Elamur Research⌕
☰
home / papers / 2024 / A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners

A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners

Paper · 2024 · Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao et al.

Summary

The paper asks whether large language models actually reason logically or mostly react to familiar surface tokens that appear in well-known problem statements. The authors call this "token bias." It occurs when systematically changing logic-irrelevant tokens, such as names, numbers or hint words, shifts model answers in a predictable direction. To study it, they build a framework with three parts:

  • Synthetic data: controlled datasets generated from curated entity lists and templates, so the exact items cannot have appeared in training data.
  • Token perturbation: each item is paired with a perturbed version that keeps the same underlying logic.
  • Statistical testing: paired outcomes are compared, with each null hypothesis assuming the model is a genuine reasoner.

The test tasks are conjunction fallacy problems (e.g., Linda-style questions), syllogisms and the graph-theory "twenty-five horses" puzzle. Experiments cover commercial and open-source LLMs, including GPT-4 and Claude. They show, with statistical backing, that good results on classic problems come largely from pattern recognition rather than consistent reasoning. This casts doubt on how well these models generalize and on whether chain-of-thought or in-context learning truly elicit reasoning.

Key points

  • Example of token bias: swapping "Linda" for "Bob" in a one-shot conjunction-fallacy exemplar confused GPT-4. Renaming the animals or changing the numbers in the "twenty-five horses" puzzle significantly lowered accuracy for GPT-4 and Claude.
  • Statistical method: results are arranged in a 2×2 contingency table of original vs. perturbed correctness. The tests are an exact binomial test or the McNemar statistic for marginal homogeneity. The Benjamini-Hochberg procedure controls the false discovery rate when testing groups of models.
  • Data generation: some conjunction-fallacy items are built from commonsense stories by Mostafazadeh et al. (2016), with an LLM completing a "because" clause.
  • Hint dependence: in tests with and without hint tokens (n=200), models still relied heavily on hints, so all null hypotheses were rejected.
  • Scope and availability: the framework only handles multiple-choice or yes/no answers, and identifying the biased tokens requires manual work. Code and data are released at github.com/bowen-upenn/llm_token_bias.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of PennsylvaniaPhiladelphia · United States221 works · 63,234 citations🔬Argonne National LaboratoryLemont · United States2 works · 68 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao, Xiaomeng Wang, Tanwi Mallick, Weijie J Su, Camillo Jose Taylor and Dan Roth. 2024. A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2024.emnlp-main.272

@inproceedings{jiang2024peek,
  title = {{A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners}},
  author = {Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao, Xiaomeng Wang, Tanwi Mallick, Weijie J Su, Camillo Jose Taylor and Dan Roth},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
  year = {2024},
  doi = {10.18653/v1/2024.emnlp-main.272},
  url = {https://doi.org/10.18653/v1/2024.emnlp-main.272}
}

