Tootfinder

VHU-Net: Variational Hadamard U-Net for Body MRI Bias Field Correction
Xin Zhu
https://arxiv.org/abs/2506.19181 https://arxiv.org/pdf…

VHU-Net: Variational Hadamard U-Net for Body MRI Bias Field Correction
Bias field artifacts in magnetic resonance imaging (MRI) scans introduce spatially smooth intensity inhomogeneities that degrade image quality and hinder downstream analysis. To address this challenge, we propose a novel variational Hadamard U-Net (VHU-Net) for effective body MRI bias field correction. The encoder comprises multiple convolutional Hadamard transform blocks (ConvHTBlocks), each integrating convolutional layers with a Hadamard transform (HT) layer. Specifically, the HT layer perfo…

SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization
Dhruv Gupta, Gayathri Ganesh Lakshmy, Yiqing Xie
https://arxiv.org/abs/2506.20081

SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization
Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features while preserving code functionality. Our discoveries include: (1) although trained on code, current retrievers heavily rely on surface-level textual features (e.g., docstrings, identifier names), and (2) they exhibit a strong bias towards well-documented cod…

Bias vs Bias -- Dawn of Justice: A Fair Fight in Recommendation Systems
Tahsin Alamgir Kheya, Mohamed Reda Bouadjenek, Sunil Aryal
https://arxiv.org/abs/2506.18327

Bias vs Bias -- Dawn of Justice: A Fair Fight in Recommendation Systems
Recommendation systems play a crucial role in our daily lives by impacting user experience across various domains, including e-commerce, job advertisements, entertainment, etc. Given the vital role of such systems in our lives, practitioners must ensure they do not produce unfair and imbalanced recommendations. Previous work addressing bias in recommendations overlooked bias in certain item categories, potentially leaving some biases unaddressed. Additionally, most previous work on fair re-rank…

Multimodal Political Bias Identification and Neutralization
Cedric Bernard, Xavier Pleimling, Amun Kharel, Chase Vickery
https://arxiv.org/abs/2506.17372 h…

Multimodal Political Bias Identification and Neutralization
Due to the presence of political echo chambers, it becomes imperative to detect and remove subjective bias and emotionally charged language from both the text and images of political articles. However, prior work has focused on solely the text portion of the bias rather than both the text and image portions. This is a problem because the images are just as powerful of a medium to communicate information as text is. To that end, we present a model that leverages both text and image bias which co…

An iterative CMB lensing estimator minimizing instrumental noise bias
Louis Legrand, Blake Sherwin, Anthony Challinor, Julien Carron, Gerrit S. Farren
https://arxiv.org/abs/2506.20667

An iterative CMB lensing estimator minimizing instrumental noise bias
Noise maps from CMB experiments are generally statistically anisotropic, due to scanning strategies, atmospheric conditions, or instrumental effects. Any mis-modeling of this complex noise can bias the reconstruction of the lensing potential and the measurement of the lensing power spectrum from the observed CMB maps. We introduce a new CMB lensing estimator based on the maximum a posteriori (MAP) reconstruction that is minimally sensitive to these instrumental noise biases. By modifying the li…

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
Long Xing, Qidong Huang, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Jinsong Li, Shuangrui Ding, Weiming Zhang, Nenghai Yu, Jiaqi Wang, Feng Wu, Dahua Lin
https://arxiv.org/abs/2506.19848

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
This paper presents ScaleCap, an inference-time scalable image captioning strategy that generates comprehensive and detailed image captions. The key challenges of high-quality image captioning lie in the inherent biases of LVLMs: multimodal bias resulting in imbalanced descriptive granularity, offering detailed accounts of some elements while merely skimming over others; linguistic bias leading to hallucinated descriptions of non-existent objects. To address these issues, we propose a scalable …

Steering Conceptual Bias via Transformer Latent-Subspace Activation
Vansh Sharma, Venkat Raman
https://arxiv.org/abs/2506.18887 https://

Steering Conceptual Bias via Transformer Latent-Subspace Activation
This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were first evaluated on scientific coding prompts to quantify their baseline bias among four programming languages. A static neuron-attribution method, perturbing the highest activated MLP weight for a C++ or CPP token, proved brittle and exhibited limited generalization across prompt styles and model scales. To address th…

In the case of the Iraq war, the administration of George W Bush believed that Saddam Hussein was building weapons of mass destruction, and
– determined to act on that belief
– sought proof of its proposition.
Convinced that he was right,
Bush sought to streamline information that confirmed its bias.
What fell by the wayside were conflicting views.
Because intelligence is ultimately about assessing the likelihood of things which are difficult to know,

A direct dispersive signature of Pauli spin blockade
Simon Svab, Rafael S. Eggli, Taras Patlatiuk, Miguel J. Carballido. Pierre Chevalier Kwon, Dominique A. Tr\"ussel, Ang Li, Erik P. A. M. Bakkers, Andreas V. Kuhlmann, Dominik M. Zumb\"uhl
https://arxiv.org/abs/2506.20509

A direct dispersive signature of Pauli spin blockade
Pauli Spin Blockade (PSB) is a key paradigm in semiconductor nanostructures and gives access to the spin physics. We report the direct observation of PSB with gate-dispersive reflectometry on double quantum dots with source-drain bias. The reservoir charge transitions are strongly modulated, turning on and off when entering and leaving the blockaded region, consistent with a simple model. Seen with holes in Ge and Si, the effects are enhanced with larger bias voltage and suppressed by magnetic …

Multivariate Statistical Analysis of Exoplanet Habitability: Detection Bias and Earth Analog Identification
Caleb Traxler, Samuel Townsend, Abby Mori, Grace Newman, Kaitlyn Morenzone
https://arxiv.org/abs/2506.18200

Multivariate Statistical Analysis of Exoplanet Habitability: Detection Bias and Earth Analog Identification
We present a comprehensive multivariate statistical analysis of 517 exoplanets from the NASA Exoplanet Archive to identify potentially habitable worlds and quantify detection bias in current surveys. Using eight key parameters (planetary radius, equilibrium temperature, insolation flux, density, and stellar effective temperature, radius, mass, metallicity), we developed a classification framework that successfully identifies Earth as an "Excellent Candidate" for habitability. Our analysis revea…

Trustworthy Artificial Intelligence for Cyber Threat Analysis
Shuangbao Paul Wang, Paul Mullin
https://arxiv.org/abs/2506.19052 https://

Trustworthy Artificial Intelligence for Cyber Threat Analysis
Artificial Intelligence brings innovations into the society. However, bias and unethical exist in many algorithms that make the applications less trustworthy. Threats hunting algorithms based on machine learning have shown great advantage over classical methods. Reinforcement learning models are getting more accurate for identifying not only signature-based but also behavior-based threats. Quantum mechanics brings a new dimension in improving classification speed with exponential advantage. In …

Alleviating User-Sensitive bias with Fair Generative Sequential Recommendation Model
Yang Liu, Feng Wu, Xuefang Zhu
https://arxiv.org/abs/2506.19777 https:…

