation between gender and contextual biases, focusing on elements such as action verbs, object nouns, and particularly on occupations. We introduce a novel dataset, GenderLexicon, and a framework that can estimate contextual bias and its related gender bias. Our model can interpret the bias with a score and thus improve the explainability of gender bias. Also, our findings confirm the existence of gender biases beyond occupational stereotypes. To validate o…

Data Bias in Human Mobility is a Universal Phenomenon but is Highly Location-specific
Katinka den Nijs, Elisa Omodei, Vedran Sekara
https://arxiv.org/abs/2508.00149 https://

Data Bias in Human Mobility is a Universal Phenomenon but is Highly Location-specific
Large-scale human mobility datasets play increasingly critical roles in many algorithmic systems, business processes and policy decisions. Unfortunately there has been little focus on understanding bias and other fundamental shortcomings of the datasets and how they impact downstream analyses and prediction tasks. In this work, we study `data production', quantifying not only whether individuals are represented in big digital datasets, but also how they are represented in terms of how much data…

Gravity Well Echo Chamber Modeling With An LLM-Based Confirmation Bias Model
Joseph Jackson, Georgiy Lapin, Jeremy E. Thompson
https://arxiv.org/abs/2509.03832 https://

Gravity Well Echo Chamber Modeling With An LLM-Based Confirmation Bias Model
Social media echo chambers play a central role in the spread of misinformation, yet existing models often overlook the influence of individual confirmation bias. An existing model of echo chambers is the "gravity well" model, which creates an analog between echo chambers and spatial gravity wells. We extend this established model by introducing a dynamic confirmation bias variable that adjusts the strength of pull based on a user's susceptibility to belief-reinforcing content. This variable is …

This https://arxiv.org/abs/2311.14590 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hepp…

Stability of domain walls with inflationary fluctuations under potential bias, and gravitational wave signatures
A recent study has shown that domain walls with inflationary initial fluctuations exhibit remarkable stability against population bias due to long-range correlations, challenging the claims of prior research. In this paper, we study the dynamics of these domain walls in the presence of potential bias and show that they collapse with a lifetime several times longer than that due to thermal fluctuations. This is interpreted as a difference in the average distance between domain walls, leading us …

Switchable Exchange Bias Resulting from Correlated Domain Structures in Orthogonally Coupled Antiferromagnet/Ferromagnet van der Waals Heterostructures
Aditya Kumar, Sadeed Hameed, Thibaud Denneulin, Aravind Puthirath Balan, Joseph Vas, Kilian Leutner, Lei Gao, Olena Gomonay, Jairo Sinova, Rafal E. Dunin-Borkowski, Mathias Kl\"aui
https://

Switchable Exchange Bias Resulting from Correlated Domain Structures in Orthogonally Coupled Antiferromagnet/Ferromagnet van der Waals Heterostructures
Van der Waals (vdW) magnetic heterostructures offer a versatile platform for engineering interfacial spin interactions with atomic precision, enabling nontrivial spin textures and dynamic behaviors. In this work, we report robust asymmetric magnetization reversal and exchange bias in Fe3GeTe2 (FGT), driven by interlayer exchange coupling with the A-type antiferromagnet CrSBr. Despite the orthogonal magnetic anisotropies out-of-plane easy axis in FGT and in-plane in CrSBr, we observe a strong in…

Meta’s banning of two anti-Zionist comedians from Instagram is the latest example of Big Tech’s deep anti-Palestinian bias
#meta #facebook #instagram

IT’S BASICALLY THE ONLY PLACE ON THE INTERNET THAT DOESN’T FUNCTION AS A CONFIRMATION BIAS MACHINE.
https://www.theverge.com/cs/features/717322/wikipedia-attacks-neutrality-history-jimmy-wales

How Wikipedia survives while the rest of the internet breaks
How the world’s largest encyclopedia became the factual foundation of the web, but now it’s under attack from the right wing, tech billionaires, and AI.

When LLMs Disagree: Diagnosing Relevance Filtering Bias and Retrieval Divergence in SDG Search
William A. Ingram, Bipasha Banerjee, Edward A. Fox
https://arxiv.org/abs/2507.02139 …

When LLMs Disagree: Diagnosing Relevance Filtering Bias and Retrieval Divergence in SDG Search
Large language models (LLMs) are increasingly used to assign document relevance labels in information retrieval pipelines, especially in domains lacking human-labeled data. However, different models often disagree on borderline cases, raising concerns about how such disagreement affects downstream retrieval. This study examines labeling disagreement between two open-weight LLMs, LLaMA and Qwen, on a corpus of scholarly abstracts related to Sustainable Development Goals (SDGs) 1, 3, and 7. We is…

Law360 now requires every story go through an AI-powered "bias" detection tool before publication after a LexisNexis exec accused the newsroom of liberal bias (Andrew Deck/Nieman Lab)
https://www.niemanlab.org/2025/07/law360-m

Hot #cosmology papers ...
The Perfect Host - JWST Cepheid Observations in a Background-Free SN Ia Host Confirm No Bias in Hubble-Constant Measurements: https://arxiv.org/abs/2509.01667
Glimmers in the Cosmic Dawn - On the Photometrically Determined Black Hole Mass to Stellar Mass Relation Across Cosmic Time: https://arxiv.org/abs/2508.15905
The coherent satellite velocity field around the interacting spiral galaxy pair NGC5713/19 - signature of two galaxy groups merging: https://academic.oup.com/mnras/article/542/1/62/8215207?login=false
Looking beyond lambda: https://arxiv.org/abs/2509.00359

BSI veröffentlicht Whitepaper zum Bias in der KI
Wenn sich KI-Systeme nicht so verhalten, wie erwünscht, stecken oft Verzerrungen in den Daten dahinter. Das BSI erklärt, wie man den Bias im System erkennt.
https://www.

Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models
Riccardo Cantini, Nicola Gabriele, Alessio Orsino, Domenico Talia
https://arxiv.org/abs/2507.02799 …

Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models
Reasoning Language Models (RLMs) have gained traction for their ability to perform complex, multi-step reasoning tasks through mechanisms such as Chain-of-Thought (CoT) prompting or fine-tuned reasoning traces. While these capabilities promise improved reliability, their impact on robustness to social biases remains unclear. In this work, we leverage the CLEAR-Bias benchmark, originally designed for Large Language Models (LLMs), to investigate the adversarial robustness of RLMs to bias elicitat…

Differentiable Fuzzy Cosmic-Web for Field Level Inference
P. Rossell\'o, F. -S. Kitaura, D. Forero-S\'anchez, F. Sinigaglia, G. Favole
https://arxiv.org/abs/2506.03969

Differentiable Fuzzy Cosmic-Web for Field Level Inference
A comprehensive analysis of the cosmological large-scale structure derived from galaxy surveys involves field-level inference, which requires a forward modelling framework that simultaneously accounts for structure formation and tracer bias. While structure formation models are well-understood, the development of an effective field-level bias model remains imprecise, particularly in the context of tracer perturbation theory within Bayesian reconstruction methods, which we address in this work. …

Structure and Smoothness Constrained Dual Networks for MR Bias Field Correction
Dong Liang, Xingyu Qiu, Yuzhen Li, Wei Wang, Kuanquan Wang, Suyu Dong, Gongning Luo
https://arxiv.org/abs/2507.01326

Structure and Smoothness Constrained Dual Networks for MR Bias Field Correction
MR imaging techniques are of great benefit to disease diagnosis. However, due to the limitation of MR devices, significant intensity inhomogeneity often exists in imaging results, which impedes both qualitative and quantitative medical analysis. Recently, several unsupervised deep learning-based models have been proposed for MR image improvement. However, these models merely concentrate on global appearance learning, and neglect constraints from image structures and smoothness of bias field, le…

Strategic Communication and Language Bias in Multi-Agent LLM Coordination
Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano, The Anh Han, German Castignani, Pietro Li\`o
https://arxiv.org/abs/2508.00032

Strategic Communication and Language Bias in Multi-Agent LLM Coordination
Large Language Model (LLM)-based agents are increasingly deployed in multi-agent scenarios where coordination is crucial but not always assured. Previous studies indicate that the language used to frame strategic scenarios can influence cooperative behavior. This paper explores whether allowing agents to communicate amplifies these language-driven effects. Leveraging the FAIRGAME framework, we simulate one-shot and repeated games across different languages and models, both with and without comm…

Signal Drop in Magnification Profiles: Combining Lensing Simulations and Observations
David Crespo, Joaqu\'in Gonz\'alez-Nuevo, Laura Bonavera, Marcos M. Cueli, Hu Zou, Rebeca Fern\'andez-Fern\'andez, Jose M. Casas
https://arxiv.org/abs/2509.02213

Signal Drop in Magnification Profiles: Combining Lensing Simulations and Observations
Gravitational lensing magnification bias is a valuable tool for studying mass density profiles, with submillimetre galaxies (SMGs) serving as ideal background sources. The satellite distribution in galaxy clusters also provides insights into their mass distribution.This study aims to investigate the signal drop in mass density profiles from magnification bias measurements, assessing the role of satellite galaxies through observational data and lensing simulations. Using a stacking technique, we…

If it was up to me, I'd ONLY save the ugly animals https://www.abc.net.au/news/2025-06-25/ugly-endangered-animals-ignored-in-conservation-bias/105443062

Wildlife experts say ugly endangered animals are being ignored in conservation efforts
While there are plenty of conservation efforts and community love for cute marsupials like the western ringtail possum, researchers say that pretty privilege is threatening the existence of blood suckers and web weavers.

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/

This https://arxiv.org/abs/2503.09969 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Detecting Dataset Bias in Medical AI: A Generalized and Modality-Agnostic Auditing Framework
Artificial Intelligence (AI) is now firmly at the center of evidence-based medicine. Despite many success stories that edge the path of AI's rise in healthcare, there are comparably many reports of significant shortcomings and unexpected behavior of AI in deployment. A major reason for these limitations is AI's reliance on association-based learning, where non-representative machine learning datasets can amplify latent bias during training and/or hide it during testing. To unlock new tools capa…

The Triangle Friendship Paradox
Bishakh Bhattacharya, Nitya Gadhiwala, Frank den Hollander, Pradeeptha R Jain, Tejashree Subramanya
https://arxiv.org/abs/2507.02627

The Triangle Friendship Paradox
We consider the generalised friendship paradox, focussing on the number of triangles at a vertex as the relevant attribute. We show that, contrary to the setting where the attribute is the number of edges at a vertex or the number of wedges at a vertex, the average friendship-bias of the number of triangles at a vertex is not always non-negative. We identify classes of finite deterministic graphs for which the bias is non-negative, and provide examples of finite deterministic graphs for which i…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[11/11]:
- Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluations
Muskan Saraf, Sajjad Rezvani Boroujeni, Justin Beaudry, Hossein Abedi, Tom Bush

Spectral Bias in Variational Quantum Machine Learning
Callum Duffy, Marcin Jastrzebski
https://arxiv.org/abs/2506.22555 https://arxiv…

Spectral Bias in Variational Quantum Machine Learning
In this work, we investigate the phenomenon of spectral bias in quantum machine learning, where, in classical settings, models tend to fit low-frequency components of a target function earlier during training than high-frequency ones, demonstrating a frequency-dependent rate of convergence. We study this effect specifically in parameterised quantum circuits (PQCs). Leveraging the established formulation of PQCs as Fourier series, we prove that spectral bias in this setting arises from the ``red…

Meta-Fair: AI-Assisted Fairness Testing of Large Language Models
Miguel Romero-Arjona, Jos\'e A. Parejo, Juan C. Alonso, Ana B. S\'anchez, Aitor Arrieta, Sergio Segura
https://arxiv.org/abs/2507.02533

Meta-Fair: AI-Assisted Fairness Testing of Large Language Models
Fairness--the absence of unjustified bias--is a core principle in the development of Artificial Intelligence (AI) systems, yet it remains difficult to assess and enforce. Current approaches to fairness testing in large language models (LLMs) often rely on manual evaluation, fixed templates, deterministic heuristics, and curated datasets, making them resource-intensive and difficult to scale. This work aims to lay the groundwork for a novel, automated method for testing fairness in LLMs, reducin…

Quantifying Clinician Bias and its Effects on Schizophrenia Diagnosis in the Emergency Department of the Mount Sinai Health System
Alissa A. Valentine, Lauren A. Lepow, Lili Chan, Alexander W. Charney, Isotta Landi
https://arxiv.org/abs/2509.02651

Quantifying Clinician Bias and its Effects on Schizophrenia Diagnosis in the Emergency Department of the Mount Sinai Health System
In the United States, schizophrenia (SCZ) carries a race and sex disparity that may be explained by clinician bias - a belief held by a clinician about a patient that prevents impartial clinical decision making. The emergency department (ED) is marked by higher rates of stress that lead to clinicians relying more on implicit biases during decision making. In this work, we considered a large cohort of psychiatric patients in the ED from the Mount Sinai Health System (MSHS) in New York City to in…

