Tootfinder

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

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

Note on Selection Bias in Observational Estimates of Algorithmic Progress
Parker Whitfill
https://arxiv.org/abs/2508.11033 https://arxiv.org/pdf/2508.11033…

Note on Selection Bias in Observational Estimates of Algorithmic Progress
Ho et. al (2024) is an interesting paper that attempts to estimate the degree of algorithmic progress from language models. They collect observational data on language models' loss and compute over time, and argue that as time has passed, language models' algorithmic efficiency has been rising. That is, the loss achieved for fixed compute has been dropping over time. In this note, I want to raise one potential methodological problem with the estimation strategy. Intuitively, if part of algorith…

BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
Thierry Blankenstein, Jialin Yu, Zixuan Li, Vassilis Plachouras, Sunando Sengupta, Philip Torr, Yarin Gal, Alasdair Paren, Adel Bibi
https://arxiv.org/abs/2510.00307

BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
Agents backed by large language models (LLMs) often rely on external tools drawn from marketplaces where multiple providers offer functionally equivalent options. This raises a critical point concerning fairness: if selection is systematically biased, it can degrade user experience and distort competition by privileging some providers over others. We introduce a benchmark of diverse tool categories, each containing multiple functionally equivalent tools, to evaluate tool-selection bias. Using t…

Z-Curve Plot: A Visual Diagnostic for Publication Bias in Meta-Analysis
Franti\v{s}ek Barto\v{s}, Ulrich Schimmack
https://arxiv.org/abs/2509.07171 https://

Z-Curve Plot: A Visual Diagnostic for Publication Bias in Meta-Analysis
Publication bias undermines meta-analytic inference, yet visual diagnostics for detecting model misfit due to publication bias are lacking. We propose the z-curve plot, a publication-bias-focused absolute model fit diagnostic. The z-curve plot overlays the model-implied posterior predictive distribution of $z$-statistics on the observed distribution of z-statistics and enables direct comparison across candidate meta-analytic models (e.g., random-effects meta-analysis, selection models, PET-PEES…

Correcting sample selection bias with categorical outcomes
Onil Boussim
https://arxiv.org/abs/2510.05551 https://arxiv.org/pdf/2510.05551

Correcting sample selection bias with categorical outcomes
In this paper, we propose a method for correcting sample selection bias when the outcome of interest is categorical, such as occupational choice, health status, or field of study. Classical approaches to sample selection rely on strong parametric distributional assumptions, which may be restrictive in practice. While the recent framework of Chernozhukov et al. (2023) offers a nonparametric identification using a local Gaussian representation (LGR) that holds for any bivariate joint distribution…

The Oatmeal comic about "AI" "art" is great, but I have to critize the "I like AI, I use AI" part; there's a selection bias at work—he sees the generated "art" as very obviously for what it is, (dehumanizing low-effort slop) but doesn't make the logical conclusion that this is true for _any type of output_ (e.g. text); it always dehumanizing low-effort slop that's not worth looking at, listening to or reading.

Who Gets Cited? Gender- and Majority-Bias in LLM-Driven Reference Selection
Jiangen He
https://arxiv.org/abs/2508.02740 https://arxiv.org/pdf/2508.02740

Who Gets Cited? Gender- and Majority-Bias in LLM-Driven Reference Selection
Large language models (LLMs) are rapidly being adopted as research assistants, particularly for literature review and reference recommendation, yet little is known about whether they introduce demographic bias into citation workflows. This study systematically investigates gender bias in LLM-driven reference selection using controlled experiments with pseudonymous author names. We evaluate several LLMs (GPT-4o, GPT-4o-mini, Claude Sonnet, and Claude Haiku) by varying gender composition within c…

Impact of projection-induced optical selection bias on the weak lensing mass calibration of galaxy clusters
Titus Nyarko Nde, Hao-Yi Wu, Shulei Cao, Gladys Muthoni Kamau, Andrius Tamosiunas, Chun-Hao To, Conghao Zhou
https://arxiv.org/abs/2510.00753

Impact of projection-induced optical selection bias on the weak lensing mass calibration of galaxy clusters
Weak gravitational lensing signals of optically identified clusters are impacted by a selection bias -- halo triaxiality and large-scale structure along the line of sight simultaneously boost the lensing signal and richness (the inferred number of galaxies associated with a cluster). As a result, a cluster sample selected by richness has a mean lensing signal higher than expected from its mean mass, and the inferred mass will be biased high. This selection bias is currently limiting the accurac…

Hearing the Order: Investigating Selection Bias in Large Audio-Language Models
Yu-Xiang Lin, Chen-An Li, Sheng-Lun Wei, Po-Chun Chen, Hsin-Hsi Chen, Hung-yi Lee
https://arxiv.org/abs/2510.00628

Hearing the Order: Investigating Selection Bias in Large Audio-Language Models
Large audio-language models (LALMs) are often used in tasks that involve reasoning over ordered options. An open question is whether their predictions are influenced by the order of answer choices, which would indicate a form of selection bias and undermine their reliability. In this paper, we identify and analyze this problem in LALMs. We demonstrate that no model is immune to this bias through extensive experiments on six LALMs across three widely used benchmarks and their spoken counterparts…