Alleviating User-Sensitive bias with Fair Generative Sequential Recommendation Model
Recommendation fairness has recently attracted much attention. In the real world, recommendation systems are driven by user behavior, and since users with the same sensitive feature (e.g., gender and age) tend to have the same patterns, recommendation models can easily capture the strong correlation preference of sensitive features and thus cause recommendation unfairness. Diffusion model (DM) as a new generative model paradigm has achieved great success in recommendation systems. DM's ability …

Filters of Identity: AR Beauty and the Algorithmic Politics of the Digital Body
Miriam Doh, Corinna Canali, Nuria Oliver
https://arxiv.org/abs/2506.19611 h…

Filters of Identity: AR Beauty and the Algorithmic Politics of the Digital Body
This position paper situates AR beauty filters within the broader debate on Body Politics in HCI. We argue that these filters are not neutral tools but technologies of governance that reinforce racialized, gendered, and ableist beauty standards. Through naming conventions, algorithmic bias, and platform governance, they impose aesthetic norms while concealing their influence. To address these challenges, we advocate for transparency-driven interventions and a critical rethinking of algorithmic …

On the $h$-majority dynamics with many opinions
Francesco d'Amore, Niccol\`o D'Archivio, George Giakkoupis, Emanuele Natale
https://arxiv.org/abs/2506.20218

On the $h$-majority dynamics with many opinions
We present the first upper bound on the convergence time to consensus of the well-known $h$-majority dynamics with $k$ opinions, in the synchronous setting, for $h$ and $k$ that are both non-constant values. We suppose that, at the beginning of the process, there is some initial additive bias towards some plurality opinion, that is, there is an opinion that is supported by $x$ nodes while any other opinion is supported by strictly fewer nodes. We prove that, with high probability, if the bi…

Bias Variation Compensation in Perimeter-Gated SPAD TRNGs
Md Sakibur Sajal, Hunter Guthrie, Marc Dandin
https://arxiv.org/abs/2506.15888 https://

Bias Variation Compensation in Perimeter-Gated SPAD TRNGs
Random number generators that utilize arrays of entropy source elements suffer from bias variation (BV). Despite the availability of efficient debiasing algorithms, optimized implementations of hardware friendly options depend on the bit bias in the raw bit streams and cannot accommodate a wide BV. In this work, we present a 64 x 64 array of perimeter gated single photon avalanche diodes (pgSPADs), fabricated in a 0.35 μm standard CMOS technology, as a source of entropy to generate random bina…

Social Group Bias in AI Finance
Thomas R. Cook, Sophia Kazinnik
https://arxiv.org/abs/2506.17490 https://arxiv.org/pdf/2506.17490

Social Group Bias in AI Finance
Financial institutions increasingly rely on large language models (LLMs) for high-stakes decision-making. However, these models risk perpetuating harmful biases if deployed without careful oversight. This paper investigates racial bias in LLMs specifically through the lens of credit decision-making tasks, operating on the premise that biases identified here are indicative of broader concerns across financial applications. We introduce a reproducible, counterfactual testing framework that evalua…

Undersmoothed LASSO Models for Propensity Score Weighting and Synthetic Negative Control Exposures for Bias Detection
Richard Wyss, Ben B. Hansen, Georg Hahn, Lars van der Laan, Joshua K. Lin
https://arxiv.org/abs/2506.17760

Undersmoothed LASSO Models for Propensity Score Weighting and Synthetic Negative Control Exposures for Bias Detection
The propensity score (PS) is often used to control for large numbers of covariates in high-dimensional healthcare database studies. The least absolute shrinkage and selection operator (LASSO) is a data-adaptive prediction algorithm that has become the most widely used tool for large-scale PS estimation in these settings. However, recent work has shown that the use of data-adaptive algorithms for PS estimation can come at the cost of slow convergence rates, resulting in PS-based causal estimator…

Two new NERDS papers: Bias in LLM populations, recommending routes
https://nerds.itu.dk/2025/05/16/two-new-nerds-papers-bias-in-llm-populations-recommending-routes/

Kennedy's picks for vaccine advisory panel raise concerns about anti-vaccine bias (NBC News)
https://www.nbcnews.com/health/health-news/rfk-jr-advisory-panel-concerns-anti-vaccine-bias-rcna213496
http://www.memeorandum.com/250618/p125#a250618p125

Ketanji Brown Jackson Wants to Save the Supreme Court From Itself
https://newrepublic.substack.com/p/supreme-court-epa-corporate-bias

#Harvard continues to ignore reports of anti- Palestinian/Arabi/Muslim bias.
“Now, in the face of Trump, Harvard pretends that it is standing up, but you cannot stand up for freedom and silence members of your own community,”
h…

Harvard Affiliates Deliver Hundreds of Complaints Alleging Anti-Arab and Anti-Muslim Bias to President Garber’s Office | News | The Harvard Crimson
More than 30 Harvard affiliates delivered a box containing 452 discrimination complaints to Massachusetts Hall at a Monday rally, alleging that Harvard has fostered “pervasive bias against Muslims, Arabs and Palestinians.”

I need you to think about how bias happens in the real world.
Like the banality of evil, bias isn't often perpetrated by monsters, rather by well meaning people who think they're being fair and thoughtful and doing their best — and they (you! us!), we ARE doing our best, but I need you to understand that doing our best isn't good enough to identify, understand, prevent, nor heal all harm.

Kinematic Model Optimization via Differentiable Contact Manifold for In-Space Manipulation
Abhay Negi, Omey M. Manyar, Satyandra K. Gupta
https://arxiv.org/abs/2506.17458

Kinematic Model Optimization via Differentiable Contact Manifold for In-Space Manipulation
Robotic manipulation in space is essential for emerging applications such as debris removal and in-space servicing, assembly, and manufacturing (ISAM). A key requirement for these tasks is the ability to perform precise, contact-rich manipulation under significant uncertainty. In particular, thermal-induced deformation of manipulator links and temperature-dependent encoder bias introduce kinematic parameter errors that significantly degrade end-effector accuracy. Traditional calibration techniq…

Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective
Hitomi Yanaka, Xinqi He, Jie Lu, Namgi Han, Sunjin Oh, Ryoma Kumon, Yuma Matsuoka, Katsuhiko Watabe, Yuko Itatsu
https://arxiv.org/abs/2506.12327

Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective
An growing number of studies have examined the social bias of rapidly developed large language models (LLMs). Although most of these studies have focused on bias occurring in a single social attribute, research in social science has shown that social bias often occurs in the form of intersectionality -- the constitutive and contextualized perspective on bias aroused by social attributes. In this study, we construct the Japanese benchmark inter-JBBQ, designed to evaluate the intersectional bias …

from my link log —
Toxic Origins, Toxic Decisions: bias in CEO selection towards risk-taking, analysed using polluted Superfund sites.
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5270031
saved 2025-05-31

Principal stratification with recurrent events truncated by a terminal event: A nested Bayesian nonparametric approach
Yuki Ohnishi, Michael O. Harhay, Fan Li
https://arxiv.org/abs/2506.19015

Principal stratification with recurrent events truncated by a terminal event: A nested Bayesian nonparametric approach
Recurrent events often serve as key endpoints in clinical studies but may be prematurely truncated by terminal events such as death, creating selection bias and complicating causal inference. To address this challenge, we propose novel causal estimands within the principal stratification framework, introducing a refined ``always-survivor'' stratum that defines survival until the final recurrent event rather than a fixed time point, yielding more stable and interpretable causal contrasts. We dev…