References

90 references, 32 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Disease symptom description dataset. Accessed: 2024-06-1. find
  2. Esl kids vocabulary. Accessed: 2024-06-15. find
  3. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  4. Alan Agresti. 2012. Categorical data analysis, volume 792. John Wiley & Sons. find
  5. Janice Ahn, Rishu Verma, Renze Lou, Di Liu, Rui Zhang, and Wenpeng Yin. 2024. Large language models for mathematical reasoning: Progresses and challenges. arXiv preprint arXiv:2402.00157.
  6. Anthropic. 2024. Models overview. Software available from Anthropic. Accessed: 2024-05-20. find
  7. Yoav Benjamini and Yosef Hochberg. 1995. Controlling the false discovery rate: A practical and powerful approach to multiple testing. Journal of the Royal Statistical Society. Series B (Methodological), 57(1):289–300. find
  8. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, et al. 2024. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI Conference on Artifici… find
  9. Marcel Binz and Eric Schulz. 2023. Using cognitive psychology to understand gpt-3. Proceedings of the National Academy of Sciences, 120(6):e2218523120. find
  10. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  11. Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. 2023. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712.
  12. Chengkun Cai, Xu Zhao, Yucheng Du, Haoliang Liu, and Lei Li. 2024. T2 of thoughts: Temperature tree elicits reasoning in large language models. arXiv preprint arXiv:2405.14075. — [arXiv:2405.14075](https://arxiv.org/abs/2405.14075) find
  13. Xinyun Chen, Ryan A Chi, Xuezhi Wang, and Denny Zhou. 2024. Premise order matters in reasoning with large language models. arXiv preprint arXiv:2402.08939. find
  14. Ishita Dasgupta, Andrew K Lampinen, Stephanie CY Chan, Antonia Creswell, Dharshan Kumaran, James L McClelland, and Felix Hill. 2022. Language models show human-like content effects on reasoning. arXiv preprint arXiv:2207.07051. find
  15. Jessica Echterhoff, Yao Liu, Abeer Alessa, Julian McAuley, and Zexue He. 2024. Cognitive bias in high-stakes decision-making with llms. arXiv preprint arXiv:2403.00811. — [arXiv:2403.00811](https://arxiv.org/abs/2403.00811) find
  16. Yao Fu, Litu Ou, Mingyu Chen, Yuhao Wan, Hao Peng, and Tushar Khot. 2023. Chain-of-thought hub: A continuous effort to measure large language models’ reasoning performance. arXiv preprint arXiv:2305.17306.
  17. Matt Gardner, Yoav Artzi, Victoria Basmov, Jonathan Berant, Ben Bogin, Sihao Chen, Pradeep Dasigi, Dheeru Dua, Yanai Elazar, Ananth Gottumukkala, et al. 2020. Evaluating models’ local decision boundaries via contrast sets. In Findings of the Association for Computational Linguistics: EMNLP 2020, pag…
  18. Panagiotis Giadikiaroglou, Maria Lymperaiou, Giorgos Filandrianos, and Giorgos Stamou. 2024. Puzzle solving using reasoning of large language models: A survey. arXiv preprint arXiv:2402.11291.
  19. Tian Gou, Boyao Zhang, Zhenglie Sun, Jing Wang, Yangang Wang, and Jue Wang. 2023. Rationality of thought improves reasoning in large language models. find
  20. Thilo Hagendorff, Sarah Fabi, and Michal Kosinski. 2023. Human-like intuitive behavior and reasoning biases emerged in large language models but disappeared in chatgpt. Nature Computational Science, 3(10):833–838. find
  21. Shibo Hao, Yi Gu, Haodi Ma, Joshua Jiahua Hong, Zhen Wang, Daisy Zhe Wang, and Zhiting Hu. 2023. Reasoning with language model is planning with world model. arXiv preprint arXiv:2305.14992. find
  22. Reid Hastie and Robyn M Dawes. 2009. Rational choice in an uncertain world: The psychology of judgment and decision making. Sage Publications. find
  23. Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar, Dan Roth, and Camillo J. Taylor. 2024b. Multi-agent vqa: Exploring multi-agent foundation models in zero-shot visual question answering. Preprint, arXiv:2403.14783. find