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 …

Ethical AI prompt recommendations in large language models using collaborative filtering
Jordan Nelson, Almas Baimagambetov, Konstantinos Avgerinakis, Nikolaos Polatidis
https://arxiv.org/abs/2510.06924

Ethical AI prompt recommendations in large language models using collaborative filtering
As large language models (LLMs) shape AI development, ensuring ethical prompt recommendations is crucial. LLMs offer innovation but risk bias, fairness issues, and accountability concerns. Traditional oversight methods struggle with scalability, necessitating dynamic solutions. This paper proposes using collaborative filtering, a technique from recommendation systems, to enhance ethical prompt selection. By leveraging user interactions, it promotes ethical guidelines while reducing bias. Contri…

Selection bias is a Schedule I drug

Uncertainty-Driven Hierarchical Sampling for Unbalanced Continual Malware Detection with Time-Series Update-Based Retrieval
Yi Xie, Ziyuan Yang, Yongqiang Huang, Yinyu Chen, Lei Zhang, Liang Liu, Yi Zhang
https://arxiv.org/abs/2509.07532

Uncertainty-Driven Hierarchical Sampling for Unbalanced Continual Malware Detection with Time-Series Update-Based Retrieval
Android malware detection continues to face persistent challenges stemming from long-term concept drift and class imbalance, as evolving malicious behaviors and shifting usage patterns dynamically reshape feature distributions. Although continual learning (CL) mitigates drift, existing replay-based methods suffer from inherent bias. Specifically, their reliance on classifier uncertainty for sample selection disproportionately prioritizes the dominant benign class, causing overfitting and reduce…

Selection Bias in Hybrid Randomized Controlled Trials using External Controls: A Simulation Study
Han Chang Chiam, Franz K\"onig, Martin Posch
https://arxiv.org/abs/2510.04829

Selection Bias in Hybrid Randomized Controlled Trials using External Controls: A Simulation Study
Hybrid randomized controlled trials (hybrid RCTs) integrate external control data, such as historical or concurrent data, with data from randomized trials. While numerous frequentist and Bayesian methods, such as the test-then-pool and Meta-Analytic-Predictive prior, have been developed to account for potential disagreement between the external control and randomized data, they cannot ensure strict type I error rate control. However, these methods can reduce biases stemming from systematic diff…

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

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

Adaptive Density Estimation Using Projection Kernels and Penalized Comparison to Overfitting
Van Ha Hoang, Tien Dat Nguyen, Thi Mong Ngoc Nguyen
https://arxiv.org/abs/2509.07800

Adaptive Density Estimation Using Projection Kernels and Penalized Comparison to Overfitting
In this work, we study wavelet projection estimators for density estimation, focusing on their construction from $\mathcal{S}$-regular, compactly supported wavelet bases. A key aspect of such estimators is the choice of the resolution level, which controls the balance between bias and variance. To address this, we employ the Penalized Comparison to Overfitting (PCO) method, providing a fully data-driven selection of the multiresolution level. This approach ensures both statistical accuracy and …

Identifying treatment effects on categorical outcomes in IV models
Onil Boussim
https://arxiv.org/abs/2510.10946 https://arxiv.org/pdf/2510.10946

Identifying treatment effects on categorical outcomes in IV models
This paper provides a nonparametric framework for causal inference with categorical outcomes under binary treatment and binary instrument settings. We decompose the observed joint probability of outcomes and treatment into marginal probabilities of potential outcomes and treatment, and association parameters that capture selection bias due to unobserved heterogeneity. Under a novel identifying assumption, association similarity, which requires the dependence between unobserved factors and poten…

HSFN: Hierarchical Selection for Fake News Detection building Heterogeneous Ensemble
Sara B. Coutinho, Rafael M. O. Cruz, Francimaria R. S. Nascimento, George D. C. Cavalcanti
https://arxiv.org/abs/2508.21482

HSFN: Hierarchical Selection for Fake News Detection building Heterogeneous Ensemble
Psychological biases, such as confirmation bias, make individuals particularly vulnerable to believing and spreading fake news on social media, leading to significant consequences in domains such as public health and politics. Machine learning-based fact-checking systems have been widely studied to mitigate this problem. Among them, ensemble methods are particularly effective in combining multiple classifiers to improve robustness. However, their performance heavily depends on the diversity of …

Replaced article(s) found for nucl-ex. https://arxiv.org/list/nucl-ex/new
[1/1]:
- Selection bias effects on high-$p_\mathrm{T}$ yield and correlation measurements in Oxygen Oxygen...
JaeBeom Park, J. L. Nagle, Dennis V. Perepelitsa, Sanghoon Lim, Constantin Loizides

Mediation Analysis in the Presence of Sample Selection Bias with an Application to Disparities in Liver Transplantation Listing
Zain Khan, Lynnette Sequeira, Alexandra T. Strauss, Vedant Jain, Juliette Dixon, Eric Moughames, Tyrus Vong, Daniel Malinsky
https://arxiv.org/abs/2509.01969