Trump signed an executive order decrying so-called anti-Christian bias in February,
and a hotline was created in April to encourage State Department workers to call in and snitch on their colleagues who might be acting with any kind of “anti-Christian bias.”
The Religious Liberty Commission was established via another executive order on May 1 during a flashy White House event.
Trump has even established his own Christian “faith” office in the White House, seemingly further…

Trump’s ‘anti-Christian bias’ taskforce reveals its propagandistic agenda in first meeting
Even though Christians are the dominant religious group in the country, Trump and his allies are desperate to portray persecution where there is none

Conservative data-driven finite element formulation
Adriana Kulikov\'a (Glasgow Computational Engineering Centre), Andrei G. Shvarts (Glasgow Computational Engineering Centre), {\L}ukasz Kaczmarczyk (Glasgow Computational Engineering Centre), Chris J. Pearce (Glasgow Computational Engineering Centre)
https://arxiv.org/abs/25…

Conservative data-driven finite element formulation
This paper presents a new data-driven finite element framework derived with mixed finite element formulation. The standard approach to diffusion problems requires the solution of the mathematical equations that describe both the conservation law and the constitutive relations, where the latter is traditionally obtained after fitting experimental data to simplified material models. To exploit all available information and avoid bias in the material model, we follow a data-driven approach. While …

Bimodal distribution of delay times and splitting of the zero-bias conductance peak in a double-barrier normal-superconductor junction
C. W. J. Beenakker, V. A. Zakharov
https://arxiv.org/abs/2506.18515

Bimodal distribution of delay times and splitting of the zero-bias conductance peak in a double-barrier normal-superconductor junction
We formulate a scattering theory of the proximity effect in a weakly disordered SININ junction (S = superconductor, I = insulating barrier, N = normal metal). This allows to relate the conductance and density of states of the junction to the scattering times $τ$ (eigenvalues of the Wigner-Smith time-delay matrix). The probability density $P(τ)$ has two peaks, at a short time $τ_{\rm min}$ and a late time $τ_{\rm max}$. The density of states at the Fermi level is the geometric mean of the tw…

Coining "#malcompetence" to mean "actions & their outcomes which are consistent with incompetence but which have an overall malicious effect, especially when the incompetence manifests differently in different situations to produced de facto discrimination."
Malcompetence can run the gamut from actual intentional malice disguised to appear as incompetence, to subconsciously coordinated malicious incompetence that the perpetrator is not consciously aware of but which a less subconsciously biased person would not engage in, to truly unintentional incompetence which manifests in a pattern because of bias in oversight/attention/competence-building. These different root causes are often not distinguishable, and sometimes blend together.
<does a quick search>
Okay, so it looks like I'm not the only one to have coined this term, but I think digging into the different types is still useful.

This https://arxiv.org/abs/2505.11370 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Understanding Nonlinear Implicit Bias via Region Counts in Input Space
One explanation for the strong generalization ability of neural networks is implicit bias. Yet, the definition and mechanism of implicit bias in non-linear contexts remains little understood. In this work, we propose to characterize implicit bias by the count of connected regions in the input space with the same predicted label. Compared with parameter-dependent metrics (e.g., norm or normalized margin), region count can be better adapted to nonlinear, overparameterized models, because it is de…

AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology
Akash Kundu, Rishika Goswami
https://arxiv.org/abs/2506.18156 https://

AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology
We investigate whether Large Language Models (LLMs) exhibit human-like cognitive patterns under four established frameworks from psychology: Thematic Apperception Test (TAT), Framing Bias, Moral Foundations Theory (MFT), and Cognitive Dissonance. We evaluated several proprietary and open-source models using structured prompts and automated scoring. Our findings reveal that these models often produce coherent narratives, show susceptibility to positive framing, exhibit moral judgments aligned wi…

Bias hardened estimators of patchy screening profiles
Noah Sailer, Boryana Hadzhiyska, Simone Ferraro
https://arxiv.org/abs/2506.17217 https://

Bias hardened estimators of patchy screening profiles
Detecting anisotropic screening of the cosmic microwave background (CMB) holds the promise of revealing the distribution of gas in the Universe, characterizing the complex processes of galaxy formation and feedback, and studying the epoch of reionization. Estimators for inhomogeneous screening, including some recently proposed small-scale (stacked) estimators, are quadratic or higher order in the CMB temperature or polarization fields and are therefore subject to contamination from CMB lensing.…

Impact of Detector Calibration Accuracy on Black Hole Spectroscopy
Mallika R. Sinha, Ling Sun, Sizheng Ma
https://arxiv.org/abs/2506.15979 https://

Impact of Detector Calibration Accuracy on Black Hole Spectroscopy
Systematic errors in detector calibration can bias signal analyses and potentially lead to incorrect interpretations suggesting violations of general relativity. In this study, we investigate how calibration systematics affect black hole (BH) spectroscopy, a technique that uses the quasinormal modes (QNMs) emitted during the ringdown phase of gravitational waves (GWs) to study remnant BHs formed in compact binary coalescences. We simulate a series of physically motivated, tunable calibration er…

Wenn das Finanzdepartement eine Milliarde Defizit budgediert, dann ist die Rechnung in der Regel positiv. Ich denke, die Schuldenbremse sollte diesen Bias berücksichtigen.

Bias Delayed is Bias Denied? Assessing the Effect of Reporting Delays on Disparity Assessments
Jennah Gosciak (Cornell University), Aparna Balagopalan (Massachusetts Institute of Technology), Derek Ouyang (Stanford University), Allison Koenecke (Cornell University), Marzyeh Ghassemi (Massachusetts Institute of Technology), Daniel E. Ho (Stanford University)

Bias Delayed is Bias Denied? Assessing the Effect of Reporting Delays on Disparity Assessments
Conducting disparity assessments at regular time intervals is critical for surfacing potential biases in decision-making and improving outcomes across demographic groups. Because disparity assessments fundamentally depend on the availability of demographic information, their efficacy is limited by the availability and consistency of available demographic identifiers. While prior work has considered the impact of missing data on fairness, little attention has been paid to the role of delayed dem…

Randall Munroe (of xkcd fame) posted about an analysis done by David R. Hagen related to his "missing 11th" comic. Great read, which includes some nice statistical analysis, but more interestingly, bias and artifacts.
https://bsky.app/profile/xkcd.com/post/3lrxgvl677…

Computer scientist Greg Nelson and I presented "Following AI's Footsteps from School to Society" at the 2025 UMaine Faculty Institute https://mycampus.maine.edu/web/uc-faculty-portal/faculty-institute-2025 including the IMPACT RISK framew…

Replaced article(s) found for econ.EM. https://arxiv.org/list/econ.EM/new
[1/1]:
- Assessing Omitted Variable Bias when the Controls are Endogenous
Paul Diegert, Matthew A. Masten, Alexandre Poirier

Omnidirectionally manipulated skyrmions in an orientationally chiral system
Jiahao Chen, Wentao Tang, Xingzhou Tang, Yang Ding, Jie Ni, Yuxi Chen, Bingxiang Li, Rui Zhang, Juan de Pablo, Yanqing Lu
https://arxiv.org/abs/2506.16781