AI-Generated Images for representing Individuals: Navigating the Thin Line Between Care and Bias
Julia C. Ahrend, Bj\"orn D\"oge, Tom M Duscher, Dario Rodighiero
https://arxiv.org/abs/2509.03071

AI-Generated Images for representing Individuals: Navigating the Thin Line Between Care and Bias
This research discusses the figurative tensions that arise when using portraits to represent individuals behind a dataset. In the broader effort to communicate European data related to depression, the Kiel Science Communication Network (KielSCN) team attempted to engage a wider audience by combining interactive data graphics with AI-generated images of people. This article examines the project's decisions and results, reflecting on the reaction from the audience when information design incorpor…

Your Model Is Unfair, Are You Even Aware? Inverse Relationship Between Comprehension and Trust in Explainability Visualizations of Biased ML Models
Zhanna Kaufman, Madeline Endres, Cindy Xiong Bearfield, Yuriy Brun
https://arxiv.org/abs/2508.00140

Your Model Is Unfair, Are You Even Aware? Inverse Relationship Between Comprehension and Trust in Explainability Visualizations of Biased ML Models
Systems relying on ML have become ubiquitous, but so has biased behavior within them. Research shows that bias significantly affects stakeholders' trust in systems and how they use them. Further, stakeholders of different backgrounds view and trust the same systems differently. Thus, how ML models' behavior is explained plays a key role in comprehension and trust. We survey explainability visualizations, creating a taxonomy of design characteristics. We conduct user studies to evaluate five sta…

Flow IV: Counterfactual Inference In Nonseparable Outcome Models Using Instrumental Variables
Marc Braun, Jose M. Pe\~na, Adel Daoud
https://arxiv.org/abs/2508.01321 https://

Flow IV: Counterfactual Inference In Nonseparable Outcome Models Using Instrumental Variables
To reach human level intelligence, learning algorithms need to incorporate causal reasoning. But identifying causality, and particularly counterfactual reasoning, remains an elusive task. In this paper, we make progress on this task by utilizing instrumental variables (IVs). IVs are a classic tool for mitigating bias from unobserved confounders when estimating causal effects. While IV methods have been extended to non-separable structural models at the population level, existing approaches to c…

Multi-diagnostic characterization of inductively coupled discharges with tailored waveform substrate bias for precise control of plasma etching
Jonas Giesekus, Anton Pletzer, Florian Beckfeld, Katharina Noesges, Claudia Bock, Julian Schulze
https://arxiv.org/abs/2509.01171

Multi-diagnostic characterization of inductively coupled discharges with tailored waveform substrate bias for precise control of plasma etching
Precise control of ion energy distribution functions (IEDF) is crucial for selectivity as well as control over sputter rate and substrate damage in nanoscale plasma processes. In this work, a low frequency (100 kHz) tailored pulse-wave-shaped bias voltage waveform is applied to the substrate electrode of an inductively coupled plasma (ICP) and its effects on the IEDF, electron density, electron dynamics and the etch rates of silicon dioxide as well as amorphous silicon are investigated in a com…

Klingt ja simpel, aber schon erstaunlich, dass Instrumente nicht angepasst sind…
When surgical tools don’t fit: how gender bias in design puts female surgeons at risk
https://theconversation.com/when-surgical-tools-…

When surgical tools don’t fit: how gender bias in design puts female surgeons at risk
Why surgical device design is changing to match the diversity of today’s operating rooms.

Bias Mitigation for AI-Feedback Loops in Recommender Systems: A Systematic Literature Review and Taxonomy
Theodor Stoecker, Samed Bayer, Ingo Weber
https://arxiv.org/abs/2509.00109

Bias Mitigation for AI-Feedback Loops in Recommender Systems: A Systematic Literature Review and Taxonomy
Recommender systems continually retrain on user reactions to their own predictions, creating AI feedback loops that amplify biases and diminish fairness over time. Despite this well-known risk, most bias mitigation techniques are tested only on static splits, so their long-term fairness across multiple retraining rounds remains unclear. We therefore present a systematic literature review of bias mitigation methods that explicitly consider AI feedback loops and are validated in multi-round simul…

KI-Update: GPT-5, Google-Shopping, Bias in der KI, Unitree R1
Das "KI-Update" liefert werktäglich eine Zusammenfassung der wichtigsten KI-Entwicklungen.
https://www.heise.de…

Crowd-SFT: Crowdsourcing for LLM Alignment
Alex Sotiropoulos, Sulyab Thottungal Valapu, Linus Lei, Jared Coleman, Bhaskar Krishnamachari
https://arxiv.org/abs/2506.04063

Crowd-SFT: Crowdsourcing for LLM Alignment
Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with a separate reward model, SFT uses human-curated datasets for supervised learning. Both approaches traditionally depend on small, vetted groups of annotators, making them costly, prone to bias, and limited in scalability. We propose an open, crowd-sourced fine…

House Republicans Want To Doxx Wikipedia Editors Over Bogus 'Bias' Complaints (Mike Masnick/Techdirt)
https://www.techdirt.com/2025/08/29/house-republicans-want-to-doxx-wikipedia-editors-over-bogus-bias-complaints/
http://www.memeorandum.com/250829/p64#a250829p64

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…

Entropy-Based Methods to Address Sampling Bias in Archaeological Predictive Modeling
Mehmet S{\i}dd{\i}k \c{C}ad{\i}rc{\i}, Golnaz Shahtahmassebi
https://arxiv.org/abs/2508.02272

Entropy-Based Methods to Address Sampling Bias in Archaeological Predictive Modeling
Predictive modeling in archaeology is essential for the understanding of people's behavior in the past and for guiding heritage conservation. However, spatial sampling bias caused by uneven research effort can severely limit model reliability. This research describes a novel new framework that integrates entropy-based corrections to measure and minimize such biases in archaeological modeling of foresight. Leveraging the open access data of the Grand Staircase-Escalante National Monument, we emp…

A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control
Zilin Kang, Chenyuan Hu, Yu Luo, Zhecheng Yuan, Ruijie Zheng, Huazhe Xu
https://arxiv.org/abs/2507.02712

A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control
Deep reinforcement learning for continuous control has recently achieved impressive progress. However, existing methods often suffer from primacy bias, a tendency to overfit early experiences stored in the replay buffer, which limits an RL agent's sample efficiency and generalizability. In contrast, humans are less susceptible to such bias, partly due to infantile amnesia, where the formation of new neurons disrupts early memory traces, leading to the forgetting of initial experiences. Inspired…

This https://arxiv.org/abs/2506.01832 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCC_…

