Tootfinder

Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling
Shuliang Liu, Zhipeng Xu, Zhenghao Liu, Yukun Yan, Minghe Yu, Yu Gu, Chong Chen, Huiyuan Xie, Ge Yu
https://arxiv.org/abs/2510.08145

Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling
Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach plays a vital role in aligning LLMs with human judgments, providing accurate and reliable assessments. However, LLM-based judgment models often exhibit judgment preference bias during the evaluation phase, tending to favor responses generated by themselves, undermining the reliability of their judgments. This paper introduces the Group-Based Polling …

Public Communication with Externalities
Georgy Lukyanov, Konstantin Shamruk, Tong Su, Ahmed Wakrim
https://arxiv.org/abs/2509.08850 https://arxiv.org/pdf/2…

Public Communication with Externalities
This paper develops a model in which a sender strategically communicates with a group of receivers whose payoffs depend on the sender's information. It is shown that aggregate payoff externalities create an endogenous conflict of interests between the sender and the receivers, rendering full information revelation, in general infeasible. We demonstrate that an exogenous bias in the sender's preferences can improve public information provision and raise welfare. Two applications of the setup are…

Strong progenitor age bias in supernova #cosmology – I. Robust and ubiquitous evidence from a larger sample of host galaxies in a broader redshift range / II. Alignment with DESI BAO and signs of a non-accelerating universe: https://academic.oup.com/mnras/article/538/4/3340/8098234 / https://academic.oup.com/mnras/article/544/1/975/8281988 -> Universe's expansion 'is now slowing, not speeding up': https://ras.ac.uk/news-and-press/research-highlights/universes-expansion-now-slowing-not-speeding (this has been claimed by the group since at least 2023 - http://vietnam.in2p3.fr/2023/windows/transparencies/02_tuesday/Astro_5/01_Son.pdf - and is rejected by the SN cosmology community as https://bsky.app/profile/astromarc.bsky.social/post/3m4xmikwfds26 explains).

Social bias is prevalent in user reports of hate and abuse online
Florence E. Enock, Helen Z. Margetts, Jonathan Bright
https://arxiv.org/abs/2510.04748 https://

Social bias is prevalent in user reports of hate and abuse online
The prevalence of online hate and abuse is a pressing global concern. While tackling such societal harms is a priority for research across the social sciences, it is a difficult task, in part because of the magnitude of the problem. User engagement with reporting mechanisms (flagging) online is an increasingly important part of monitoring and addressing harmful content at scale. However, users may not flag content routinely enough, and when they do engage, they may be biased by group identity a…

An information metric for comparing and assessing informative interim decisions in sequential clinical trials
G. Caruso, W. F. Rosenberger, P. Mozgunov, N. Flournoy
https://arxiv.org/abs/2509.04904

An information metric for comparing and assessing informative interim decisions in sequential clinical trials
Group sequential designs enable interim analyses and potential early stopping for efficacy or futility. While these adaptations improve trial efficiency and ethical considerations, they also introduce bias into the adapted analyses. We demonstrate how failing to account for informative interim decisions in the analysis can substantially affect posterior estimates of the treatment effect, often resulting in overly optimistic credible intervals aligned with the stopping decision. Drawing on infor…

Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulation
Hongbin Lin, Juan Rojas, Kwok Wai Samuel Au
https://arxiv.org/abs/2508.11204 https://

Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot Manipulation
Sampling efficiency is critical for deploying visuomotor learning in real-world robotic manipulation. While task symmetry has emerged as a promising inductive bias to improve efficiency, most prior work is limited to isometric symmetries -- applying the same group transformation to all task objects across all timesteps. In this work, we explore non-isometric symmetries, applying multiple independent group transformations across spatial and temporal dimensions to relax these constraints. We intr…

Confirmation Bias as a Cognitive Resource in LLM-Supported Deliberation
Sander de Jong, Rune M{\o}berg Jacobsen, Niels van Berkel
https://arxiv.org/abs/2509.14824 https://

Confirmation Bias as a Cognitive Resource in LLM-Supported Deliberation
Large language models (LLMs) are increasingly used in group decision-making, but their influence risks fostering conformity and reducing epistemic vigilance. Drawing on the Argumentative Theory of Reasoning, we argue that confirmation bias, often seen as detrimental, can be harnessed as a resource when paired with critical evaluation. We propose a three-step process in which individuals first generate ideas independently, then use LLMs to refine and articulate them, and finally engage with LLMs…

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

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

Interactions Between Multiple Environmental Markets: Addressing Contamination Bias in Overlapping Policies
Tiantian Yang, Richard S. J. Tol
https://arxiv.org/abs/2509.26403 http…

Interactions Between Multiple Environmental Markets: Addressing Contamination Bias in Overlapping Policies
To address the dual environmental challenges of pollution and climate change, China has established multiple environmental markets, including pollution emissions trading, carbon emissions trading, energy-use rights trading, and green electricity trading. Previous empirical studies suffer from known biases arising from time-varying treatment and multiple treatments. To address these limitations, this study adopts a dynamic control group design and combines Difference-in-Difference (DiD) and Arti…

Analysing contrarian behaviour using nonlinear biased $q$-voter model
Amit Pradhan, Pratik Mullick, Parongama Sen
https://arxiv.org/abs/2509.01982 https://…

Analysing contrarian behaviour using nonlinear biased $q$-voter model
We investigate the role of contrarians in a recently proposed weighted-influence variant of the $q$-voter model. In this framework, non-unanimous influence groups affect the focal agent through weighted contributions governed by a bias parameter $p$. We extend this setting by introducing a fraction $α$ ($α> 0$) of contrarians, defined as agents who systematically oppose the prevailing influence irrespective of whether the group is unanimous or divided. Analytical mean-field calculations and M…

Cohort-Anchored Robust Inference for Event-Study with Staggered Adoption
Ziyi Liu
https://arxiv.org/abs/2509.01829 https://arxiv.org/pdf/2509.01829

Cohort-Anchored Robust Inference for Event-Study with Staggered Adoption
I propose a cohort-anchored framework for robust inference in event studies with staggered adoption. Robust inference based on aggregated event-study coefficients, as in Rambachan and Roth (2023), can be misleading because pre- and post-treatment coefficients are identified from different cohort compositions and the not-yet-treated control group changes over time. To address these issues, I work at the cohort-period level and introduce the \textit{block bias}-the parallel-trends violation for a…

Fairness for the People, by the People: Minority Collective Action
Omri Ben-Dov, Samira Samadi, Amartya Sanyal, Alexandru \c{T}ifrea
https://arxiv.org/abs/2508.15374 https://

Fairness for the People, by the People: Minority Collective Action
Machine learning models often preserve biases present in training data, leading to unfair treatment of certain minority groups. Despite an array of existing firm-side bias mitigation techniques, they typically incur utility costs and require organizational buy-in. Recognizing that many models rely on user-contributed data, end-users can induce fairness through the framework of Algorithmic Collective Action, where a coordinated minority group strategically relabels its own data to enhance fairne…