Omnidirectionally manipulated skyrmions in an orientationally chiral system
Skyrmions, originally from condensed matter physics, have been widely explored in various physical systems, including soft matter. A crucial challenge in manipulating topological solitary waves like skyrmions is controlling their flow on demand. Here, we control the arbitrary moving direction of skyrmions in a chiral liquid crystal system by adjusting the bias of the applied alternate current electric field. Specifically, the velocity, including both moving direction and speed can be continuous…

How Robust is Model Editing after Fine-Tuning? An Empirical Study on Text-to-Image Diffusion Models
Feng He, Zhenyang Liu, Marco Valentino, Zhixue Zhao
https://arxiv.org/abs/2506.18428

How Robust is Model Editing after Fine-Tuning? An Empirical Study on Text-to-Image Diffusion Models
Model editing offers a low-cost technique to inject or correct a particular behavior in a pre-trained model without extensive retraining, supporting applications such as factual correction and bias mitigation. Despite this common practice, it remains unknown whether edits persist after fine-tuning or whether they are inadvertently reversed. This question has fundamental practical implications. For example, if fine-tuning removes prior edits, it could serve as a defence mechanism against hidden …

Hadamard Encoded Row Column Ultrasonic Expansive Scanning (HERCULES) with Bias-Switchable Row-Column Arrays
Darren Olufemi Dahunsi, Randy Palmar, Tyler Henry, Mohammad Rahim Sobhani, Negar Majidi, Joy Wang, Afshin Kashani Ilkhechi, Jeremy Brown, Roger Zemp
https://arxiv.org/abs/2506.11443

Hadamard Encoded Row Column Ultrasonic Expansive Scanning (HERCULES) with Bias-Switchable Row-Column Arrays
Top-Orthogonal-to-Bottom-Electrode (TOBE) arrays, also known as bias-switchable row-column arrays (RCAs), allow for imaging techniques otherwise impossible for non-bias-switachable RCAs. Hadamard Encoded Row Column Ultrasonic Expansive Scanning (HERCULES) is a novel imaging technique that allows for expansive 3D scanning by transmitting plane or cylindrical wavefronts and receiving using Hadamard-Encoded-Read-Out (HERO) to perform beamforming on what is effectively a full 2D synthetic receive a…

I just ran across this on LinkedIn: yet another study showing that LLMs embed and amplify human biases in the training data—this time in resume screening.
Yet this is the technology Trump, Musk, and DOGE want to use to rewrite things like HUD regulations and to replace human support agents.

Gender, race, and intersectional bias in AI resume screening via language model retrieval
Kyra Wilson and Aylin Caliskan examine gender, race, and intersectional bias in AI resume screening and suggest protective policies.

The Impact of $\Omega_{m0}$ Prior Bias on Cosmological Parameter Estimation: Reconciling DESI DR2 BAO and Pantheon SNe Data Combination Results
Seokcheon Lee
https://arxiv.org/abs/2506.16022

The Impact of $Ω_{m0}$ Prior Bias on Cosmological Parameter Estimation: Reconciling DESI DR2 BAO and Pantheon+ SNe Data Combination Results
Recent cosmological parameter analyses combining DESI DR2 Baryon Acoustic Oscillation (BAO) data with external probes, such as Pantheon+ Supernovae (SNe) observations, have reported deviations of the dark energy equation-of-state parameters ($\oo, \oa$) from the standard $Λ$CDM model predictions ($\oo=-1, \oa=0$). A notable aspect of these results is the role of $\Omo$ prior information from SNe, which is known to exhibit tension with BAO-only constraints. In this study, we rigorously investig…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/5]:
- ASCenD-BDS: Adaptable, Stochastic and Context-aware framework for Detection of Bias, Discriminati...
Rajiv Bahl, et al.

"Mitigating Bias and Advocating for Data Sovereignty: The Role of Metadata and Paradata in Ethical #AI-Driven Information Systems" https://doi.org/10.1080/19386389.2025.2515766

Intertwined magnetic phase driven exchange bias and its impact on the anomalous Hall effect in MnBi$_4$Te$_7$
Nazma Firdosh, Shreyashi Sinha, Indraneel Sinha, Mainpal Singh, Satyabrata Patnaik, Sujit Manna
https://arxiv.org/abs/2506.15540

Intertwined magnetic phase driven exchange bias and its impact on the anomalous Hall effect in MnBi$_4$Te$_7$
We report on the interplay between atomic scale inhomogeneity and competing magnetic phases and its effect on the anomalous Hall effect in the layered antiferromagnet MnBi$_4$Te$_7$, a natural superlattice hosting coexisting ferromagnetic and antiferromagnetic phases. Using a combination of scanning tunneling microscopy (STM), DC and AC magnetization, and magneto-transport measurements, we reveal that intrinsic Mn Bi antisite defects induce strong interlayer exchange coupling, giving rise to a …

Sources: FTC is discussing a consent decree on the Omnicom-Interpublic merger, prohibiting the combined company from boycotting platforms over political content (New York Times)
https://www.nytimes.com/2025/06/12/business/ftc-omnicom-interpublic-mer…

FTC May Impose Political Bias Rule on Omnicom and Interpublic Merger
The Federal Trade Commission is considering restrictions on Omnicom and Interpublic to prevent the combined company from refusing to place ads on platforms for political reasons.

SDDiff: Boost Radar Perception via Spatial-Doppler Diffusion
Shengpeng Wang, Xin Luo, Yulong Xie, Wei Wang
https://arxiv.org/abs/2506.16936 https://…

SDDiff: Boost Radar Perception via Spatial-Doppler Diffusion
Point cloud extraction (PCE) and ego velocity estimation (EVE) are key capabilities gaining attention in 3D radar perception. However, existing work typically treats these two tasks independently, which may neglect the interplay between radar's spatial and Doppler domain features, potentially introducing additional bias. In this paper, we observe an underlying correlation between 3D points and ego velocity, which offers reciprocal benefits for PCE and EVE. To fully unlock such inspiring potenti…

Mitigating collusion in Gold Humanism Honor Society nominations
Congzhou M Sha
https://arxiv.org/abs/2506.14061 https://arxiv.org/pdf…

Mitigating collusion in Gold Humanism Honor Society nominations
An anecdotally common complaint regarding induction into the Gold Humanism Honor Society is the bias toward close friends during the initial nomination process. In this work, we numerically simulate the nomination process under different assumptions, demonstrate that collusion can be detected, and propose a simple strategy to correct for bias in the nomination process.