Pseudorandom bits for non-commutative programs
We obtain new explicit pseudorandom generators for several computational models involving groups. Our main results are as follows: 1. We consider read-once group-products over a finite group $G$, i.e., tests of the form $\prod_{i=1}^n g_i^{x_i}$ where $g_i\in G$, a special case of read-once permutation branching programs. We give generators with optimal seed length $c_G \log(n/\varepsilon)$ over any $p$-group. The proof uses the small-bias plus noise paradigm, but derandomizes the noise to av…

Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approach
Aditya Tomar, Rudra Murthy, Pushpak Bhattacharyya
https://arxiv.org/abs/2507.01715

Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approach
Bias and stereotypes in language models can cause harm, especially in sensitive areas like content moderation and decision-making. This paper addresses bias and stereotype detection by exploring how jointly learning these tasks enhances model performance. We introduce StereoBias, a unique dataset labeled for bias and stereotype detection across five categories: religion, gender, socio-economic status, race, profession, and others, enabling a deeper study of their relationship. Our experiments c…

What Does Information Science Offer for Data Science Research?: A Review of Data and Information Ethics Literature
Brady D. Lund, Ting Wang
https://arxiv.org/abs/2506.03165

What Does Information Science Offer for Data Science Research?: A Review of Data and Information Ethics Literature
This paper reviews literature pertaining to the development of data science as a discipline, current issues with data bias and ethics, and the role that the discipline of information science may play in addressing these concerns. Information science research and researchers have much to offer for data science, owing to their background as transdisciplinary scholars who apply human-centered and social-behavioral perspectives to issues within natural science disciplines. Information science resea…

UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection
Jigang Fan, Quanlin Wu, Shengjie Luo, Liwei Wang
https://arxiv.org/abs/2506.03237

UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection
The detection of ligand binding sites for proteins is a fundamental step in Structure-Based Drug Design. Despite notable advances in recent years, existing methods, datasets, and evaluation metrics are confronted with several key challenges: (1) current datasets and methods are centered on individual protein-ligand complexes and neglect that diverse binding sites may exist across multiple complexes of the same protein, introducing significant statistical bias; (2) ligand binding site detection …

250 international media outlets protest Gaza journalist deaths,
‘At the rate journalists are being killed in Gaza by the Israeli army, there will soon be no-one left to keep you informed,’ says Reporters Without Borders, amid front-page protest
https://www.

250 international media outlets protest Gaza journalist deaths, Israel slams ‘bias’
At the rate journalists are being killed in Gaza by the Israeli army, there will soon be no-one left to keep you informed,' says Reporters Without Borders, amid front-page protest

Replaced article(s) found for physics.ao-ph. https://arxiv.org/list/physics.ao-ph/new
[1/1]:
- Global Climate Model Bias Correction Using Deep Learning
Abhishek Pasula, Deepak N. Subramani

Algorithm Adaptation Bias in Recommendation System Online Experiments
Chen Zheng, Zhenyu Zhao
https://arxiv.org/abs/2509.00199 https://arxiv.org/pdf/2509.0…

Algorithm Adaptation Bias in Recommendation System Online Experiments
Online experiments (A/B tests) are widely regarded as the gold standard for evaluating recommender system variants and guiding launch decisions. However, a variety of biases can distort the results of the experiment and mislead decision-making. An underexplored but critical bias is algorithm adaptation effect. This bias arises from the flywheel dynamics among production models, user data, and training pipelines: new models are evaluated on user data whose distributions are shaped by the incumbe…

A systematic bias in template-based RV extraction algorithms
Andr\'e M. Silva, N. C. Santos, J. P. Faria, J. H. C. Martins, E. A. S. Cristo, S. G. Sousa, P. T. P. Viana, \'E. Artigau, K. Al Moulla, A. Castro-Gonz\'alez, D. F. M. Folha, P. Figueira, T. Schmidt, F. Pepe, X. Dumusque, O. D. S. Demangeon, T. L. Campante, X. Delfosse, B. Wehbe, J. Lillo-Box, A. R. Costa Silva, J. Rodrigues, J. I. Gonz\'alez Hern\'andez, T. Azevedo Silva, S. Cristiani, H. M. Tabernero, E.…

A systematic bias in template-based RV extraction algorithms
In this paper we identify and explore a previously unidentified, multi meter-per-second, systematic correlation between time and RVs inferred through TM and LBL methods. We evaluate the influence of the data-driven stellar template in the RV bias and hypothesize on the possible sources of this effect. We first use the s-BART pipeline to extract RVs from three different datasets gathered over four nights of ESPRESSO and HARPS observations. Then, we demonstrate that the effect can be recovered on…

The Perfect Host: JWST Cepheid Observations in a Background-Free SN Ia Host Confirm No Bias in Hubble-Constant Measurements
Adam G. Riess, Siyang Li, Gagandeep S. Anand, Wenlong Yuan, Louise Breuval, Stefano Casertano, Lucas M. Macri, Dan Scolnic, Yukei S. Murakami, Alexei V. Filippenko, Thomas G. Brink
https://arxiv.org/abs/2509.01667

The Perfect Host: JWST Cepheid Observations in a Background-Free SN Ia Host Confirm No Bias in Hubble-Constant Measurements
Cycle 1 JWST observations of Cepheids in SN Ia hosts resolved their red-giant-dominated NIR backgrounds, sharply reducing crowding and showing that photometric bias in lower-resolution HST data does not account for the Hubble tension. We present Cycle 2 JWST observations of >100 Cepheids in NGC 3447, a unique system that pushes this test to the limit by transitioning from low to no background contamination. NGC 3447, an SN Ia host at D~25 Mpc, is an interacting pair comprising (i) a spiral with…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[1/5]:
- Combating Confirmation Bias: A Unified Pseudo-Labeling Framework for Entity Alignment
Qijie Ding, Jie Yin, Daokun Zhang, Junbin Gao

Double quantum dots with quenched charging energy in PbTe nanowires
Seth Byard, Maksim Gomanko, Adam Raynolds, Susheng Tan, Tongxie Zhang, Shixiong Zhang, Sergey M. Frolov
https://arxiv.org/abs/2509.03706

Double quantum dots with quenched charging energy in PbTe nanowires
We investigate double quantum dots defined by electrostatic gating in semiconductor PbTe nanowire devices. We perform transport measurements to obtain charge stability diagrams distinguished by negligible separation between paired triple points and by the spin degeneracy of all transport resonances at zero magnetic field. We show a fourfold splitting of high-bias stability diagram triangles in an applied magnetic field to illustrate the lifting of this spin degeneracy. We also identify patterns…

