awesome_llm_hallucination.md

Awesome llm hallucination (truth-gpt)

• Awesome llm hallucination (truth-gpt)
  • Survey
  • Papers
  • Evalution
  • Other
  • Extra reference

Survey

• Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study, arXiv, 2406.07057, arxiv, pdf, cication: -1

  Yichi Zhang, Yao Huang, Yitong Sun, Chang Liu, Zhe Zhao, Zhengwei Fang, Yifan Wang, Huanran Chen, Xiao Yang, Xingxing Wei · (multi-trust.github)

• Can We Catch the Elephant? The Evolvement of Hallucination Evaluation on Natural Language Generation: A Survey, arXiv, 2404.12041, arxiv, pdf, cication: -1

  Siya Qi, Yulan He, Zheng Yuan

• A Survey on Hallucination in Large Vision-Language Models, arXiv, 2402.00253, arxiv, pdf, cication: -1

  Hanchao Liu, Wenyuan Xue, Yifei Chen, Dapeng Chen, Xiutian Zhao, Ke Wang, Liping Hou, Rongjun Li, Wei Peng

• TrustLLM: Trustworthiness in Large Language Models, arXiv, 2401.05561, arxiv, pdf, cication: -1

  Lichao Sun, Yue Huang, Haoran Wang, Siyuan Wu, Qihui Zhang, Chujie Gao, Yixin Huang, Wenhan Lyu, Yixuan Zhang, Xiner Li · (trustllmbenchmark.github)

• A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models, arXiv, 2401.01313, arxiv, pdf, cication: -1

  S. M Towhidul Islam Tonmoy, S M Mehedi Zaman, Vinija Jain, Anku Rani, Vipula Rawte, Aman Chadha, Amitava Das

• A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions, arXiv, 2311.05232, arxiv, pdf, cication: -1

  Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin

• Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity, arXiv, 2310.07521, arxiv, pdf, cication: 3

  Cunxiang Wang, Xiaoze Liu, Yuanhao Yue, Xiangru Tang, Tianhang Zhang, Cheng Jiayang, Yunzhi Yao, Wenyang Gao, Xuming Hu, Zehan Qi · (jiqizhixin)

Papers

• Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability, arXiv, 2408.07852, arxiv, pdf, cication: -1

  Jiri Hron, Laura Culp, Gamaleldin Elsayed, Rosanne Liu, Ben Adlam, Maxwell Bileschi, Bernd Bohnet, JD Co-Reyes, Noah Fiedel, C. Daniel Freeman

• Generation Constraint Scaling Can Mitigate Hallucination, arXiv, 2407.16908, arxiv, pdf, cication: -1

  Georgios Kollias, Payel Das, Subhajit Chaudhury

• Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps, arXiv, 2407.07071, arxiv, pdf, cication: -1

  Yung-Sung Chuang, Linlu Qiu, Cheng-Yu Hsieh, Ranjay Krishna, Yoon Kim, James Glass · (Lookback-Lens - voidism)

• PROVER-VERIFIER GAMES IMPROVE LEGIBILITY OF LLM OUTPUTS

• Extrinsic Hallucinations in LLMs | Lil'Log

• VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models, arXiv, 2406.16338, arxiv, pdf, cication: -1

  Yuxuan Wang, Yueqian Wang, Dongyan Zhao, Cihang Xie, Zilong Zheng

• Lamini-Memory-Tuning - lamini-ai

  Banishing LLM Hallucinations Requires Rethinking Generalization · (huggingface)

• To Believe or Not to Believe Your LLM, arXiv, 2406.02543, arxiv, pdf, cication: -1

  Yasin Abbasi Yadkori, Ilja Kuzborskij, András György, Csaba Szepesvári

• Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?, arXiv, 2405.05904, arxiv, pdf, cication: -1

  Zorik Gekhman, Gal Yona, Roee Aharoni, Matan Eyal, Amir Feder, Roi Reichart, Jonathan Herzig

• In Search of Truth: An Interrogation Approach to Hallucination Detection, arXiv, 2403.02889, arxiv, pdf, cication: -1

  Yakir Yehuda, Itzik Malkiel, Oren Barkan, Jonathan Weill, Royi Ronen, Noam Koenigstein

• Fine-grained Hallucination Detection and Editing for Language Models, arXiv, 2401.06855, arxiv, pdf, cication: -1

  Abhika Mishra, Akari Asai, Vidhisha Balachandran, Yizhong Wang, Graham Neubig, Yulia Tsvetkov, Hannaneh Hajishirzi · (huggingface)

• Steering Llama 2 via Contrastive Activation Addition, arXiv, 2312.06681, arxiv, pdf, cication: -1

  Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, Alexander Matt Turner

• Unlocking Anticipatory Text Generation: A Constrained Approach for Faithful Decoding with Large Language Models, arXiv, 2312.06149, arxiv, pdf, cication: -1

  Lifu Tu, Semih Yavuz, Jin Qu, Jiacheng Xu, Rui Meng, Caiming Xiong, Yingbo Zhou

• Technical Report: Large Language Models can Strategically Deceive their Users when Put Under Pressure, arXiv, 2311.07590, arxiv, pdf, cication: -1