  24. Mingyu Jin, Qinkai Yu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, Mengnan Du, et al. 2024. The impact of reasoning step length on large language models. arXiv preprint arXiv:2401.04925.
  25. Zhijing Jin, Abhinav Lalwani, Tejas Vaidhya, Xiaoyu Shen, Yiwen Ding, Zhiheng Lyu, Mrinmaya Sachan, Rada Mihalcea, and Bernhard Schoelkopf. 2022. Logical fallacy detection. arXiv preprint arXiv:2202.13758.
  26. Daniel Kahneman. 2011. macmillan. find
  27. Michal Kosinski. 2023. Evaluating large language models in theory of mind tasks. arXiv e-prints, pages arXiv–2302.
  28. Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, John D Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, et al. 2024. Training language models to self-correct via reinforcement learning. arXiv preprint arXiv:2409.12917.
  29. Ruixin Hong, Hongming Zhang, Xinyu Pang, Dong Yu, and Changshui Zhang. 2023. A closer look at the self-verification abilities of large language models in logical reasoning. arXiv preprint arXiv:2311.07954. find
  30. Tamera Lanham, Anna Chen, Ansh Radhakrishnan, Benoit Steiner, Carson Denison, Danny Hernandez, Dustin Li, Esin Durmus, Evan Hubinger, Jackson Kernion, et al. 2023. Measuring faithfulness in chain-of-thought reasoning. arXiv preprint arXiv:2307.13702.
  31. Jie Huang and Kevin Chen-Chuan Chang. 2022. Towards reasoning in large language models: A survey. arXiv preprint arXiv:2212.10403.
  32. Erich Leo Lehmann, Joseph P Romano, and George Casella. 1986. Testing statistical hypotheses, volume 3. Springer. find
  33. Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. 2023. Large language models cannot self-correct reasoning yet. arXiv preprint arXiv:2310.01798.
  34. Bangzheng Li, Ben Zhou, Fei Wang, Xingyu Fu, Dan Roth, and Muhao Chen. 2023. Deceiving semantic shortcuts on reasoning chains: How far can models go without hallucination? arXiv preprint arXiv:2311.09702. — [arXiv:2311.09702](https://arxiv.org/abs/2311.09702) find
  35. Mohsen Jamali, Ziv M Williams, and Jing Cai. 2023. Unveiling theory of mind in large language models: A parallel to single neurons in the human brain. arXiv preprint arXiv:2309.01660. — [arXiv:2309.01660](https://arxiv.org/abs/2309.01660) find
  36. Xun Liang, Shichao Song, Zifan Zheng, Hanyu Wang, Qingchen Yu, Xunkai Li, Rong-Hua Li, Feiyu Xiong, and Zhiyu Li. 2024. Internal consistency and self-feedback in large language models: A survey. arXiv preprint arXiv:2407.14507. — [arXiv:2407.14507](https://arxiv.org/abs/2407.14507)
  37. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. find
  38. Ruixi Lin and Hwee Tou Ng. 2023. Mind the biases: Quantifying cognitive biases in language model prompting. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5269–5281. find
  39. Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang, Weijie J Su, Camillo J Taylor, and Tanwi Mallick. 2024a. Multi-modal and multi-agent systems meet rationality: A survey. arXiv preprint arXiv:2406.00252. — [arXiv:2406.00252](https://arxiv.org/abs/2406.00252) find
  40. Qing Lyu, Shreya Havaldar, Adam Stein, Li Zhang, Delip Rao, Eric Wong, Marianna Apidianaki, and Chris Callison-Burch. 2023. Faithful chain-of-thought reasoning. arXiv preprint arXiv:2301.13379.
  41. Xinxi Lyu, Sewon Min, Iz Beltagy, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2022. Z-icl: zero-shot in-context learning with pseudo-demonstrations. arXiv preprint arXiv:2212.09865. find
  42. Yingwei Ma, Yue Liu, Yue Yu, Yuanliang Zhang, Yu Jiang, Changjian Wang, and Shanshan Li. 2023. At which training stage does code data help llms reasoning? arXiv preprint arXiv:2309.16298. — [arXiv:2309.16298](https://arxiv.org/abs/2309.16298) find
  43. Olivia Macmillan-Scott and Mirco Musolesi. 2024. (ir) rationality and cognitive biases in large language models. arXiv preprint arXiv:2402.09193. — [arXiv:2402.09193](https://arxiv.org/abs/2402.09193) find
  44. Quinn McNemar. 1947. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika, 12(2):153–157. find
  45. William Merrill and Ashish Sabharwal. 2023. The expresssive power of transformers with chain of thought. arXiv preprint arXiv:2310.07923. find