The bias of IID resampled backtests for rolling-window mean-variance portfolios
Andrew Paskaramoorthy, Terence van Zyl, Tim Gebbie
https://arxiv.org/abs/2505.06383

The bias of IID resampled backtests for rolling-window mean-variance portfolios
Backtests on historical data are the basis for practical evaluations of portfolio selection rules, but their reliability is often limited by reliance on a single sample path. This can lead to high estimation variance. Resampling techniques offer a potential solution by increasing the effective sample size, but can disrupt the temporal ordering inherent in financial data and introduce significant bias. This paper investigates the critical questions: First, How large is this bias for Sharpe Ratio…

Visualization for interactively adjusting the de-bias effect of word embedding
Arisa Sugino, Takayuki Itoh
https://arxiv.org/abs/2506.02447 https://…

Visualization for interactively adjusting the de-bias effect of word embedding
Word embedding, which converts words into numerical values, is an important natural language processing technique and widely used. One of the serious problems of word embedding is that the bias will be learned and affect the model if the dataset used for pre-training contains bias. On the other hand, indiscriminate removal of bias from word embeddings may result in the loss of information, even if the bias is undesirable to us. As a result, a risk of model performance degradation due to bias re…

Modeling Gravitational Wave Bias from 3D Power Spectra of Spectroscopic Surveys
Dorsa Sadat Hosseini, Amir Dehghani, J. Leo Kim, Alex Krolewski, Suvodip Mukherjee, Ghazal Geshnizjani
https://arxiv.org/abs/2506.11201

Modeling Gravitational Wave Bias from 3D Power Spectra of Spectroscopic Surveys
We present a framework for relating gravitational wave (GW) sources to the astrophysical properties of spectroscopic galaxy samples. We show how this can enable using clustering measurements of gravitational wave (GW) sources to infer the relationship between the GW sources and the astrophysical properties of their host galaxies. We accomplish this by creating mock GW catalogs from the spectroscopic Sloan Digital Sky Survey (SDSS) DR7 galaxy survey. We populate the GWs using a joint host-galaxy…

You probably know I get frowny when browser makers lie about support or pretend their late implementation of a feature is somehow new, so I am suffering from a bunch of confirmation bias (and validation) here:
“Safari at WWDC '25: The Ghost of Christmas Past”
https://infrequently.org/2025…

Safari at WWDC '25: The Ghost of Christmas Past
Alex Russell on browsers, standards, and the process of progress.

Transfer entropy for finite data
Alec Kirkley
https://arxiv.org/abs/2506.16215 https://arxiv.org/pdf/2506.16215

Transfer entropy for finite data
Transfer entropy is a widely used measure for quantifying directed information flows in complex systems. While the challenges of estimating transfer entropy for continuous data are well known, it has two major shortcomings that persist even for data of finite cardinality: it exhibits a substantial positive bias for sparse bin counts, and it has no clear means to assess statistical significance. By more precisely accounting for information content in finite data streams, we derive a transfer ent…

Bias-field-free operation of nitrogen-vacancy ensembles in diamond for accurate vector magnetometry
Lilian Childress, Vincent Halde, Kayla Johnson, Andrew Lowther, David Roy-Guay, Romain Ruhlmann, Adrian Solyom
https://arxiv.org/abs/2505.24574

Bias-field-free operation of nitrogen-vacancy ensembles in diamond for accurate vector magnetometry
Accurate measurement of vector magnetic fields is critical for applications including navigation, geoscience, and space exploration. Nitrogen-vacancy (NV) center spin ensembles offer a promising solution for high-sensitivity vector magnetometry, as their different orientations in the diamond lattice measure different components of the magnetic field. However, the bias magnetic field typically used to separate signals from each NV orientation introduces inaccuracy from drifts in permanent magnet…

Roles of Non-switchable Domains and Internal Bias in Electrocaloric and Pyroelectric effects
Jun Usami, Yuki Okamoto, Hisashi Inoue, Takeshi Kobayashi, Hiroyuki Yamada
https://arxiv.org/abs/2506.07573

Roles of Non-switchable Domains and Internal Bias in Electrocaloric and Pyroelectric effects
Solid-state cooling and energy harvesting via pyroelectric effect (PEE) and electrocaloric effect (ECE) in ferroelectric thin films could be enhanced beyond their intrinsic ferroelectric response by exploiting the recently observed direction-dependent enhancement of the PEE; however, its microscopic origin remains unknown. Herein, we report direct hysteresis measurements of pyrocurrent ($I_{\rm p}$) and ECE-induced temperature change versus bias voltage in 1-$μ$m-thick Pb(Zr$_{0.65}$Ti$_{0.35}…

Excellent keynote in the #SemDH2025 workshop by Laura Hollink on Cultural Bias in Linked Open Data. Laura is addressing all bias related aspects in cultural heritage items itself, in the data representing it, the data schemata, vocabularies, and ontologies on which the data are based, as well as in the knowledge representation languages used to create the schemata.

This https://arxiv.org/abs/2501.07849 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation
Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation. In this paper, we reveal a novel provider bias in LLMs: without explicit directives, these models show systematic preferences for services from specific providers in their recommendations (e.g., favoring Google Cloud over Microsoft Azure). To systematically investigate this bias, we develop an automated pipeline to construct t…

Our results confirm persistent gender disparities:
women are more frequently acknowledged than credited as co-authors, especially in roles involving investigation and analysis
https://arxiv.org/abs/2506.15237

Dissecting the gender divide: Authorship and acknowledgment in scientific publications
The issue of gender bias in scientific publications has been the subject of ongoing debate. One aspect of this debate concerns whether women receive equal credit for their contributions compared to men. Conventional wisdom suggests that women are more likely to be acknowledged than listed as co-authors, a role that carries greater prestige. Here, we analyze data from hundreds of thousands of scientists across nine disciplines and a broad range of publications. Our results confirm persistent gen…

🇺🇦 #NowPlaying on #BBC6Music's #NickGrimshaw
Zed Bias:
🎵 Neighbourhood
#ZedBias
https://tonyquattro.bandcamp.com/album/zed-bias-neighbourhood-tony-quattros-saturday-night-mix
https://open.spotify.com/track/6J6QyLMIoToFr1VvDpt8jo

Trump-aligned legal group sues Michigan Law Review over 'Illegal DEI' bias (Kaelan Deese/Washington Examiner)
https://www.washingtonexaminer.com/news/3447681/trump-aligned-legal-group-sues-michigan-law-review/
http://www.memeorandum.com/250619/p93#a250619p93

Sources: FTC is discussing a consent decree on the Omnicom-Interpublic merger, prohibiting the combined company from boycotting platforms over political content (New York Times)
https://www.

FTC May Impose Political Bias Rule on Omnicom and Interpublic Merger
The Federal Trade Commission is considering restrictions on Omnicom and Interpublic to prevent the combined company from refusing to place ads on platforms for political reasons.

