Elamur Research⌕
☰
home / papers / 2026 / Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Paper · 2026 · Haoming Xu, Ningyuan Zhao, Yunzhi Yao et al.

Summary

LLMs can answer a fact consistently and still drop it once the prompt contains misleading peer answers or documents. Point-wise measures such as self-consistency therefore overstate how firmly a model holds a belief. The authors treat belief robustness as a structural property and propose Neighbor-Consistency Belief (NCB). This score is motivated by a simplified Bayesian argument. It multiplies the model's empirical correctness on a target question by the geometric mean of its correctness on related "neighbor" questions: entity prerequisites, logical implications and thematic associations.

To test NCB, they build a Neighbor-Enriched Dataset of 2,000 time-invariant facts. They also design cognitive stress tests that mimic social pressure from peer answers and authority bias from sources of varying credibility. Across four LLMs, high-NCB facts withstand interference noticeably better than low-NCB ones. The authors further introduce Structure-Aware Training (SAT), which targets context-invariant belief when the model learns new knowledge. SAT cuts long-tail brittleness by roughly 30%. The findings matter for RAG and multi-agent settings, where context can easily mislead models.

Key points

  • Pilot study: Qwen3-30B-A3B-Instruct answered 995 questions correctly in all 30 samples (SC = 1.0). Under contextual interference, its accuracy on them fell from 100% to 33.8%.
  • Dataset: Seed facts come from SimpleQA, HotpotQA and SciQ. There are 500 facts in each of four domains: STEM, Arts & Culture, Social Sciences and Sports. Neighbor facts were generated by DeepSeek-V3.2, then screened and verified by humans.
  • Stress protocols: One setting varies the number of agreeing or conflicting peer agents (social pressure). The other varies source credibility (authority bias). Each setting includes conflict and misleading scenarios.
  • SAT results on Qwen-2.5-32B-Instruct:
    • Base accuracy reached 93.0%.
    • Average stress-test accuracy reached 60.6%, compared with 6.4% for vanilla, 30.9% for answer augmentation and 33.4% for knowledge augmentation.
    • Generic skills stayed largely intact: MMLU 80.1, GSM8k 91.0.
  • Limitations: The work covers only three relation types and static facts. NCB has not been validated against human judgments, and building neighborhoods adds computational overhead. Code is available at github.com/zjunlp/belief.

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 EdinburghEdinburgh · United Kingdom381 works · 80,747 citations🎓Zhejiang UniversityHangzhou · China224 works · 13,587 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,894 works

Cite

Cite as Haoming Xu, Ningyuan Zhao, Yunzhi Yao, Weihong Xu, Hongru Wang, Xinle Deng, Shumin Deng, Jeff Z. Pan, Huajun Chen and Ningyu Zhang. 2026. Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.203

@inproceedings{xu2026illusions,
  title = {{Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency}},
  author = {Haoming Xu, Ningyuan Zhao, Yunzhi Yao, Weihong Xu, Hongru Wang, Xinle Deng, Shumin Deng, Jeff Z. Pan, Huajun Chen and Ningyu Zhang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.203},
  url = {https://doi.org/10.18653/v1/2026.acl-long.203}
}

