To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias

• URL: http://arxiv.org/abs/2606.24596v1
• Date: Tue, 23 Jun 2026 13:53:50 GMT
• Title: To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias
• Abstract summary: We introduce a unified framework that standardizes heterogeneous benchmarks to contrast isolated demographic assessments with forced-choice comparative settings.<n>We show that comparative settings act as aggressive catalysts for latent discrimination, a shift primarily driven by underspecified contexts.<n>Finally, we demonstrate that this comparative prejudice is a generalized phenomenon that scales positively with model size.
• Score: 61.40435736418359
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As Large Language Models are increasingly deployed in critical applications, robustly evaluating their social biases is paramount. However, the current literature suffers from widespread methodological fragmentation, which yields contradictory conclusions. This stems largely from ignoring the structural framing of benchmark-level evaluations. To resolve this, we introduce a unified and controllable framework that standardizes heterogeneous benchmarks to systematically contrast isolated demographic assessments with forced-choice comparative settings. Crucially, this allows us to disentangle the confounding effects of Chain-of-Thought reasoning, neutral fallback options, and other structural artifacts in social bias evaluations. Our evaluation across multiple model families reveals a massive, systematic paradigm gap: while isolated assessments limit prejudice activation, comparative settings act as aggressive catalysts for latent discrimination, a shift primarily driven by underspecified contexts. Alarmingly, CoT reasoning exacerbates social biases under comparative settings, and this systemic bias persists as a deterministic prejudice even when models are provided neutral fallback options or claim to answer randomly. Finally, we demonstrate that this comparative prejudice is a generalized phenomenon that scales positively with model size. Ultimately, we offer a crucial methodological guideline: while researchers must leverage comparative settings to robustly audit hidden biases, practitioners cannot safely rely on comparative deployments in ambiguous real-world tasks.

Related papers

• The Validity of Coreference-based Evaluations of Natural Language Understanding [3.505146496638911]
  I analyze standard coreference evaluations and show that their design often leads to non-generalizable conclusions.<n>I propose and implement a novel evaluation focused on testing systems' ability to infer the relative plausibility of events.
  arXiv  Detail & Related papers  (2026-02-18T05:49:28Z)
• Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness [49.35494016290887]
  We show that equal performance across subgroups is an unreliable measure of fairness when data are representative of relevant populations but reflective of real-world disparities.<n>Our framework suggests complementing disaggregated evaluations with explicit causal assumptions and analysis to control for confounding and distribution shift.
  arXiv  Detail & Related papers  (2025-06-04T17:40:31Z)
• Estimating Commonsense Plausibility through Semantic Shifts [66.06254418551737]
  We propose ComPaSS, a novel discriminative framework that quantifies commonsense plausibility by measuring semantic shifts.<n> Evaluations on two types of fine-grained commonsense plausibility estimation tasks show that ComPaSS consistently outperforms baselines.
  arXiv  Detail & Related papers  (2025-02-19T06:31:06Z)
• The simulation of judgment in LLMs [32.57692724251287]
  Large Language Models (LLMs) are increasingly embedded in evaluative processes, from information filtering to assessing and addressing knowledge gaps through explanation and credibility judgments.<n>This raises the need to examine how such evaluations are built, what assumptions they rely on, and how their strategies diverge from those of humans.<n>We benchmark six LLMs against expert ratings--NewsGuard and Media Bias/Fact Check--and against human judgments collected through a controlled experiment.
  arXiv  Detail & Related papers  (2025-02-06T18:52:10Z)
• Diverging Preferences: When do Annotators Disagree and do Models Know? [92.24651142187989]
  We develop a taxonomy of disagreement sources spanning 10 categories across four high-level classes. We find that the majority of disagreements are in opposition with standard reward modeling approaches. We develop methods for identifying diverging preferences to mitigate their influence on evaluation and training.
  arXiv  Detail & Related papers  (2024-10-18T17:32:22Z)
• Covert Bias: The Severity of Social Views' Unalignment in Language Models Towards Implicit and Explicit Opinion [0.40964539027092917]
  We evaluate the severity of bias toward a view by using a biased model in edge cases of excessive bias scenarios. Our findings reveal a discrepancy in LLM performance in identifying implicit and explicit opinions, with a general tendency of bias toward explicit opinions of opposing stances. The direct, incautious responses of the unaligned models suggest a need for further refinement of decisiveness.
  arXiv  Detail & Related papers  (2024-08-15T15:23:00Z)
• FairPair: A Robust Evaluation of Biases in Language Models through Paired Perturbations [33.24762796282484]
  We present FairPair, an evaluation framework for assessing differential treatment that occurs during ordinary usage. Unlike prior work, our method factors in the inherent variability that comes from the generation process itself by measuring the sampling variability.
  arXiv  Detail & Related papers  (2024-04-09T21:09:22Z)
• Social Bias Probing: Fairness Benchmarking for Language Models [38.180696489079985]
  This paper proposes a novel framework for probing language models for social biases by assessing disparate treatment. We curate SoFa, a large-scale benchmark designed to address the limitations of existing fairness collections. We show that biases within language models are more nuanced than acknowledged, indicating a broader scope of encoded biases than previously recognized.
  arXiv  Detail & Related papers  (2023-11-15T16:35:59Z)
• Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise [62.997667081978825]
  In high-risk environments, deep learning models need to be able to judge their uncertainty and reject inputs when there is a significant chance of misclassification. We conduct a rigorous evaluation of the most commonly used uncertainty and robustness methods for the classification of Whole Slide Images. We observe that ensembles of methods generally lead to better uncertainty estimates as well as an increased robustness towards domain shifts and label noise.
  arXiv  Detail & Related papers  (2023-01-03T11:34:36Z)
• Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks [95.29345070102045]
  In this paper, we focus our investigation on social bias detection of dialog safety problems. We first propose a novel Dial-Bias Frame for analyzing the social bias in conversations pragmatically. We introduce CDail-Bias dataset that is the first well-annotated Chinese social bias dialog dataset.
  arXiv  Detail & Related papers  (2022-02-16T11:59:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.