Improving precision of cumulative incidence estimates in randomized controlled trials with external controls
Zehao Su, Helene C. W. Rytgaard, Henrik Ravn, Frank Eriksson
https://arxiv.org/abs/2506.18415

Improving precision of cumulative incidence estimates in randomized controlled trials with external controls
Augmenting the control arm in clinical trials with external data can improve statistical power for demonstrating treatment effects. In many time-to-event outcome trials, participants are subject to truncation by death. Direct application of methods for competing risks analysis on the joint data may introduce bias, for example, due to covariate shifts between the populations. In this work, we consider transportability of the conditional cause-specific hazard of the event of interest under the co…

Mitigating Non-Target Speaker Bias in Guided Speaker Embedding
Shota Horiguchi, Takanori Ashihara, Marc Delcroix, Atsushi Ando, Naohiro Tawara
https://arxiv.org/abs/2506.12500

Mitigating Non-Target Speaker Bias in Guided Speaker Embedding
Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target speakers as clues, drastically improved embeddings under severe overlap with small degradation in low-overlap cases. However, since extreme overlaps are rare in natural conversations, this degradation cannot be overlooked. This paper first reveals that the degradation is caused by…

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 …

Dissecting the gender divide: Authorship and acknowledgment in scientific publications
Keigo Kusumegi, Yukie Sano, Daniel E. Acu\~na
https://arxiv.org/abs/2506.15237

Dissecting the gender divide: Authorship and acknowledgment in scientific publications
The issue of gender bias in scientific publications has been the subject of ongoing debate. One aspect of this debate concerns whether women receive equal credit for their contributions compared to men. Conventional wisdom suggests that women are more likely to be acknowledged than listed as co-authors, a role that carries greater prestige. Here, we analyze data from hundreds of thousands of scientists across nine disciplines and a broad range of publications. Our results confirm persistent gen…

I find myself thinking about a long-lost friend a lot lately. Sometime in the late 90s, we both accepted that our friendship had run its course. I had come to embrace fairly low-key socialism and he was increasingly angry about the media's "liberal bias." The common ground we had once shared was gone. I imagine him cheering now, even as I recall his father, a deeply conservative Marine colonel, remarking that only authoritarian regimes used the military against their own citize…

Adultification Bias in LLMs and Text-to-Image Models
Jane Castleman, Aleksandra Korolova
https://arxiv.org/abs/2506.07282 https://arx…

Adultification Bias in LLMs and Text-to-Image Models
The rapid adoption of generative AI models in domains such as education, policing, and social media raises significant concerns about potential bias and safety issues, particularly along protected attributes, such as race and gender, and when interacting with minors. Given the urgency of facilitating safe interactions with AI systems, we study bias along axes of race and gender in young girls. More specifically, we focus on "adultification bias," a phenomenon in which Black girls are presumed t…

ErrorEraser: Unlearning Data Bias for Improved Continual Learning
Xuemei Cao, Hanlin Gu, Xin Yang, Bingjun Wei, Haoyang Liang, Xiangkun Wang, Tianrui Li
https://arxiv.org/abs/2506.09347

ErrorEraser: Unlearning Data Bias for Improved Continual Learning
Continual Learning (CL) primarily aims to retain knowledge to prevent catastrophic forgetting and transfer knowledge to facilitate learning new tasks. Unlike traditional methods, we propose a novel perspective: CL not only needs to prevent forgetting, but also requires intentional forgetting.This arises from existing CL methods ignoring biases in real-world data, leading the model to learn spurious correlations that transfer and amplify across tasks. From feature extraction and prediction resul…

I just ran across this on LinkedIn: yet another study showing that LLMs embed and amplify human biases in the training data—this time in resume screening.
Yet this is the technology Trump, Musk, and DOGE want to use to rewrite things like HUD regulations and to replace human support agents.

Gender, race, and intersectional bias in AI resume screening via language model retrieval
Kyra Wilson and Aylin Caliskan examine gender, race, and intersectional bias in AI resume screening and suggest protective policies.

“In the US, we have a set of electoral and legislative institutions that drive us toward only having two parties,”
Mark Copelovitch told us.
“That allowed the 20 to 25 percent of people that support the far right to basically take over one of the two parties,
and everything in our system is weighted towards the Republican constituency
— the Supreme Court, the gerrymandered House, the way the Senate is apportioned.
All of these things basically bias the electo…

“Neither our media nor our political system is designed to deal with a far right authoritarian party”
Mark Copelovitch unpacks his signature phrase.

Using krypton-83m to determine the neutrino-mass bias caused by a non-constant electric potential of the KATRIN source
Moritz Machatschek
https://arxiv.org/abs/2506.13829

Using krypton-83m to determine the neutrino-mass bias caused by a non-constant electric potential of the KATRIN source
Precision spectroscopy of the electron spectrum of the tritium $β$ decay near the kinematic endpoint is a direct method to determine the effective electron antineutrino mass. The KArlsruhe TRItium Neutrino (KATRIN) experiment aims to determine this quantity with a sensitivity of better than $0.3\,\mathrm{eV}$ ($90\,\%$~C.L.). An inhomogeneous electric potential in the tritium source of KATRIN leads to a distortion of the $β$ spectrum, which directly impacts the neutrino-mass observable. This …

Bias-Switchable Row-Column Array Imaging using Fast Orthogonal Row-Column Electronic Scanning (FORCES) Compared with Conventional Row-Column Array Imaging
Randy Palamar, Mohammad Rahim Sobhani, Darren Dahunsi, Negar Majidi, Afshin Kashani Ilkhechi, Joy Wang, Jeremy Brown, Roger Zemp
https://arxiv.org/abs/2506.10958

Bias-Switchable Row-Column Array Imaging using Fast Orthogonal Row-Column Electronic Scanning (FORCES) Compared with Conventional Row-Column Array Imaging
Row-Column Arrays (RCAs) offer an attractive alternative to fully wired 2D-arrays for 3D-ultrasound, due to their greatly simplified wiring. However, conventional RCAs face challenges related to their long elements. These include an inability to image beyond the shadow of the aperture and an inability to focus in both transmit and receive for desired scan planes. To address these limitations, we recently developed bias-switchable RCAs, also known as Top Orthogonal to Bottom Electrode (TOBE) arr…

This https://arxiv.org/abs/2504.00998 has been replaced.
initial toot: https://mastoxiv.page/@a…

Real-space methods for ab initio modelling of surfaces and interfaces under external potential bias
Accurate ab initio modelling of surfaces and interfaces, especially under an applied external potential bias, is important for describing and characterizing various phenomena that occur in electronic, catalytic, and energy storage devices. Leveraging the ability of real-space density functional theory (DFT) codes to accommodate generic boundary conditions, we introduce two methods for applying an external potential bias that can be suitable for modelling surfaces and interfaces. In the first me…

Scatter in the star formation rate-halo mass relation: secondary bias and its impact on line-intensity mapping
Rui Lan Jun (UTokyo), Tom Theuns (ICC, Durham), Kana Moriwaki (UTokyo), Sownak Bose (ICC, Durham)
https://arxiv.org/abs/2506.03015

Scatter in the star formation rate-halo mass relation: secondary bias and its impact on line-intensity mapping
We use the IllustrisTNG cosmological hydrodynamical simulations to study the impact of secondary bias -- specifically, the correlation between star formation rate (SFR) and halo bias at fixed halo mass -- on the line-intensity mapping (LIM) power spectrum. In LIM, the galaxy contributions are flux-weighted, and for many emission lines (e.g., H$α$), flux scales with SFR. We show that the (ensemble-averaged) large-scale two-halo term of the power spectrum depends only on the mean luminosity-halo…

Accelerating ground-state auxiliary-field quantum Monte Carlo simulations by delayed update and block force-bias update
Hao Du, Yuan-Yao He
https://arxiv.org/abs/2506.09611