References

80 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Robert P. Abelson. 1979. Differences between belief and knowledge systems. Cognitive Science, 3(4):355– 366. find
  2. Michael C. Anderson and Collin Green. 2001. Suppressing unwanted memories by executive control. Nature, 410(6826):366–369. find
  3. Michael C. Anderson and Simon Hanslmayr. 2014. Neural mechanisms of motivated forgetting. Trends in Cognitive Sciences, 18(6):279–292. find
  4. Anthropic Alignment Science Blog. 2025. Modifying llm beliefs with synthetic document finetuning. https://alignment.anthropic.com/2025/ modifying-beliefs-via-sdf/. Accessed 2025. ↗
  5. Amos Azaria, Rina Azoulay, and Shulamit Reches. 2024. Chatgpt is a remarkable tool-for experts. DATA INTELLIGENCE, 6(1):240–296. find
  6. Yoshua Bengio, Michael Cohen, Damiano Fornasiere, Joumana Ghosn, Pietro Greiner, Matt MacDermott, 4440 9 find
  7. Sören Mindermann, Adam Oberman, Jesse Richardson, Oliver Richardson, Marc-Antoine Rondeau, Pierre-Luc St-Charles, and David Williams-King. 2025. Superintelligent agents pose catastrophic risks: Can scientist ai offer a safer path? Preprint, arXiv:2502.15657. find
  8. Kaidi Xu. 2024. Shifting attention to relevance: Towards the predictive uncertainty quantification of free-form large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5050–5063, Bangkok, Thailand. Association f… find
  9. Lukas Berglund, Meg Tong, Maximilian Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, and Owain Evans. 2024. The reversal curse: LLMs trained on “a is b” fail to learn “b is a”. In The Twelfth International Conference on Learning Representations. find
  10. Sebastian Farquhar, Jannik Kossen, Lorenz Kuhn, and Yarin Gal. 2024. Detecting hallucinations in large language models using semantic entropy. Nature, 630(8017):625–630. find
  11. Eric Bigelow, Daniel Wurgaft, YingQiao Wang, Noah Goodman, Tomer Ullman, Hidenori Tanaka, and Ekdeep Singh Lubana. 2025a. Belief dynamics reveal the dual nature of in-context learning and activation steering. Preprint, arXiv:2511.00617. — [arXiv:2511.00617](https://arxiv.org/abs/2511.00617) find
  12. Alina Fastowski, Bardh Prenkaj, and Gjergji Kasneci. 2025. From confidence to collapse in LLM factual robustness. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 8650– 8667, Suzhou, China. Association for Computational Linguistics. find
  13. Eric J Bigelow, Ari Holtzman, Hidenori Tanaka, and Tomer Ullman. 2025b. Forking paths in neural text generation. In The Thirteenth International Conference on Learning Representations. find
  14. Jürgen Brandstetter, Péter Rácz, Clay Beckner, Eduardo B. Sandoval, Jennifer Hay, and Christoph Bartneck. 2014. A peer pressure experiment: Recreation of the asch conformity experiment with robots. In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 1335–1340. find
  15. Hung-Ting Chen, Michael Zhang, and Eunsol Choi. 2022. Rich knowledge sources bring complex knowledge conflicts: Recalibrating models to reflect conflicting evidence. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2292–2307, Abu Dhabi, United Arab Emi…
  16. Mehul Damani, Isha Puri, Stewart Slocum, Idan Shenfeld, Leshem Choshen, Yoon Kim, and Jacob Andreas. 2025. Beyond binary rewards: Training lms to reason about their uncertainty. Preprint, arXiv:2507.16806. find
  17. Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, and Jason Weston. 2024. Chain-of-verification reduces hallucination in large language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3563–3578, Bangkok, Thailand. Associ…
  18. Kevin Du, Vésteinn Snæbjarnarson, Niklas Stoehr, Jennifer White, Aaron Schein, and Ryan Cotterell. 2024. Context versus prior knowledge in language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13211–13235, Bangkok,… find
  19. Jinhao Duan, Hao Cheng, Shiqi Wang, Alex Zavalny, Chenan Wang, Renjing Xu, Bhavya Kailkhura, and Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv…
  20. Jiayi Geng, Howard Chen, Ryan Liu, Manoel Horta Ribeiro, Robb Willer, Graham Neubig, and Thomas L. Griffiths. 2025. Accumulating context changes the beliefs of language models. Preprint, arXiv:2511.01805. — [arXiv:2511.01805](https://arxiv.org/abs/2511.01805) find
  21. Daya Guo, Dejian Yang, et al. 2025. Deepseek-r1 incentivizes reasoning in llms through reinforcement learning. Nat., 645(8081):633–638. find
