Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions
Pouya Pezeshkpour Megagon Labs、Estevam Hruschka Megagon Labs
Abstract
Large Language Models (LLMs) have demonstrated remarkable capabilities in various NLP tasks. However, previous works have shown these models are sensitive towards prompt wording, and few-shot demonstrations and their order, posing challenges to fair assessment of these models. As these models become more powerful, it becomes imperative to understand and address these limitations. In this paper, we focus on LLMs robustness on the task of multiple-choice questions—commonly adopted task to study reasoning and fact-retrieving capability of LLMs. Investigating the sensitivity of LLMs towards the order of options in multiple-choice questions, we demonstrate a considerable performance gap of approximately $13\%$ to $75\%$ in LLMs on different benchmarks, when answer options are reordered, even when using demonstrations in a few-shot setting. Through a detailed analysis, we conjecture that this sensitivity arises when LLMs are uncertain about the prediction between the top-2/3 choices, and specific options placements may favor certain prediction between those top choices depending on the question caused by positional bias. We also identify patterns in top-2 choices that amplify or mitigate
中文速览
大语言模型（LLM）在多选题（multiple-choice questions）任务上存在一个被忽视的"软肋"：只要把选项的排列顺序打乱，模型的准确率就可能大幅波动，差距最高达到75%，即便在少样本提示下也无法根本消除这一现象。研究者通过系统实验发现，这种敏感性源于两股力量的叠加——模型在几个高概率候选答案之间拿不准主意，同时又存在位置偏好（positional bias），倾向于选择出现在特定位置的选项。进一步分析揭示了具体规律：把最有可能的两个选项分别放在第一和最后位置会最大程度放大偏差，而把它们放在相邻位置则能有效缓解偏差。基于这些发现，研究者提出两种校准方法，在多个模型和基准数据集上将准确率提升了最多8个百分点，为更公平地评估和使用大语言模型提供了重要参考。
原文 arXiv:2308.11483;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2308.11483v1