Accelerating ground-state auxiliary-field quantum Monte Carlo simulations by delayed update and block force-bias update
Ground-state auxiliary-field quantum Monte Carlo (AFQMC) methods have become key numerical tools for studying quantum phases and phase transitions in interacting many-fermion systems. Despite the broad applicability, the efficiency of these algorithms is often limited by the bottleneck associated with the {\it local update} of the field configuration. In this work, we propose two novel update schemes, the {\it delayed update} and {\it block force-bias update}, both of which can generally and ef…

Weighted Parameter Estimators of the Generalized Extreme Value Distribution in the Presence of Missing Observations
James H. McVittie, Orla A. Murphy
https://arxiv.org/abs/2506.15964

Weighted Parameter Estimators of the Generalized Extreme Value Distribution in the Presence of Missing Observations
Missing data occur in a variety of applications of extreme value analysis. In the block maxima approach to an extreme value analysis, missingness is often handled by either ignoring missing observations or dropping a block of observations from the analysis. However, in some cases, missingness may occur due to equipment failure during an extreme event, which can lead to bias in estimation. In this work, we propose weighted maximum likelihood and weighted moment-based estimators for the generaliz…

VGR: Visual Grounded Reasoning
Jiacong Wang, Zijiang Kang, Haochen Wang, Haiyong Jiang, Jiawen Li, Bohong Wu, Ya Wang, Jiao Ran, Xiao Liang, Chao Feng, Jun Xiao
https://arxiv.org/abs/2506.11991

VGR: Visual Grounded Reasoning
In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This narrow focus limits their ability to handle complex visual reasoning tasks that demand comprehensive understanding of image details. To address these limitations, this paper introduces VGR, a novel reasoning multimodal large language model (MLLM) with enhanced …

Non-Separable Halo Bias from High-Redshift Galaxy Clustering
Emy Mons, Vipul Prasad Maranchery, M. S. Suryan Sivadas, Charles Jose
https://arxiv.org/abs/2506.07662

Non-Separable Halo Bias from High-Redshift Galaxy Clustering
The halo model provides a powerful framework for interpreting galaxy clustering by linking the spatial distribution of dark matter haloes to the underlying matter distribution. A key assumption within the linear bias approximation of the halo model is that the halo bias between two halo populations is a separable function of the mass of each population. In this work, we test the validity of the separable bias approximation on quasi-linear scales using both simulations and observational data. Un…

Correcting for Position Bias in Learning to Rank: A Control Function Approach
Md Aminul Islam, Kathryn Vasilaky, Elena Zheleva
https://arxiv.org/abs/2506.06989

Correcting for Position Bias in Learning to Rank: A Control Function Approach
Implicit feedback data, such as user clicks, is commonly used in learning-to-rank (LTR) systems because it is easy to collect and it often reflects user preferences. However, this data is prone to various biases, and training an LTR system directly on biased data can result in suboptimal ranking performance. One of the most prominent and well-studied biases in implicit feedback data is position bias, which occurs because users are more likely to interact with higher-ranked documents regardless …

This https://arxiv.org/abs/2506.00253 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race
Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about their fair usage. We investigate the mechanisms behind this discrepancy and find that alignment surprisingly amplifies implicit bias in model outputs. Specifically, we show that aligned LMs, unlike their unaligned counterparts, overlook racial concepts in early internal representations when the context is ambiguous. …

Leveraging erasure errors in logical qubits with metastable $^{171}$Yb atoms
Bichen Zhang, Genyue Liu, Guillaume Bornet, Sebastian P. Horvath, Pai Peng, Shuo Ma, Shilin Huang, Shruti Puri, Jeff D. Thompson
https://arxiv.org/abs/2506.13724

Leveraging erasure errors in logical qubits with metastable $^{171}$Yb atoms
Implementing large-scale quantum algorithms with practical advantage will require fault-tolerance achieved through quantum error correction, but the associated overhead is a significant cost. The overhead can be reduced by engineering physical qubits with fewer errors, and by shaping the residual errors to be more easily correctable. In this work, we demonstrate quantum error correcting codes and logical qubit circuits in a metastable ${}^{171}$Yb qubit with a noise bias towards erasure errors,…

An interview with Gaia Marcus, director of the UK-based think tank Ada Lovelace Institute, on AI regulation in the UK and Europe, AI safety, bias, and more (Melissa Heikkilä/Financial Times)

Ada Lovelace Institute’s Gaia Marcus: regulation would increase people’s comfort with AI
The head of the UK-based think-tank talks about her hopes and fears for future oversight of AI

Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias
Yuanzhe Hu, Kinshuk Goel, Vlad Killiakov, Yaoqing Yang
https://arxiv.org/abs/2506.06280

Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias
Diagnosing deep neural networks (DNNs) through the eigenspectrum of weight matrices has been an active area of research in recent years. At a high level, eigenspectrum analysis of DNNs involves measuring the heavytailness of the empirical spectral densities (ESD) of weight matrices. It provides insight into how well a model is trained and can guide decisions on assigning better layer-wise training hyperparameters. In this paper, we address a challenge associated with such eigenspectrum methods:…

DiffPR: Diffusion-Based Phase Reconstruction via Frequency-Decoupled Learning
Yi Zhang
https://arxiv.org/abs/2506.11183 https://arxiv…

DiffPR: Diffusion-Based Phase Reconstruction via Frequency-Decoupled Learning
Oversmoothing remains a persistent problem when applying deep learning to off-axis quantitative phase imaging (QPI). End-to-end U-Nets favour low-frequency content and under-represent fine, diagnostic detail. We trace this issue to spectral bias and show that the bias is reinforced by high-level skip connections that feed high-frequency features directly into the decoder. Removing those deepest skips thus supervising the network only at a low resolution significantly improves generalisation and…

Affective-CARA: A Knowledge Graph Driven Framework for Culturally Adaptive Emotional Intelligence in HCI
Nirodya Pussadeniya, Bahareh Nakisa, Mohmmad Naim Rastgoo
https://arxiv.org/abs/2506.14166

Affective-CARA: A Knowledge Graph Driven Framework for Culturally Adaptive Emotional Intelligence in HCI
Culturally adaptive emotional responses remain a critical challenge in affective computing. This paper introduces Affective-CARA, an agentic framework designed to enhance user-agent interactions by integrating a Cultural Emotion Knowledge Graph (derived from StereoKG) with Valence, Arousal, and Dominance annotations, culture-specific data, and cross-cultural checks to minimize bias. A Gradient-Based Reward Policy Optimization mechanism further refines responses according to cultural alignment, …

Towards Understanding Bias in Synthetic Data for Evaluation
Hossein A. Rahmani, Varsha Ramineni, Nick Craswell, Bhaskar Mitra, Emine Yilmaz
https://arxiv.org/abs/2506.10301

Towards Understanding Bias in Synthetic Data for Evaluation
Test collections are crucial for evaluating Information Retrieval (IR) systems. Creating a diverse set of user queries for these collections can be challenging, and obtaining relevance judgments, which indicate how well retrieved documents match a query, is often costly and resource-intensive. Recently, generating synthetic datasets using Large Language Models (LLMs) has gained attention in various applications. While previous work has used LLMs to generate synthetic queries or documents to imp…

Bias and Identifiability in the Bounded Confidence Model
Claudio Borile, Jacopo Lenti, Valentina Ghidini, Corrado Monti, Gianmarco De Francisci Morales
https://arxiv.org/abs/2506.11751

Bias and Identifiability in the Bounded Confidence Model
Opinion dynamics models such as the bounded confidence models (BCMs) describe how a population can reach consensus, fragmentation, or polarization, depending on a few parameters. Connecting such models to real-world data could help understanding such phenomena, testing model assumptions. To this end, estimation of model parameters is a key aspect, and maximum likelihood estimation provides a principled way to tackle it. Here, our goal is to outline the properties of statistical estimators of th…

Measuring and Minimizing Disturbance of Marine Animals to Underwater Vehicles
Levi Cai, Youenn J\'ez\'equel, T. Aran Mooney, Yogesh Girdhar
https://arxiv.org/abs/2506.11335

Measuring and Minimizing Disturbance of Marine Animals to Underwater Vehicles
Do fish respond to the presence of underwater vehicles, potentially biasing our estimates about them? If so, are there strategies to measure and mitigate this response? This work provides a theoretical and practical framework towards bias-free estimation of animal behavior from underwater vehicle observations. We also provide preliminary results from the field in coral reef environments to address these questions.