  46. William Merrill and Ashish Sabharwal. 2024. A logic for expressing log-precision transformers. Advances in Neural Information Processing Systems, 36. find
  47. Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2022. Rethinking the role of demonstrations: What makes in-context learning work? arXiv preprint arXiv:2202.12837.
  48. Melanie Mitchell and David C Krakauer. 2023. The debate over understanding in ai’s large language models. Proceedings of the National Academy of Sciences, 120(13):e2215907120. find
  49. Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, and James Allen. 2016. A corpus and evaluation framework for deeper understanding of commonsense stories. arXiv preprint arXiv:1604.01696. find
  50. Frederick Mosteller. 1952. Some statistical problems in measuring the subjective response to drugs. Biometrics, 8(3):220–226. find
  51. Anirban Mukherjee and Hannah Hanwen Chang. 2024. Heuristic reasoning in ai: Instrumental use and mimetic absorption. arXiv preprint arXiv:2403.09404. — [arXiv:2403.09404](https://arxiv.org/abs/2403.09404) find
  52. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems, 35:27730–27744.
  53. Pew Research Center. 2011. Top 25. Accessed: 2024-06-15. find
  54. Archiki Prasad, Alexander Koller, Mareike Hartmann, Peter Clark, Ashish Sabharwal, Mohit Bansal, and Tushar Khot. 2023. Adapt: As-needed decomposition and planning with language models. arXiv preprint arXiv:2311.05772.
  55. Pranav Putta, Edmund Mills, Naman Garg, Sumeet Motwani, Chelsea Finn, Divyansh Garg, and Rafael Rafailov. 2024. Agent q: Advanced reasoning and learning for autonomous ai agents. arXiv preprint arXiv:2408.07199. find
  56. Shuofei Qiao, Yixin Ou, Ningyu Zhang, Xiang Chen, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, and Huajun Chen. 2022. Reasoning with language model prompting: A survey. arXiv preprint arXiv:2212.09597.
  57. Mathieu Ravaut, Bosheng Ding, Fangkai Jiao, Hailin Chen, Xingxuan Li, Ruochen Zhao, Chengwei Qin, Caiming Xiong, and Shafiq Joty. 2024. How much are llms contaminated? a comprehensive survey and the llmsanitize library. arXiv preprint arXiv:2404.00699. find
  58. Jennifer Rosenberg. 2021. Times man of the year list. Accessed: 05-05-2024. find
  59. Abigail See, Peter J Liu, and Christopher D Manning. 2017. Get to the point: Summarization with pointer-generator networks. arXiv preprint arXiv:1704.04368. find
  60. Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed H Chi, Nathanael Schärli, and Denny Zhou. 2023. Large language models can be easily distracted by irrelevant context. In International Conference on Machine Learning, pages 31210–31227. PMLR.
  61. Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez, Dongwei Jiang, Manya Wadhwa, Prasann Singhal, Xinyu Zhao, Xi Ye, Kyle Mahowald, and Greg Durrett. 2024. To cot or not to cot? chain-of-thought helps mainly on math and symbolic reasoning. arXiv preprint arXiv:2409.12183.
  62. Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, et al. 2022a. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615.
  63. Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, et al. 2022b. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615.
  64. Gaurav Suri, Lily R Slater, Ali Ziaee, and Morgan Nguyen. 2024. Do large language models show decision heuristics similar to humans? a case study using gpt-3.5. Journal of Experimental Psychology: General. find
  65. Alaina N Talboy and Elizabeth Fuller. 2023. Challenging the appearance of machine intelligence: Cognitive bias in llms. arXiv preprint arXiv:2304.01358. — [arXiv:2304.01358](https://arxiv.org/abs/2304.01358) find
  66. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. 2018. Commonsenseqa: A question answering challenge targeting commonsense knowledge. arXiv preprint arXiv:1811.00937.
  67. Alex Tamkin, Amanda Askell, Liane Lovitt, Esin Durmus, Nicholas Joseph, Shauna Kravec, Karina Nguyen, Jared Kaplan, and Deep Ganguli. 2023. Evaluating and mitigating discrimination in language model decisions. arXiv preprint arXiv:2312.03689. find