  Jérémy Scheurer, Mikita Balesni, Marius Hobbhahn

• Calibrated Language Models Must Hallucinate, arXiv, 2311.14648, arxiv, pdf, cication: -1

  Adam Tauman Kalai, Santosh S. Vempala · (jiqizhixin)

• Fine-tuning Language Models for Factuality, arXiv, 2311.08401, arxiv, pdf, cication: -1

  Katherine Tian, Eric Mitchell, Huaxiu Yao, Christopher D. Manning, Chelsea Finn

• Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges, arXiv, 2311.03287, arxiv, pdf, cication: -1

  Chenhang Cui, Yiyang Zhou, Xinyu Yang, Shirley Wu, Linjun Zhang, James Zou, Huaxiu Yao · (Bingo - gzcch)

  · (jiqizhixin)

• The Perils & Promises of Fact-checking with Large Language Models, arXiv, 2310.13549, arxiv, pdf, cication: 1

  Dorian Quelle, Alexandre Bovet

• Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs, arXiv, 2310.11689, arxiv, pdf, cication: 2

  Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan O Arik, Tomas Pfister, Somesh Jha · (mp.weixin.qq)

• Personas as a Way to Model Truthfulness in Language Models, arXiv, 2310.18168, arxiv, pdf, cication: -1

  Nitish Joshi, Javier Rando, Abulhair Saparov, Najoung Kim, He He

• Woodpecker: Hallucination Correction for Multimodal Large Language Models, arXiv, 2310.16045, arxiv, pdf, cication: 1

  Shukang Yin, Chaoyou Fu, Sirui Zhao, Tong Xu, Hao Wang, Dianbo Sui, Yunhang Shen, Ke Li, Xing Sun, Enhong Chen · (qbitai)

• The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A", arXiv, 2309.12288, arxiv, pdf, cication: 3

  Lukas Berglund, Meg Tong, Max Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, Owain Evans · (mp.weixin.qq)

• Chain-of-Verification Reduces Hallucination in Large Language Models, arXiv, 2309.11495, arxiv, pdf, cication: 8

  Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, Jason Weston · (qbitai)

• DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models, arXiv, 2309.03883, arxiv, pdf, cication: 6

  Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, Pengcheng He · (mp.weixin.qq)

• Towards Measuring the Representation of Subjective Global Opinions in Language Models, arXiv, 2306.16388, arxiv, pdf, cication: 17

  Esin Durmus, Karina Nyugen, Thomas I. Liao, Nicholas Schiefer, Amanda Askell, Anton Bakhtin, Carol Chen, Zac Hatfield-Dodds, Danny Hernandez, Nicholas Joseph

• Inference-Time Intervention: Eliciting Truthful Answers from a Language Model, arXiv, 2306.03341, arxiv, pdf, cication: 14

  Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg · (mp.weixin.qq)

• DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models, arXiv, 2306.11698, arxiv, pdf, cication: 24

  Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer

• WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia, arXiv, 2305.14292, arxiv, pdf, cication: -1

  Sina J. Semnani, Violet Z. Yao, Heidi C. Zhang, Monica S. Lam

  · (wikichat - stanford-oval)

• Let's Verify Step by Step, arXiv, 2305.20050, arxiv, pdf, cication: -1

  Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, Karl Cobbe · (docs.google)

Multi-Mod

• AUTOHALLUSION: Automatic Generation of Hallucination Benchmarks for Vision-Language Models, arXiv, 2406.10900, arxiv, pdf, cication: -1

  Xiyang Wu, Tianrui Guan, Dianqi Li, Shuaiyi Huang, Xiaoyu Liu, Xijun Wang, Ruiqi Xian, Abhinav Shrivastava, Furong Huang, Jordan Lee Boyd-Graber

Evalution

• Lynx: An Open Source Hallucination Evaluation Model, arXiv, 2407.08488, arxiv, pdf, cication: -1

  Selvan Sunitha Ravi, Bartosz Mielczarek, Anand Kannappan, Douwe Kiela, Rebecca Qian · (huggingface)

• Long-form factuality in large language models, arXiv, 2403.18802, arxiv, pdf, cication: -1

  Jerry Wei, Chengrun Yang, Xinying Song, Yifeng Lu, Nathan Hu, Dustin Tran, Daiyi Peng, Ruibo Liu, Da Huang, Cosmo Du · (long-form-factuality - google-deepmind)

• TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization, arXiv, 2402.13249, arxiv, pdf, cication: -1

  Liyan Tang, Igor Shalyminov, Amy Wing-mei Wong, Jon Burnsky, Jake W. Vincent, Yu'an Yang, Siffi Singh, Song Feng, Hwanjun Song, Hang Su

• The Hallucinations Leaderboard, an Open Effort to Measure Hallucinations in Large Language Models

• HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination & Visual Illusion in Large Vision-Language Models, arXiv, 2310.14566, arxiv, pdf, cication: -1

  Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob · (HallusionBench - tianyi-lab)

• hallucination-leaderboard - vectara

  Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents · (t)

Other

• I fact-checked ChatGPT with Bard, Claude, and Copilot - and this AI was the most confidently incorrect
• Automatic Hallucination detection with SelfCheckGPT NLI
• 大模型幻觉问题调研

Extra reference