A Framework for Auditing Chatbots for Dialect-Based Quality-of-Service Harms
Emma Harvey, Rene F. Kizilcec, Allison Koenecke
https://arxiv.org/abs/2506.04419

A Framework for Auditing Chatbots for Dialect-Based Quality-of-Service Harms
Increasingly, individuals who engage in online activities are expected to interact with large language model (LLM)-based chatbots. Prior work has shown that LLMs can display dialect bias, which occurs when they produce harmful responses when prompted with text written in minoritized dialects. However, whether and how this bias propagates to systems built on top of LLMs, such as chatbots, is still unclear. We conduct a review of existing approaches for auditing LLMs for dialect bias and show tha…

Analysis of LLM Bias (Chinese Propaganda & Anti-US Sentiment) in DeepSeek-R1 vs. ChatGPT o3-mini-high
PeiHsuan Huang, ZihWei Lin, Simon Imbot, WenCheng Fu, Ethan Tu
https://arxiv.org/abs/2506.01814

Analysis of LLM Bias (Chinese Propaganda & Anti-US Sentiment) in DeepSeek-R1 vs. ChatGPT o3-mini-high
Large language models (LLMs) increasingly shape public understanding and civic decisions, yet their ideological neutrality is a growing concern. While existing research has explored various forms of LLM bias, a direct, cross-lingual comparison of models with differing geopolitical alignments-specifically a PRC-system model versus a non-PRC counterpart-has been lacking. This study addresses this gap by systematically evaluating DeepSeek-R1 (PRC-aligned) against ChatGPT o3-mini-high (non-PRC) for…

CSST Cosmological Emulator III: Hybrid Lagrangian Bias Expansion Emulation of Galaxy Clustering
Shuren Zhou, Zhao Chen, Yu Yu
https://arxiv.org/abs/2506.04671

CSST Cosmological Emulator III: Hybrid Lagrangian Bias Expansion Emulation of Galaxy Clustering
Galaxy clustering is an important probe in the upcoming China Space Station Telescope (CSST) survey to understand the structure growth and reveal the nature of the dark sector. However, it is a long-term challenge to model this biased tracer and connect the observable to the underlying physics. In this work, we present a hybrid Lagrangian bias expansion emulator, combining the Lagrangian bias expansion and the accurate dynamical evolution from $N$-body simulation, to predict the power spectrum …

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…

Generalizable estimation of conditional average treatment effects using Causal Forest in randomized
Rikuta Hamaya, Etsuji Suzuki, Konan Hara
https://arxiv.org/abs/2506.12296

Generalizable estimation of conditional average treatment effects using Causal Forest in randomized
Generalizing conditional average treatment effects (CATE) estimates in a randomized controlled trial (RCT) to a broader source population can be challenging because of selection bias and high-dimensional covariates. We aim to evaluate CATE estimation approaches using Causal Forest that address selection bias due to trial participation. We propose and compare four CATE estimation approaches using Causal Forest: (1) ignoring selection variables, (2) including selection variables, (3) using invers…

This https://arxiv.org/abs/2503.23630 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Finding Interest Needle in Popularity Haystack: Improving Retrieval by Modeling Item Exposure
Recommender systems operate in closed feedback loops, where user interactions reinforce popularity bias, leading to over-recommendation of already popular items while under-exposing niche or novel content. Existing bias mitigation methods, such as Inverse Propensity Scoring (IPS) and Off-Policy Correction (OPC), primarily operate at the ranking stage or during training, lacking explicit real-time control over exposure dynamics. In this work, we introduce an exposure-aware retrieval scoring appr…

A Two-step Estimating Approach for Heavy-tailed AR Models with General Non-zero Median Noises
Rui She, Linlin Dai, Shiqing Ling
https://arxiv.org/abs/2506.11509

A Two-step Estimating Approach for Heavy-tailed AR Models with General Non-zero Median Noises
This paper develops a novel two-step estimating procedure for heavy-tailed AR models with non-zero median noises, allowing for time-varying volatility. We first establish the self-weighted quantile regression estimator (SQE) across all quantile levels $τ\in (0,1)$ for the AR parameters $θ_{0}$. We show that the SQE, minus a bias, converges weakly to a Gaussian process uniformly at a rate of $n^{-1/2}$. The bias is zero if and only if $τ$ equals $τ_{0}$, the probability that the noise is l…

Scale-dependent bias and mode coupling in redshift-space clustering near the BAO scale
Aseem Paranjape (IUCAA), Ravi K. Sheth (UPenn/ICTP)
https://arxiv.org/abs/2506.08082

Scale-dependent bias and mode coupling in redshift-space clustering near the BAO scale
The baryon acoustic oscillation (BAO) feature in the 2-point clustering of biased tracers in redshift space can be described in a model-agnostic manner, relying only on the assumption that nonlinear growth approximately smears this feature with a Gaussian kernel sourced by gravitationally driven bulk flows as in the Zel'dovich approximation. An explicit model that demonstrated this in recent work did not account for two physical effects that are very likely observationally relevant in the conte…

Benford's Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
Jiandong Shao, Yao Lu, Jianfei Yang
https://arxiv.org/abs/2506.01734 https://

Benford's Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
Large Language Models (LLMs) exhibit impressive performance on complex reasoning tasks, yet they frequently fail on basic numerical problems, producing incorrect outputs. Inspired by Benford's Law -- a statistical pattern where lower digits occur more frequently as leading digits -- we hypothesize that the long-tailed digit distributions in web-collected corpora may be learned by LLMs during pretraining, leading to biased numerical generation. To investigate the hypothesis, we first examine whe…

Recover Experimental Data with Selection Bias using Counterfactual Logic
Jingyang He, Shuai Wang, Ang Li
https://arxiv.org/abs/2506.00335 https://

Recover Experimental Data with Selection Bias using Counterfactual Logic
Selection bias, arising from the systematic inclusion or exclusion of certain samples, poses a significant challenge to the validity of causal inference. While Bareinboim et al. introduced methods for recovering unbiased observational and interventional distributions from biased data using partial external information, the complexity of the backdoor adjustment and the method's strong reliance on observational data limit its applicability in many practical settings. In this paper, we formally di…