  68. Wikipedia contributors. 2024a. Forbes celebrity 100. Accessed: 2024-05-20. find
  69. Wikipedia contributors. 2024b. News media in the united states. Accessed: 2024-06-1. find
  70. Yijia Xiao, Edward Sun, Tianyu Liu, and Wei Wang. 2024. Logicvista: Multimodal llm logical reasoning benchmark in visual contexts. arXiv preprint arXiv:2407.04973. — [arXiv:2407.04973](https://arxiv.org/abs/2407.04973) find
  71. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  72. Yangxinyu Xie, Tanwi Mallick, Joshua David Berg-erson, John K Hutchison, Duane R Verner, Jordan Branham, M Ross Alexander, Robert B Ross, Yan Feng, Leslie-Anne Levy, et al. 2024. Wildfiregpt: Tailored large language model for wildfire analysis. arXiv preprint arXiv:2402.07877. — [arXiv:2402.07877](https://arxiv.org/abs/2402.07877) find
  73. Miles Turpin, Julian Michael, Ethan Perez, and Samuel Bowman. 2024. Language models don’t always say what they think: unfaithful explanations in chain-of-thought prompting. Advances in Neural Information Processing Systems, 36.
  74. Han Xu, Jingyang Ye, Yutong Li, and Haipeng Chen. 2024. Can speculative sampling accelerate react without compromising reasoning quality? In The Second Tiny Papers Track at ICLR 2024. find
  75. Amos Tversky and Daniel Kahneman. 1981. The framing of decisions and the psychology of choice. science, 211(4481):453–458. find
  76. Amos Tversky and Daniel Kahneman. 1983. Extensional versus intuitive reasoning: The conjunction fallacy in probability judgment. Psychological review, 90(4):293. find
  77. Amos Tversky and Daniel Kahneman. 1988. Rational choice and the framing of decisions. Decision making: Descriptive, normative, and prescriptive interactions, pages 167–192. find
  78. Tomer Ullman. 2023. Large language models fail on trivial alterations to theory-of-mind tasks. arXiv preprint arXiv:2302.08399. find
  79. USDL. 2024. Occupational employment and wage statistics. Accessed: 05-05-2024. find
  80. Boshi Wang, Sewon Min, Xiang Deng, Jiaming Shen, You Wu, Luke Zettlemoyer, and Huan Sun. 2022. Towards understanding chain-of-thought prompting: An empirical study of what matters. arXiv preprint arXiv:2212.10001.
  81. Sohee Yang, Elena Gribovskaya, Nora Kassner, Mor Geva, and Sebastian Riedel. 2024. Do large language models latently perform multi-hop reasoning? arXiv preprint arXiv:2402.16837. find
  82. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600.
  83. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2024. Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, 36. find
  84. Zifan Zheng, Yezhaohui Wang, Yuxin Huang, Shichao Song, Bo Tang, Feiyu Xiong, and Zhiyu Li. 2024. Attention heads of large language models: A survey. arXiv preprint arXiv:2409.03752. — [arXiv:2409.03752](https://arxiv.org/abs/2409.03752)
  85. Ben Zhou, Kyle Richardson, Qiang Ning, Tushar Khot, Ashish Sabharwal, and Dan Roth. 2020. Temporal reasoning on implicit events from distant supervision. arXiv preprint arXiv:2010.12753. find
  86. Pengda Wang, Zilin Xiao, Hanjie Chen, and Frederick L Oswald. 2024. Will the real linda please stand up... to large language models? examining the representativeness heuristic in llms. arXiv preprint arXiv:2404.01461. — [arXiv:2404.01461](https://arxiv.org/abs/2404.01461) find
  87. Ben Zhou, Kyle Richardson, Xiaodong Yu, and Dan Roth. 2022. Learning to decompose: Hypothetical question decomposition based on comparable texts. arXiv preprint arXiv:2210.16865. find
  88. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. 2022a. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682.
  89. Kun Zhou, Yutao Zhu, Zhipeng Chen, Wentong Chen, Wayne Xin Zhao, Xu Chen, Yankai Lin, Ji-Rong Wen, and Jiawei Han. 2023. Don’t make your llm an evaluation benchmark cheater. arXiv preprint arXiv:2311.01964. find
  90. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022b. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/jiang-2024-peek-into-token-bias-large/