Anchoring-Based Causal Design (ABCD): Estimating the Effects of Beliefs
Raanan Sulitzeanu-Kenan, Micha Mandel, Yosef Rinott
https://arxiv.org/abs/2508.01677 https://

Anchoring-Based Causal Design (ABCD): Estimating the Effects of Beliefs
A central challenge in any study of the effects of beliefs on outcomes, such as decisions and behavior, is the risk of omitted variables bias. Omitted variables, frequently unmeasured or even unknown, can induce correlations between beliefs and decisions that are not genuinely causal, in which case the omitted variables are referred to as confounders. To address the challenge of causal inference, researchers frequently rely on information provision experiments to randomly manipulate beliefs. Th…

The seeds of the future are in the present: A blind exploration of metastable states
Timoth\'ee Devergne, Vladimir Kostic, Massimiliano Pontil, Michele Parrinello
https://arxiv.org/abs/2508.01477

The seeds of the future are in the present: A blind exploration of metastable states
In this work, we present a novel type of molecular dynamics simulation that aims at discovering, in a blind way, new metastable states. Using only data coming from an initial unbiased simulation, and with the help of an appropriately defined loss function, we compute a bias that favors sampling yet unexplored configurational space regions, encouraging the system to leave the initial basin. In our work, we take advantage of what is normally thought to be a defect, namely the difficulty of neural…

AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models
Snehasis Mukhopadhyay, Aryan Kasat, Shivam Dubey, Rahul Karthikeyan, Dhruv Sood, Vinija Jain, Aman Chadha, Amitava Das
https://arxiv.org/abs/2509.02133

AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models
Large Language Models (LLMs) can inadvertently reflect societal biases present in their training data, leading to harmful or prejudiced outputs. In the Indian context, our empirical evaluations across a suite of models reveal that biases around caste and religion are particularly salient. Yet, most existing mitigation strategies are Western-centric and fail to address these local nuances. We propose AMBEDKAR, a framework inspired by the egalitarian vision of Dr B. R. Ambedkar, architect of the …

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

Stakeholder Perspectives on Humanistic Implementation of Computer Perception in Healthcare: A Qualitative Study
Kristin M. Kostick-Quenet (Baylor College of Medicine, Houston, TX, 77030, USA), Meghan E. Hurley (Baylor College of Medicine, Houston, TX, 77030, USA), Syed Ayaz (Baylor College of Medicine, Houston, TX, 77030, USA), John Herrington (Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA), Casey Zampella (Children's Hospital of Philadelphia, Philadelphia, P…

Stakeholder Perspectives on Humanistic Implementation of Computer Perception in Healthcare: A Qualitative Study
Computer perception (CP) technologies (digital phenotyping, affective computing and related passive sensing approaches) offer unprecedented opportunities to personalize healthcare, but provoke concerns about privacy, bias and the erosion of empathic, relationship-centered practice. A comprehensive understanding of perceived risks, benefits, and implementation challenges from those who design, deploy and experience these tools in real-world settings remains elusive. This study provides the first…

This https://arxiv.org/abs/2506.03074 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

GL-LowPopArt: A Nearly Instance-Wise Minimax Estimator for Generalized Low-Rank Trace Regression
We present `GL-LowPopArt`, a novel Catoni-style estimator for generalized low-rank trace regression. Building on `LowPopArt` (Jang et al., 2024), it employs a two-stage approach: nuclear norm regularization followed by matrix Catoni estimation. We establish state-of-the-art estimation error bounds, surpassing existing guarantees (Fan et al., 2019; Kang et al., 2022), and reveal a novel experimental design objective, $\mathrm{GL}(π)$. The key technical challenge is controlling bias from the non…

Covariate-informed link prediction with extreme taxonomic bias
Jennifer N. Kampe, Camille DeSisto, David B. Dunson
https://arxiv.org/abs/2506.23370 https:/…

Covariate-informed link prediction with extreme taxonomic bias
Biotic interactions provide a valuable window into the inner workings of complex ecological communities and capture the loss of ecological function often precipitated by environmental change. However, the financial and logistical challenges associated with collecting interaction data result in networks that are recorded with geographical and taxonomic bias, particularly when studies are narrowly focused. We develop an approach to reduce bias in link prediction in the common scenario in which da…

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
Dani Roytburg, Matthew Bozoukov, Matthew Nguyen, Jou Barzdukas, Simon Fu, Narmeen Oozeer
https://arxiv.org/abs/2509.03647

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in evaluation pipelines, particularly for tasks like preference tuning and model routing. We investigate whether lightweight steering vectors can mitigate this problem at inference time without retraining. We introduce a curated dataset that distinguishes self-preferen…

Diffusion-RL Based Air Traffic Conflict Detection and Resolution Method
Tonghe Li, Jixin Liu, Weili Zeng, Hao Jiang
https://arxiv.org/abs/2509.03550 https://

Diffusion-RL Based Air Traffic Conflict Detection and Resolution Method
In the context of continuously rising global air traffic, efficient and safe Conflict Detection and Resolution (CD&R) is paramount for air traffic management. Although Deep Reinforcement Learning (DRL) offers a promising pathway for CD&R automation, existing approaches commonly suffer from a "unimodal bias" in their policies. This leads to a critical lack of decision-making flexibility when confronted with complex and dynamic constraints, often resulting in "decision deadlocks." To overcome thi…

President Trump's AI Action Plan, which has 90 policy recommendations, explicitly seeks to roll back Biden-era measures on AI bias and cybersecurity threats (Kate Knibbs/Wired)
https://www.wired.com/story/trumps-ai-action-plan-crusade-against-bias-regu…

Trump’s AI Action Plan Is a Crusade Against ‘Bias’—and Regulation
The Trump administration’s new AI policy blueprint calls for limited regulation and lots of leeway for Big Tech to grow even bigger.