  22. Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. 2024. Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680.
  23. Ryo Hasegawa, Yusuke Sakai, Hidetaka Kamigaito, and Taro Watanabe. 2025. Knowledge editing induces underconfidence in language models. In Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025), pages 338–347, Suzhou, China. Association for Computational Linguisti… find
  24. Zhonghao He, Tianyi Qiu, Hirokazu Shirado, and Maarten Sap. 2025. Martingale score: An unsupervised metric for bayesian rationality in llm reasoning. Preprint, arXiv:2512.02914. — [arXiv:2512.02914](https://arxiv.org/abs/2512.02914) find
  25. Yufang Hou, Alessandra Pascale, Javier Carnerero-Cano, Tigran Tchrakian, Radu Marinescu, Elizabeth Daly, Inkit Padhi, and Prasanna Sattigeri. 2024. Wikicontradict: A benchmark for evaluating llms on real-world knowledge conflicts from wikipedia. In Advances in Neural Information Processing Systems,… find
  26. CARL I. HOVLAND and WALTER WEISS. 1951. The influence of source credibility on communication effectiveness*. Public Opinion Quarterly, 15(4):635– 650. find
  27. Ming Hu, Chenglong Ma, Wei Li, Wanghan Xu, Jiamin Wu, Jucheng Hu, Tianbin Li, Guohang Zhuang, Jiaqi Liu, Yingzhou Lu, et al. 2025. A survey of scientific large language models: From data foundations to agent frontiers. arXiv preprint arXiv:2508.21148. — [arXiv:2508.21148](https://arxiv.org/abs/2508.21148) find
  28. Shangying Hua, Shuangci Jin, and Shengyi Jiang. 2024. The limitations and ethical considerations of chatgpt. DATA INTELLIGENCE, 6(1):201–239. find
  29. Tim Tian Hua, Andrew Qin, Samuel Marks, and Neel Nanda. 2025. Steering evaluation-aware language models to act like they are deployed. Preprint, arXiv:2510.20487. — [arXiv:2510.20487](https://arxiv.org/abs/2510.20487) find
  30. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2025. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems,…
  31. Sohaib Imran, Ihor Kendiukhov, Matthew Broerman, Aditya Thomas, Riccardo Campanella, Rob Lamb, and Peter M. Atkinson. 2025. Are llm belief updates consistent with bayes’ theorem? Preprint, arXiv:2507.17951. — [arXiv:2507.17951](https://arxiv.org/abs/2507.17951) find
  32. Mingyu Jin, Weidi Luo, Sitao Cheng, Xinyi Wang, Wenyue Hua, Ruixiang Tang, William Yang Wang, and Yongfeng Zhang. 2025. Disentangling memory and reasoning ability in large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape…
  33. Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, and Jun Zhao. 2024. Cutting off the head ends the conflict: A mechanism for interpreting and mitigating knowledge conflicts in language models. In Findings of the Association for Computational Lingui… find
  34. Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan, Dawn Drain, Ethan Perez, Nicholas Schiefer, Zac Hatfield-Dodds, Nova DasSarma, Eli Tran-Johnson, Scott Johnston, Sheer El-Showk, Andy Jones, Nelson Elhage, Tristan Hume, Anna Chen, Yuntao Bai, Sam Bowman, Stanislav Fort, Deep Ganguli, Danny… find
  35. Matthew Kearney, Reuben Binns, and Yarin Gal. 2025. Language models change facts based on the way you talk. Preprint, arXiv:2507.14238. — [arXiv:2507.14238](https://arxiv.org/abs/2507.14238) find
  36. Lorenz Kuhn, Yarin Gal, and Sebastian Farquhar. 2023. Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation. In The Eleventh International Conference on Learning Representations.
  37. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. Preprint, arXiv:2309.06180.
  38. Jinqi Lai, Wensheng Gan, Jiayang Wu, Zhenlian Qi, and Philip S Yu. 2024. Large language models in law: A survey. AI Open, 5:181–196.
  39. Hengli Li, Zhaoxin Yu, Qi Shen, Chenxi Li, Mengmeng Wang, Tinglang Wu, Yipeng Kang, Yuxuan Wang, Song-Chun Zhu, Zixia Jia, and Zilong Zheng. 2025a. Beda: Belief estimation as probabilistic constraints for performing strategic dialogue acts. Preprint, arXiv:2512.24885. — [arXiv:2512.24885](https://arxiv.org/abs/2512.24885) find
  40. Zhong-Zhi Li, Duzhen Zhang, Ming-Liang Zhang, Jiaxin Zhang, Zengyan Liu, Yuxuan Yao, Haotian Xu, Junhao Zheng, Pei-Jie Wang, Xiuyi Chen, Yingying Zhang, Fei Yin, Jiahua Dong, Zhiwei Li, Bao-Long Bi, Ling-Rui Mei, Junfeng Fang, Xiao Liang, Zhijiang Guo, Le Song, and Cheng-Lin Liu. 2025b. From system…
