Lune

ACL Findings2024

Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models

Sheng-Lun Wei, Cheng-Kuang Wu, Hen-Hsen Huang, Hsin-Hsi Chen

Abstract

In this paper, we investigate the phenomena of "selection biases" in Large Language Models (LLMs), focusing on problems where models are tasked with choosing the optimal option from an ordered sequence. We delve into biases related to option order and token usage, which significantly impact LLMs' decision-making processes. We also quantify the impact of these biases through an extensive empirical analysis across multiple models and tasks. Furthermore, we propose mitigation strategies to enhance model performance. Our key contributions are threefold: 1) Precisely quantifying the influence of option order and token on LLMs, 2) Developing strategies to mitigate the impact of token and order sensitivity to enhance robustness, and 3) Offering a detailed analysis of sensitivity across models and tasks, which informs the creation of more stable and reliable LLM applications for selection problems.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

17 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • OTTER: Effortless Label Distribution Adaptation of Zero-shot Models cites Measuring Massive Multitask Language Understanding
  • OTTER: Effortless Label Distribution Adaptation of Zero-shot Models cites Large Language Models Are Not Robust Multiple Choice Selectors
  • A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations cites Measuring Massive Multitask Language Understanding
  • A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations cites Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization
  • A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations cites WinoGrande: An Adversarial Winograd Schema Challenge at Scale
  • Large Language Models Are Not Robust Multiple Choice Selectors cites Measuring Massive Multitask Language Understanding
  • Large Language Models Are Not Robust Multiple Choice Selectors cites Calibrate Before Use: Improving Few-shot Performance of Language Models
  • Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models? cites Measuring Massive Multitask Language Understanding
  • Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models? cites Large Language Models Are Not Robust Multiple Choice Selectors
  • BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models cites Large Language Models Are Not Robust Multiple Choice Selectors
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers17

  1. Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?Hyeong Kyu Choi, Xiaojin Zhu, Sharon LiNeurIPS 2025 · 93 citations
  2. A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and RecommendationsMd. Tahmid Rahman Laskar, Sawsan Alqahtani, M. Saiful Bari, Mizanur Rahman et al.EMNLP 2024 · 47 citations
  3. StreamingThinker: Large Language Models Can Think While ReadingJunlong Tong, Yingqi Fan, Anhao Zhao, Yunpu Ma et al.ICLR 2026 · 17 citations
  4. BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language ModelsThierry Blankenstein, Jialin Yu, Zixuan Li, Vassilis Plachouras et al.ICLR 2026 · 8 citations
  5. OTTER: Effortless Label Distribution Adaptation of Zero-shot ModelsChangho Shin, Jitian Zhao, Sonia Cromp, Harit Vishwakarma et al.NeurIPS 2024 · 4 citations

Builds on9

  1. Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
  2. WinoGrande: An Adversarial Winograd Schema Challenge at ScaleKeisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, Yejin ChoiAAAI 2020 · 3,037 citations
  3. Calibrate Before Use: Improving Few-shot Performance of Language ModelsZihao Zhao, Eric Wallace, Shi Feng, Dan Klein et al.ICML 2021 · 1,843 citations
  4. Large Language Models Are Not Robust Multiple Choice SelectorsChujie Zheng, Hao Zhou, Fandong Meng, Jie Zhou et al.ICLR 2024 · 424 citations
  5. Large Language Models are Not Yet Human-Level Evaluators for Abstractive SummarizationChenhui Shen, Liying Cheng, Xuan-Phi Nguyen, Yang You et al.EMNLP Findings 2023 · 52 citations

Related papers

  1. Set-LLM: A Permutation-Invariant LLMBeni Egressy, Jan StühmerNeurIPS 2025 · 13 citations
  2. Characterizing Positional Bias in Large Language Models: A Multi-Model Evaluation of Prompt Order EffectsPatrick Schilcher, Dominik Karasin, Michael Schöpf, Haisam Saleh et al.EMNLP Findings 2025 · 1 citation
  3. Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice QuestionsRuizhe Li, Yanjun GaoACL Findings 2025 · 4 citations
  4. Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream TasksMiaomiao Li, Hao Chen, Yang Wang, Tingyuan Zhu et al.ACL 2026 · 16 citations
  5. Order-Independence Without Fine TuningReid McIlroy-Young, Katrina Brown, Conlan Olson, Linjun Zhang et al.NeurIPS 2024 · 10 citations
Dusk over the sea between two cliffs drawn in fine vertical lines