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

Triboelectric charge transfer theory driven by interfacial thermoelectric effect
Ji-Ho Mun, Eui-Cheol Shin, Jaeuk Seo, Yong-Hyun Kim
https://arxiv.org/abs/2507.02528

Triboelectric charge transfer theory driven by interfacial thermoelectric effect
Despite extensive study and the practical significance of friction-driven static electricity, a quantitative triboelectric charge transfer theory has yet to be established. Here, we elucidate the detailed dynamics of triboelectric charge transfer driven by interfacial thermoelectric bias maintaining a steady state at the interface. We demonstrate that triboelectric charge exists in a delta-like distribution at a steady state. We suggest that the transferred triboelectric charge is dictated by h…

FAIR-MATCH: A Multi-Objective Framework for Bias Mitigation in Reciprocal Dating Recommendations
Madhav Kotecha
https://arxiv.org/abs/2507.01063 https://…

FAIR-MATCH: A Multi-Objective Framework for Bias Mitigation in Reciprocal Dating Recommendations
Online dating platforms have fundamentally transformed the formation of romantic relationships, with millions of users worldwide relying on algorithmic matching systems to find compatible partners. However, current recommendation systems in dating applications suffer from significant algorithmic deficiencies, including but not limited to popularity bias, filter bubble effects, and inadequate reciprocity modeling that limit effectiveness and introduce harmful biases. This research integrates fou…

SESGO: Spanish Evaluation of Stereotypical Generative Outputs
Melissa Robles, Catalina Bernal, Denniss Raigoso, Mateo Dulce Rubio
https://arxiv.org/abs/2509.03329 https://

SESGO: Spanish Evaluation of Stereotypical Generative Outputs
This paper addresses the critical gap in evaluating bias in multilingual Large Language Models (LLMs), with a specific focus on Spanish language within culturally-aware Latin American contexts. Despite widespread global deployment, current evaluations remain predominantly US-English-centric, leaving potential harms in other linguistic and cultural contexts largely underexamined. We introduce a novel, culturally-grounded framework for detecting social biases in instruction-tuned LLMs. Our approa…

MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion
Xin Guan, PeiHsin Lin, Zekun Wu, Ze Wang, Ruibo Zhang, Emre Kazim, Adriano Koshiyama
https://arxiv.org/abs/2507.02595

MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion
Multiperspective Fusion (MPF) is a novel posttraining alignment framework for large language models (LLMs) developed in response to the growing need for easy bias mitigation. Built on top of the SAGED pipeline, an automated system for constructing bias benchmarks and extracting interpretable baseline distributions, MPF leverages multiperspective generations to expose and align biases in LLM outputs with nuanced, humanlike baselines. By decomposing baseline, such as sentiment distributions from …

Who's Sorry Now: User Preferences Among Rote, Empathic, and Explanatory Apologies from LLM Chatbots
Zahra Ashktorab, Alessandra Buccella, Jason D'Cruz, Zoe Fowler, Andrew Gill, Kei Yan Leung, P. D. Magnus, John Richards, Kush R. Varshney
https://arxiv.org/abs/2507.02745

Who's Sorry Now: User Preferences Among Rote, Empathic, and Explanatory Apologies from LLM Chatbots
As chatbots driven by large language models (LLMs) are increasingly deployed in everyday contexts, their ability to recover from errors through effective apologies is critical to maintaining user trust and satisfaction. In a preregistered study with Prolific workers (N=162), we examine user preferences for three types of apologies (rote, explanatory, and empathic) issued in response to three categories of common LLM mistakes (bias, unfounded fabrication, and factual errors). We designed a pairw…

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…

Contextual Online Pricing with (Biased) Offline Data
Yixuan Zhang, Ruihao Zhu, Qiaomin Xie
https://arxiv.org/abs/2507.02762 https://a…

Contextual Online Pricing with (Biased) Offline Data
We study contextual online pricing with biased offline data. For the scalar price elasticity case, we identify the instance-dependent quantity $δ^2$ that measures how far the offline data lies from the (unknown) online optimum. We show that the time length $T$, bias bound $V$, size $N$ and dispersion $λ_{\min}(\hatΣ)$ of the offline data, and $δ^2$ jointly determine the statistical complexity. An Optimism-in-the-Face-of-Uncertainty (OFU) policy achieves a minimax-optimal, instance-dependent…

Emergence of Fair Leaders via Mediators in Multi-Agent Reinforcement Learning
Akshay Dodwadmath, Setareh Maghsudi
https://arxiv.org/abs/2508.02421 https://…

Emergence of Fair Leaders via Mediators in Multi-Agent Reinforcement Learning
Stackelberg games and their resulting equilibria have received increasing attention in the multi-agent reinforcement learning literature. Each stage of a traditional Stackelberg game involves a leader(s) acting first, followed by the followers. In situations where the roles of leader(s) and followers can be interchanged, the designated role can have considerable advantages, for example, in first-mover advantage settings. Then the question arises: Who should be the leader and when? A bias in the…

Two-dimensional magnetic tunnel p-n junctions for low-power electronics
Wenkai Zhu, Ziao Wang, Tiangui Hu, Zakhar R. Kudrynskyi, Tong Zhou, Zakhar D. Kovalyuk, Ce Hu, Hailong Lin, Xiaodong Li, Yongcheng Deng, Quanshan Lv, Lixia Zhao, Amalia Patane, Igor Zutic, Houzhi Zheng, Kaiyou Wang
https://arxiv.org/abs/2509.04206

Two-dimensional magnetic tunnel p-n junctions for low-power electronics
For decades, semiconductors and their heterostructures have underpinned both fundamental and applied research across all areas of electronics. Two-dimensional, 2D (atomically thin) semiconductors have now the potential to push further the miniaturization of electronic components, enabling the development of more efficient electronics. Here, we report on a giant anomalous zero-bias spin voltage in magnetic tunnel junctions based on 2D materials. The generation, manipulation and detection of elec…

Quantifying the impact of detection bias from blended galaxies on cosmic shear surveys
Eray Genc, Peter Schneider, Sandra Unruh, Tim Schrabback
https://arxiv.org/abs/2507.01546

Quantifying the impact of detection bias from blended galaxies on cosmic shear surveys
Increasingly large areas in cosmic shear surveys lead to a reduction of statistical errors, necessitating to control systematic errors increasingly better. One of these systematic effects was initially studied by Hartlap et al. in 2011, namely that image overlap with (bright foreground) galaxies may prevent some distant (source) galaxies to remain undetected. Since this overlap is more likely to occur in regions of high foreground density -- which tend to be the regions in which the shear is la…

Towards an Observational Detection of Halo Spin Bias using Spin-Orbit Coherence
Yigon Kim, Antonio D. Montero-Dorta, Rory Smith, Jong-Ho Shinn
https://arxiv.org/abs/2506.21827

Towards an Observational Detection of Halo Spin Bias using Spin-Orbit Coherence
Context. The clustering of dark-matter halos depends primarily on halo mass. However, at fixed halo mass, numerical simulations have revealed multiple secondary dependencies. This so-called secondary halo bias has important implications for our understanding of structure formation and observational cosmology. Despite its significance, the effect has not yet been measured observationally with statistical confidence. Aims. We aim to develop the first observational method to probe halo spin bias: …

The Illusion of Fairness: Auditing Fairness Interventions with Audit Studies
Disa Sariola, Patrick Button, Aron Culotta, Nicholas Mattei
https://arxiv.org/abs/2507.02152