  41. Fenglin Liu, Hongjian Zhou, Boyang Gu, Xinyu Zou, Jinfa Huang, Jinge Wu, Yiru Li, Sam S Chen, Yining Hua, Peilin Zhou, et al. 2025a. Application of large language models in medicine. Nature Reviews Bioengineering, pages 1–20. find
  42. Xiaohong Liu, Hao Liu, Guoxing Yang, Zeyu Jiang, Shuguang Cui, Zhaoze Zhang, Huan Wang, Liyuan Tao, Yongchang Sun, Zhu Song, et al. 2025b. A generalist medical language model for disease diagnosis assistance. Nature medicine, 31(3):932–942. find
  43. Shayne Longpre, Kartik Perisetla, Anthony Chen, Nikhil Ramesh, Chris DuBois, and Sameer Singh. 2021. Entity-based knowledge conflicts in question answering. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7052–7063, Online and Punta Cana, Dominican Re…
  44. Renjie Luo, Zichen Liu, Xiangyan Liu, Chao Du, Min Lin, Wenhu Chen, Wei Lu, and Tianyu Pang. 2025. Language models can learn from verbal feedback without scalar rewards. Preprint, arXiv:2509.22638. — [arXiv:2509.22638](https://arxiv.org/abs/2509.22638) find
  45. Uzay Macar, Paul C. Bogdan, Senthooran Rajamanoharan, and Neel Nanda. 2025. Thought branches: Interpreting llm reasoning requires resampling. Preprint, arXiv:2510.27484. 4442 11 — [arXiv:2510.27484](https://arxiv.org/abs/2510.27484) find
  46. Yisong Miao and Min-Yen Kan. 2025. Discursive circuits: How do language models understand discourse relations? In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 32558–32577, Suzhou, China. Association for Computational Linguistics. find
  47. Benjamin Newman, Abhilasha Ravichander, Jaehun Jung, Rui Xin, Hamish Ivison, Yegor Kuznetsov, Pang Wei Koh, and Yejin Choi. 2025. The curious case of factuality finetuning: Models’ internal beliefs can improve factuality. Preprint, arXiv:2507.08371. — [arXiv:2507.08371](https://arxiv.org/abs/2507.08371) find
  48. Team OLMo, Pete Walsh, Luca Soldaini, Dirk Groeneveld, Kyle Lo, Shane Arora, Akshita Bhagia, Yuling Gu, Shengyi Huang, Matt Jordan, Nathan Lambert, Dustin Schwenk, Oyvind Tafjord, Taira Anderson, David Atkinson, Faeze Brahman, Christopher Clark, Pradeep Dasigi, Nouha Dziri, Michal Guerquin, Hamish I… find
  49. Tsung-Hsuan Pan, Chung-Chi Chen, Hen-Hsen Huang, and Hsin-Hsi Chen. 2025. Diagnosing model editing via knowledge spectrum. Preprint, arXiv:2509.17482. — [arXiv:2509.17482](https://arxiv.org/abs/2509.17482) find
  50. Pouya Pezeshkpour. 2023. Measuring and modifying factual knowledge in large language models. In 2023 International Conference on Machine Learning and Applications (ICMLA), pages 831–838.
  51. Chanthika Pornpitakpan. 2004. The persuasiveness of source credibility: A critical review of five decades’ evidence. Journal of Applied Social Psychology, 34(2):243–281. find
  52. Pranab Sahoo, Ayush Kumar Singh, Sriparna Saha, Vinija Jain, Samrat Mondal, and Aman Chadha. 2024. A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv preprint arXiv:2402.07927.
  53. Henrique Santos, Ke Shen, Alice M. Mulvehill, Mayank Kejriwal, and Deborah L. Mcguinness. 2024. A theoretically grounded question answering data set for evaluating machine common sense. DATA INTELLI-GENCE, 6(1):1–28. find
  54. Alan H. Schoenfeld. 1983. Beyond the purely cognitive: Belief systems, social cognitions, and metacognitions as driving forces in intellectual performance. Cognitive Science, 7(4):329–363. find
  55. Gary I. Schulman. 1967. Asch conformity studies: Conformity to the experimenter and/or to the group? Sociometry, 30(1):26–40. find
  56. Mrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R. Bowman, Esin DURMUS, Zac Hatfield-Dodds, Scott R Johnston, Shauna M Kravec, Timothy Maxwell, Sam Mc-Candlish, Kamal Ndousse, Oliver Rausch, Nicholas Schiefer, Da Yan, Miranda Zhang, and Ethan Perez. 2024. Towards under…
  57. Muzafer Sherif and Carl I. Hovland. 1961. Social Judgment: Assimilation and Contrast Effects in Communication and Attitude Change. Yale University Press, New Haven. find
  58. Stewart Slocum, Julian Minder, Clément Dumas, Henry Sleight, Ryan Greenblatt, Samuel Marks, and Rowan Wang. 2025. Believe it or not: How deeply do llms believe implanted facts? Preprint, arXiv:2510.17941. — [arXiv:2510.17941](https://arxiv.org/abs/2510.17941) find
  59. Mark Steyvers, Heliodoro Tejeda, Aakriti Kumar, Catarina Belem, Sheer Karny, Xinyue Hu, Lukas W. Mayer, and Padhraic Smyth. 2025. What large language models know and what people think they know. Nature Machine Intelligence, 7(2):221–231. find
