Quantifying and Mitigating Selection Bias in LLMs: A Transferable LoRA Fine-Tuning and Efficient Majority Voting Approach

• URL: http://arxiv.org/abs/2511.21709v1
• Date: Mon, 17 Nov 2025 21:31:37 GMT
• Title: Quantifying and Mitigating Selection Bias in LLMs: A Transferable LoRA Fine-Tuning and Efficient Majority Voting Approach
• Authors: Blessed Guda, Lawrence Francis, Gabrial Zencha Ashungafac, Carlee Joe-Wong, Moise Busogi,
• Abstract summary: Multiple Choice Question (MCQ) answering is a widely used method for evaluating the performance of Large Language Models (LLMs)<n>LLMs often exhibit selection bias in MCQ tasks, where their choices are influenced by factors like answer position or option symbols rather than the content.
• Score: 13.829059542429876
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multiple Choice Question (MCQ) answering is a widely used method for evaluating the performance of Large Language Models (LLMs). However, LLMs often exhibit selection bias in MCQ tasks, where their choices are influenced by factors like answer position or option symbols rather than the content. This bias undermines the reliability of MCQ as an evaluation framework. Most existing selection bias metrics require answer labels and measure divergences between prediction and answer distributions, but do not fully capture the consistency of a model's predictions across different orderings of answer choices. Existing selection bias mitigation strategies have notable limitations: majority voting, though effective, is computationally prohibitive; calibration-based methods require validation sets and often fail to generalize across datasets. To address these gaps, we propose three key contributions: (1) a new unsupervised label-free Permutation Bias Metric (PBM) that directly quantifies inconsistencies in model predictions across answer permutations, providing a more precise measure of selection bias, (2) an efficient majority voting approach called Batch Question-Context KV caching (BaQCKV), to significantly reduce computational costs while preserving bias mitigation effectiveness, and (3) an unsupervised Low-Rank Adaptation (LoRA-1) fine-tuning strategy based on our proposed metric and the BaQCKV that mitigates selection bias, providing a computationally efficient alternative that maintains model generalizability. Experiments across multiple MCQ benchmarks demonstrate that our approaches reduce bias, increasing consistency in accuracy while minimizing computational costs.

Related papers

• Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models [55.94503936470247]
  Large-scale AI evaluation increasingly relies on aggregating binary judgments from $K$ annotators, including judges.<n>Most classical methods assume annotators are conditionally independent given the true label $Yin0,1$, an assumption often violated by LLM judges.<n>We study label aggregation through a hierarchy of dependence-aware models based on Ising graphical models and latent factors.
  arXiv  Detail & Related papers  (2026-01-29T21:26:50Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)
• Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models [2.393011821499345]
  We investigate the presence and nature of selection bias in Large Vision-Language Models (LVLMs)<n>We propose an inference-time logit-level debiasing method that estimates an ensemble bias vector from general and contextual prompts.<n>Our method mitigates bias without retraining and is compatible with frozen LVLMs.
  arXiv  Detail & Related papers  (2025-09-20T20:45:47Z)
• SCOPE: Stochastic and Counterbiased Option Placement for Evaluating Large Language Models [0.27309692684728604]
  Large Language Models (LLMs) can achieve inflated scores on multiple-choice tasks by exploiting inherent biases in option positions or labels.<n>This study introduces SCOPE, an evaluation framework designed to measure and mitigate such selection bias in a dataset-independent manner.
  arXiv  Detail & Related papers  (2025-07-24T08:28:17Z)
• A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding [61.86327960322782]
  We propose a principled framework for randomized decision-making based on interval estimates of the quality of each item.<n>We introduce MERIT, an optimization-based method that maximizes the worst-case expected number of top candidates selected.<n>We prove that MERIT satisfies desirable axiomatic properties not guaranteed by existing approaches.
  arXiv  Detail & Related papers  (2025-06-23T19:59:30Z)
• Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering [78.89231943329885]
  Multiple-Choice Question Answering (MCQA) is widely used to evaluate Large Language Models (LLMs)<n>We show that multiple factors can significantly impact the reported performance of LLMs.<n>We analyze whether existing answer extraction methods are aligned with human judgment.
  arXiv  Detail & Related papers  (2025-03-19T08:45:03Z)
• CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges [21.580762639442913]
  We introduce CalibraEval, a novel label-free method for mitigating selection bias during inference. CalibraEval reformulates debiasing as an optimization task aimed at adjusting observed prediction distributions to align with unbiased prediction distributions. We show that CalibraEval effectively mitigates selection bias and improves performance compared to existing debiasing methods.
  arXiv  Detail & Related papers  (2024-10-20T13:47:39Z)
• Mitigating Selection Bias with Node Pruning and Auxiliary Options [11.835002896308545]
  Large language models (LLMs) often exhibit systematic preferences for certain answer choices when responding to multiple-choice questions.<n>This bias reduces the accuracy and reliability of LLM outputs, limiting their usefulness in decision-critical applications.<n>We introduce two methods: Bias Node Pruning (BNP), which prunes parameters that contribute to selection bias, and Auxiliary Option Injection (AOI), which introduces an answer choice to reduce bias in both white-box and black-box settings.
  arXiv  Detail & Related papers  (2024-09-27T15:53:54Z)
• Efficient Weighting Schemes for Auditing Instant-Runoff Voting Elections [57.67176250198289]
  AWAIRE involves adaptively weighted averages of test statistics, essentially "learning" an effective set of hypotheses to test. We explore schemes and settings more extensively, to identify and recommend efficient choices for practice. A limitation of the current AWAIRE implementation is its restriction to a small number of candidates.
  arXiv  Detail & Related papers  (2024-02-18T10:13:01Z)
• Large Language Models Are Not Robust Multiple Choice Selectors [117.72712117510953]
  Multiple choice questions (MCQs) serve as a common yet important task format in the evaluation of large language models (LLMs) This work shows that modern LLMs are vulnerable to option position changes due to their inherent "selection bias" We propose a label-free, inference-time debiasing method, called PriDe, which separates the model's prior bias for option IDs from the overall prediction distribution.
  arXiv  Detail & Related papers  (2023-09-07T17:44:56Z)

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.