The Illusion of Fairness: Auditing Fairness Interventions with Audit Studies
Artificial intelligence systems, especially those using machine learning, are being deployed in domains from hiring to loan issuance in order to automate these complex decisions. Judging both the effectiveness and fairness of these AI systems, and their human decision making counterpart, is a complex and important topic studied across both computational and social sciences. Within machine learning, a common way to address bias in downstream classifiers is to resample the training data to offset…

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

Bias, Accuracy, and Trust: Gender-Diverse Perspectives on Large Language Models
Aimen Gaba, Emily Wall, Tejas Ramkumar Babu, Yuriy Brun, Kyle Hall, Cindy Xiong Bearfield
https://arxiv.org/abs/2506.21898

Bias, Accuracy, and Trust: Gender-Diverse Perspectives on Large Language Models
Large language models (LLMs) are becoming increasingly ubiquitous in our daily lives, but numerous concerns about bias in LLMs exist. This study examines how gender-diverse populations perceive bias, accuracy, and trustworthiness in LLMs, specifically ChatGPT. Through 25 in-depth interviews with non-binary/transgender, male, and female participants, we investigate how gendered and neutral prompts influence model responses and how users evaluate these responses. Our findings reveal that gendered…

LLMs for estimating positional bias in logged interaction data
Aleksandr V. Petrov, Michael Murtagh, Karthik Nagesh
https://arxiv.org/abs/2509.03696 https://

US representatives James Comer and Nancy Mace want Wikipedia to hand over editor identities and internal communications; the Wikipedia Foundation should decline (Mike Masnick/Techdirt)
https://www.techdirt.com/2025/08/29/house-…

House Republicans Want To Doxx Wikipedia Editors Over Bogus ‘Bias’ Complaints
Congress has absolutely zero constitutional authority to investigate a private website for its editorial decisions. Zero. None. This is First Amendment 101. Yet House Oversight Committee Chairman J…

Leveraging Imperfection with MEDLEY A Multi-Model Approach Harnessing Bias in Medical AI
Farhad Abtahi, Mehdi Astaraki, Fernando Seoane
https://arxiv.org/abs/2508.21648 https://…

Leveraging Imperfection with MEDLEY A Multi-Model Approach Harnessing Bias in Medical AI
Bias in medical artificial intelligence is conventionally viewed as a defect requiring elimination. However, human reasoning inherently incorporates biases shaped by education, culture, and experience, suggesting their presence may be inevitable and potentially valuable. We propose MEDLEY (Medical Ensemble Diagnostic system with Leveraged diversitY), a conceptual framework that orchestrates multiple AI models while preserving their diverse outputs rather than collapsing them into a consensus. U…

Theories of "Sexuality" in Natural Language Processing Bias Research
Jacob Hobbs
https://arxiv.org/abs/2506.22481 https://a…

Theories of "Sexuality" in Natural Language Processing Bias Research
In recent years, significant advancements in the field of Natural Language Processing (NLP) have positioned commercialized language models as wide-reaching, highly useful tools. In tandem, there has been an explosion of multidisciplinary research examining how NLP tasks reflect, perpetuate, and amplify social biases such as gender and racial bias. A significant gap in this scholarship is a detailed analysis of how queer sexualities are encoded and (mis)represented by both NLP systems and practi…

Enhanced negative capacitance in La-doped Pb(Zr$_{0.4}$Ti$_{0.6}$)O$_3$ ferroelectric capacitor by tuning bias voltage pulse to induce intrinsic domain switching kinetics
Ganga S. Kumar, Sudipta Goswami, Shubhasree Chatterjee, Dilruba Hasina, Miral Verma, Devajyoti Mukherjee, Chandan Kumar Ghosh, Dipten Bhattacharya
https://arxiv.org/abs/2…

Enhanced negative capacitance in La-doped Pb(Zr$_{0.4}$Ti$_{0.6}$)O$_3$ ferroelectric capacitor by tuning bias voltage pulse to induce intrinsic domain switching kinetics
We report a remarkable enhancement of specific negative capacitance in multidomain La-doped Pb(Zr$_{0.4}$Ti$_{0.6}$)O$_3$ (PLZT) ferroelectric capacitors when bias voltage pulse profile (amplitude and timescale) induces switching of the ferroelectric domains following intrinsic switching kinetics associated with minimum energy barrier. This is because of emergence of maximum domain wall density during ``switching" of the domains. Domain configuration changes from such an ``optimum" state if hig…

Bias in estimating Theil, Atkinson, and dispersion indices for gamma mixture populations
Jackson Assis, Roberto Vila, Helton Saulo
https://arxiv.org/abs/2506.22168

Bias in estimating Theil, Atkinson, and dispersion indices for gamma mixture populations
In this paper, we derive closed-form expressions for the bias of estimators of the Theil, Atkinson, and dispersion indices when the underlying population follows a finite mixture of gamma distributions. Our methodology builds on probabilistic techniques grounded in Mosimann's proportion-sum independence theorem and the gamma-Dirichlet connection, enabling analytical tractability in the presence of population heterogeneity. These results extend existing findings for single gamma models.

The Simons Observatory: Assessing the Impact of Dust Complexity on the Recovery of Primordial $B$-modes
Yiqi Liu, Susanna Azzoni, Susan E. Clark, Brandon S. Hensley, L\'eo Vacher, David Alonso, Carlo Baccigalupi, Michael L. Brown, Alessandro Carones, Jens Chluba, Jo Dunkley, Carlos Herv\'ias-Caimapo, Bradley R. Johnson, Nicoletta Krachmalnicoff, Giuseppe Puglisi, Mathieu Remazeilles, Kevin Wolz

The Simons Observatory: Assessing the Impact of Dust Complexity on the Recovery of Primordial $B$-modes
We investigate how dust foreground complexity can affect measurements of the tensor-to-scalar ratio, $r$, in the context of the Simons Observatory, using a cross-spectrum component separation analysis. Employing a suite of simulations with realistic Galactic dust emission, we find that spatial variation in the dust frequency spectrum, parametrized by $β_d$, can bias the estimate for $r$ when modeled using a low-order moment expansion to capture this spatial variation. While this approach perfo…

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.