  60. Mirac Suzgun, Tayfun Gur, Federico Bianchi, Daniel E. Ho, Thomas Icard, Dan Jurafsky, and James Zou. 2025. Language models cannot reliably distinguish belief from knowledge and fact. Nature Machine Intelligence, 7(11):1780–1790. find
  61. Hexiang Tan, Fei Sun, Sha Liu, Du Su, Qi Cao, Xin Chen, Jingang Wang, Xunliang Cai, Yuanzhuo Wang, Huawei Shen, and Xueqi Cheng. 2025. Too consistent to detect: A study of self-consistent errors in LLMs. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages…
  62. Qwen Team. 2024. Qwen2.5: A party of foundation models. find
  63. Qwen Team. 2025. Qwen3 technical report. Preprint, arXiv:2505.09388.
  64. Stylianos Loukas Vasileiou, Antonio Rago, Maria Van-ina Martinez, and William Yeoh. 2025. How do people revise inconsistent beliefs? examining belief revision in humans with user studies. Preprint, arXiv:2506.09977. — [arXiv:2506.09977](https://arxiv.org/abs/2506.09977) find
  65. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023a. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations.
  66. Yuqing Wang, Yun Zhao, and Linda Petzold. 2023b. Are large language models ready for healthcare? a comparative study on clinical language understanding. In Machine learning for healthcare conference, pages 804–823. PMLR. 4443 12 find
  67. Jason Wei, Nguyen Karina, Hyung Won Chung, Yunxin Joy Jiao, Spencer Papay, Amelia Glaese, John Schulman, and William Fedus. 2024. Measuring short-form factuality in large language models. Preprint, arXiv:2411.04368.
  68. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2023. Chain-of-thought prompting elicits reasoning in large language models. Preprint, arXiv:2201.11903.
  69. Jerry Wei, Da Huang, Yifeng Lu, Denny Zhou, and Quoc V Le. 2025. Simple synthetic data reduces sycophancy in large language models.
  70. Zhi Zhou, Yuhao Tan, Zenan Li, Yuan Yao, Lan-Zhe Guo, Yu-Feng Li, and Xiaoxing Ma. 2025. A theoretical study on bridging internal probability and self-consistency for LLM reasoning. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. find
  71. Qing Zong, Jiayu Liu, Tianshi Zheng, Chunyang Li, Baixuan Xu, Haochen Shi, Weiqi Wang, Zhaowei Wang, Chunkit Chan, and Yangqiu Song. 2025. Critical: Can critique help llm uncertainty or confidence calibration? Preprint, arXiv:2510.24505. — [arXiv:2510.24505](https://arxiv.org/abs/2510.24505) find
  72. Johannes Welbl, Nelson F. Liu, and Matt Gardner. 2017. Crowdsourcing multiple choice science questions. Preprint, arXiv:1707.06209.
  73. Zhiyuan Weng, Guikun Chen, and Wenguan Wang. 2025. Do as we do, not as you think: the conformity of large language models. In The Thirteenth International Conference on Learning Representations. find
  74. Jr. Whitehead, Jack L. 1968. Factors of source credibility. Quarterly Journal of Speech, 54(1):59–63. find
  75. Yuyang Xu, Renjun Hu, Haochao Ying, Jian Wu, Xing Shi, and Wei Lin. 2025. Large language models could be rote learners. Preprint, arXiv:2504.08300. — [arXiv:2504.08300](https://arxiv.org/abs/2504.08300) find
  76. 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. Preprint, arXiv:1809.09600.
  77. Yunzhi Yao, Jiaxin Qin, Ningyu Zhang, Haoming Xu, Yuqi Zhu, Zeping Yu, Mengru Wang, Yuqi Tang, Jia-Chen Gu, Shumin Deng, Nanyun Peng, and Huajun Chen. 2025. Rethinking knowledge editing in reasoning era. find
  78. Qinan Yu, Jack Merullo, and Ellie Pavlick. 2023. Characterizing mechanisms for factual recall in language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9924–9959, Singapore. Association for Computational Linguistics. find
  79. Jintian Zhang, Xin Xu, Ningyu Zhang, Ruibo Liu, Bryan Hooi, and Shumin Deng. 2024. Exploring collaboration mechanisms for LLM agents: A social psychology view. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14544– 14607, Bang…
  80. Ningyu Zhang, Zhen Bi, Xiaozhuan Liang, Siyuan Cheng, Haosen Hong, Shumin Deng, Jiazhang Lian, Qiang Zhang, and Huajun Chen. 2022. Ontoprotein: Protein pretraining with gene ontology embedding. arXiv preprint arXiv:2201.11147. 4444 13 — [arXiv:2201.11147](https://arxiv.org/abs/2201.11147) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/xu-2026-illusions-confidence-diagnosing-llm-truthfulness/