Mediation Analysis in the Presence of Sample Selection Bias with an Application to Disparities in Liver Transplantation Listing
The study of disparities in the liver transplantation process may focus on quantifying causal effects, particularly the average, direct, or indirect effects of various social determinants of health on being listed as a candidate for transplant. Selection bias arises when the data sample does not represent the target population, defined here as all individuals referred to the transplant clinic. Listing decisions are made for the subset of patients who complete the evaluation process, who may dif…

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

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

Multi-view-guided Passage Reranking with Large Language Models
Jeongwoo Na, Jun Kwon, Eunseong Choi, Jongwuk Lee
https://arxiv.org/abs/2509.07485 https://a…

Multi-view-guided Passage Reranking with Large Language Models
Recent advances in large language models (LLMs) have shown impressive performance in passage reranking tasks. Despite their success, LLM-based methods still face challenges in efficiency and sensitivity to external biases. (1) Existing models rely mostly on autoregressive generation and sliding window strategies to rank passages, which incur heavy computational overhead as the number of passages increases. (2) External biases, such as position or selection bias, hinder the model's ability to ac…

Distinguishability of causal structures under latent confounding and selection
Ryan Carey, Marina Maciel Ansanelli, Elie Wolfe, Robin J. Evans
https://arxiv.org/abs/2509.20433 h…

Distinguishability of causal structures under latent confounding and selection
Statistical relationships in observed data can arise for several different reasons: the observed variables may be causally related, they may share a latent common cause, or there may be selection bias. Each of these scenarios can be modelled using different causal graphs. Not all such causal graphs, however, can be distinguished by experimental data. In this paper, we formulate the equivalence class of causal graphs as a novel graphical structure, the selected-marginalized directed graph (smDG)…

Empirical likelihood meta analysis with publication bias correction under Copas-like selection model
Mengke Li, Yukun Liu, Pengfei Li, Jing Qin
https://arxiv.org/abs/2507.13615

Empirical likelihood meta analysis with publication bias correction under Copas-like selection model
Meta analysis is commonly-used to synthesize multiple results from individual studies. However, its validation is usually threatened by publication bias and between-study heterogeneity, which can be captured by the Copas selection model. Existing inference methods under this model are all based on conditional likelihood and may not be fully efficient. In this paper, we propose a full likelihood approach to meta analysis by integrating the conditional likelihood and a marginal semi-parametric em…

NA61/SHINE results on multiplicity and net-charge fluctuations at CERN SPS energies
Ma\'ckowiak-Paw{\l}owska
https://arxiv.org/abs/2510.00687 https://a…

NA61/SHINE results on multiplicity and net-charge fluctuations at CERN SPS energies
This contribution presents final results on the energy dependence of multiplicity and net-electric charge fluctuations in Ar+Sc interactions collected by the NA61/SHINE experiment. Fluctuations were analyzed using higher-order cumulant ratios in Ar+Sc most central collisions and compared to p+p interactions. The results consider detector bias and centrality selection in the case of Ar+Sc. The results are compared across different energies and against model predictions.

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

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

A Greedy PDE Router for Blending Neural Operators and Classical Methods
Sahana Rayan, Yash Patel, Ambuj Tewari
https://arxiv.org/abs/2509.24814 https://arx…

A Greedy PDE Router for Blending Neural Operators and Classical Methods
When solving PDEs, classical numerical solvers are often computationally expensive, while machine learning methods can suffer from spectral bias, failing to capture high-frequency components. Designing an optimal hybrid iterative solver--where, at each iteration, a solver is selected from an ensemble of solvers to leverage their complementary strengths--poses a challenging combinatorial problem. While the greedy selection strategy is desirable for its constant-factor approximation guarantee to …

Tree-based methods for length-biased survival data
Jinwoo Lee, Jiyu Sun, Hyunwoo Lee, Donghwan Lee
https://arxiv.org/abs/2508.16312 https://arxiv.org/pdf/2…

Tree-based methods for length-biased survival data
Left-truncated survival data commonly arise in prevalent cohort studies, where only individuals who have experienced disease onset and survived until enrollment in the study. When the onset process follows a stationary Poisson process, the resulting data are length-biased. This sampling mechanism induces a selection bias towards longer survival individuals, and nonparametric and semiparametric methods for traditional survival data are not directly applicable. While tree-based methods developed …

Enhanced Survival Trees
Ruiwen Zhou, Ke Xie, Lei Liu, Zhichen Xu, Jimin Ding, Xiaogang Su
https://arxiv.org/abs/2509.18494 https://arxiv.org/pdf/2509.18494…

Enhanced Survival Trees
We introduce a new survival tree method for censored failure time data that incorporates three key advancements over traditional approaches. First, we develop a more computationally efficient splitting procedure that effectively mitigates the end-cut preference problem, and we propose an intersected validation strategy to reduce the variable selection bias inherent in greedy searches. Second, we present a novel framework for determining tree structures through fused regularization. In combinati…