Improving Narrative Classification and Explanation via Fine Tuned Language Models
Rishit Tyagi, Rahul Bouri, Mohit Gupta
https://arxiv.org/abs/2509.04077 https://

Improving Narrative Classification and Explanation via Fine Tuned Language Models
Understanding covert narratives and implicit messaging is essential for analyzing bias and sentiment. Traditional NLP methods struggle with detecting subtle phrasing and hidden agendas. This study tackles two key challenges: (1) multi-label classification of narratives and sub-narratives in news articles, and (2) generating concise, evidence-based explanations for dominant narratives. We fine-tune a BERT model with a recall-oriented approach for comprehensive narrative detection, refining predi…

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity
Jacopo Nudo, Mario Edoardo Pandolfo, Edoardo Loru, Mattia Samory, Matteo Cinelli, Walter Quattrociocchi
https://arxiv.org/abs/2507.00657

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity
We investigate how Large Language Models (LLMs) behave when simulating political discourse on social media. Leveraging 21 million interactions on X during the 2024 U.S. presidential election, we construct LLM agents based on 1,186 real users, prompting them to reply to politically salient tweets under controlled conditions. Agents are initialized either with minimal ideological cues (Zero Shot) or recent tweet history (Few Shot), allowing one-to-one comparisons with human replies. We evaluate t…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/7]:
- Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification
Takuma Udagawa, Yang Zhao, Hiroshi Kanayama, Bishwaranjan Bhattacharjee

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…

Hyper Suprime-Cam Y3 results: photo-$z$ bias calibration with lensing shear ratios and cosmological constraints from cosmic shea
Divya Rana, Surhud More, Hironao Miyatake, Sunao Sugiyama, Tianqing Zhang, Masato Shirasaki
https://arxiv.org/abs/2508.21681

Hyper Suprime-Cam Y3 results: photo-$z$ bias calibration with lensing shear ratios and cosmological constraints from cosmic shea
We present an independent calibration of the photometric redshift (photo-$z$) distributions for source galaxies in the HSC-Y3 weak lensing survey using small-scale galaxy-galaxy lensing. By measuring the tangential shear around spectroscopic lens galaxies from GAMA, SDSS, and DESI, divided into fifteen narrow redshift bins, we compute shear ratios that are sensitive to the mean redshift of source galaxies. Using a blinded analysis, we derive constraints on the photo-$z$ bias parameters in sourc…

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…

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…

Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluations
Muskan Saraf, Sajjad Rezvani Boroujeni, Justin Beaudry, Hossein Abedi, Tom Bush
https://arxiv.org/abs/2508.21164

Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluations
Large language models (LLMs) are increasingly used to evaluate outputs, yet their judgments may be influenced. This study examines bias in self- and cross-model evaluations by ChatGPT, Gemini, and Claude under four conditions: no labels, true labels, and two false-label scenarios. Blog posts authored by each model were evaluated by all three using both overall preference voting and quality ratings for Coherence, Informativeness, and Conciseness, with all scores expressed as percentages for dire…

Towards Fair Rankings: Leveraging LLMs for Gender Bias Detection and Measurement
Maryam Mousavian, Zahra Abbasiantaeb, Mohammad Aliannejadi, Fabio Crestani
https://arxiv.org/abs/2506.22372

Towards Fair Rankings: Leveraging LLMs for Gender Bias Detection and Measurement
The presence of social biases in Natural Language Processing (NLP) and Information Retrieval (IR) systems is an ongoing challenge, which underlines the importance of developing robust approaches to identifying and evaluating such biases. In this paper, we aim to address this issue by leveraging Large Language Models (LLMs) to detect and measure gender bias in passage ranking. Existing gender fairness metrics rely on lexical- and frequency-based measures, leading to various limitations, e.g., mi…

Evaluating Scoring Bias in LLM-as-a-Judge
Qingquan Li, Shaoyu Dou, Kailai Shao, Chao Chen, Haixiang Hu
https://arxiv.org/abs/2506.22316 https://

Evaluating Scoring Bias in LLM-as-a-Judge
The remarkable performance of Large Language Models (LLMs) gives rise to``LLM-as-a-Judge'', where LLMs are employed as evaluators for complex tasks. Moreover, it has been widely adopted across fields such as Natural Language Processing (NLP), preference learning, and various specific domains. However, there are various biases within LLM-as-a-Judge, which adversely affect the fairness and reliability of judgments. Current research on evaluating or mitigating bias in LLM-as-a-Judge predominantly …

Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning
Kwesi Cobbina, Tianyi Zhou
https://arxiv.org/abs/2507.22887 https://arxiv.org/…

Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning
In-context learning (ICL) is a critical emerging capability of large language models (LLMs), enabling few-shot learning during inference by including a few demonstrations (demos) in the prompt. However, it has been found that ICL's performance can be sensitive to the choices of demos and their order. This paper investigates an unexplored new positional bias of ICL for the first time: we observe that the predictions and accuracy can drift drastically when the positions of demos, the system promp…

Leveraging In-Context Learning for Political Bias Testing of LLMs
Patrick Haller, Jannis Vamvas, Rico Sennrich, Lena A. J\"ager
https://arxiv.org/abs/2506.22232

Leveraging In-Context Learning for Political Bias Testing of LLMs
A growing body of work has been querying LLMs with political questions to evaluate their potential biases. However, this probing method has limited stability, making comparisons between models unreliable. In this paper, we argue that LLMs need more context. We propose a new probing task, Questionnaire Modeling (QM), that uses human survey data as in-context examples. We show that QM improves the stability of question-based bias evaluation, and demonstrate that it may be used to compare instruct…

How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations
Yoshiki Takenami, Yin Jou Huang, Yugo Murawaki, Chenhui Chu
https://arxiv.org/abs/2508.21137

How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations
Cognitive biases, well-studied in humans, can also be observed in LLMs, affecting their reliability in real-world applications. This paper investigates the anchoring effect in LLM-driven price negotiations. To this end, we instructed seller LLM agents to apply the anchoring effect and evaluated negotiations using not only an objective metric but also a subjective metric. Experimental results show that LLMs are influenced by the anchoring effect like humans. Additionally, we investigated the rel…

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…

Obscured but Not Erased: Evaluating Nationality Bias in LLMs via Name-Based Bias Benchmarks
Giulio Pelosio, Devesh Batra, No\'emie Bovey, Robert Hankache, Cristovao Iglesias, Greig Cowan, Raad Khraishi
https://arxiv.org/abs/2507.16989

Obscured but Not Erased: Evaluating Nationality Bias in LLMs via Name-Based Bias Benchmarks
Large Language Models (LLMs) can exhibit latent biases towards specific nationalities even when explicit demographic markers are not present. In this work, we introduce a novel name-based benchmarking approach derived from the Bias Benchmark for QA (BBQ) dataset to investigate the impact of substituting explicit nationality labels with culturally indicative names, a scenario more reflective of real-world LLM applications. Our novel approach examines how this substitution affects both bias magni…