Uncritical trust in LLMs can give rise to a phenomenon Cognitive Mirage, leading to misguided decision-making and a cascade of unintended consequences. To effectively control the risk of hallucinations, we summarize recent progress in hallucination theories and solutions in this paper. We propose to organize relevant work by a comprehensive survey.

[:bell: News! :bell: ] We have released a new survey paper:"Cognitive Mirage: A Review of Hallucinations in Large Language Models" based on this repository, with a perspective of Hallucinations in LLMs! We are looking forward to any comments or discussions on this topic :)

🕵️ Introduction

As large language models continue to develop in the field of AI, text generation systems are susceptible to a worrisome phenomenon known as hallucination. In this study, we summarize recent compelling insights into hallucinations in LLMs. We present a novel taxonomy of hallucinations from various text generation tasks, thus provide theoretical insights, detection methods and improvement approaches. Based on this, future research directions are proposed. Our contribution are threefold: (1) We provide a detailed and complete taxonomy for hallucinations appearing in text generation tasks; (2) We provide theoretical analyses of hallucinations in LLMs and provide existing detection and improvement methods; (3) We propose several research directions that can be developed in the future. As hallucinations garner significant attention from the community, we will maintain updates on relevant research progress.

🏆 A Timeline of LLMs

LLM Name	Title	Authors	Publication Date
T5	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.	Colin Raffel, Noam Shazeer, Adam Roberts	2019.10
GPT-3	Language Models are Few-Shot Learners.	Tom B. Brown, Benjamin Mann, Nick Ryder	2020.12
mT5	mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer.	Linting Xue, Noah Constant, Adam Roberts	2021.3
Codex	Evaluating Large Language Models Trained on Code.	Mark Chen, Jerry Tworek, Heewoo Jun	2021.7
FLAN	Finetuned Language Models are Zero-Shot Learners.	Jason Wei, Maarten Bosma, Vincent Y. Zhao	2021.9
WebGPT	WebGPT: Browser-assisted question-answering with human feedback.	Reiichiro Nakano, Jacob Hilton, Suchir Balaji	2021.12
InstructGPT	Training language models to follow instructions with human feedback.	Long Ouyang, Jeffrey Wu, Xu Jiang	2022.3
CodeGen	CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis.	Erik Nijkamp, Bo Pang, Hiroaki Hayashi	2022.3
Claude	Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.	Yuntao Bai, Andy Jones, Kamal Ndousse	2022.4
PaLM	PaLM: Scaling Language Modeling with Pathways.	Aakanksha Chowdhery, Sharan Narang, Jacob Devlin	2022.4
OPT	OPT: Open Pre-trained Transformer Language Models.	Susan Zhang, Stephen Roller, Naman Goyal	2022.5
Super-NaturalInstructions	ESuper-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks.	Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi	2022.9
GLM	GLM-130B: An Open Bilingual Pre-trained Model.	Aohan Zeng, Xiao Liu, Zhengxiao Du	2022.10
BLOOM	BLOOM: A 176B-Parameter Open-Access Multilingual Language Model.	Teven Le Scao, Angela Fan, Christopher Akiki	2022.11
LLaMA	LLaMA: Open and Efficient Foundation Language Models.	Hugo Touvron, Thibaut Lavril, Gautier Izacard	2023.2
Alpaca	Alpaca: A Strong, Replicable Instruction-Following Model.	Rohan Taori, Ishaan Gulrajani, Tianyi Zhang	2023.3
GPT-4	GPT-4 Technical Report.	OpenAI	2023.3
WizardLM	WizardLM: Empowering Large Language Models to Follow Complex Instructions.	Can Xu, Qingfeng Sun, Kai Zheng	2023.4
Vicuna	Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90% ChatGPT Quality.	The Vicuna Team	2023.5
ChatGLM	ChatGLM.	Wisdom and Clear Speech Team	2023.6
Llama2	Llama 2: Open Foundation and Fine-Tuned Chat Models.	Hugo Touvron, Louis Martin, Kevin Stone	2023.7

🏳‍🌈 Definition of Hallucination

• "Truthful AI: Developing and governing AI that does not lie.", 2021.10

  • Owain Evans, Owen Cotton-Barratt, Lukas Finnveden
  • [Paper]

• "Survey of Hallucination in Natural Language Generation", 2022.2

  • Ziwei Ji, Nayeon Lee, Rita Frieske
  • [Paper]

• "Context-faithful Prompting for Large Language Models.", 2023.3

  • Wenxuan Zhou, Sheng Zhang, Hoifung Poon
  • [Paper]

• "Do Language Models Know When They’re Hallucinating References?", 2023.5

  • Ayush Agrawal, Lester Mackey, Adam Tauman Kalai
  • [Paper]

🎉 Mechanism Analysis

✨Data Attribution

• "Data Distributional Properties Drive Emergent In-Context Learning in Transformers.", 2022.5

  • Stephanie C. Y. Chan, Adam Santoro, Andrew K. Lampinen
  • [Paper]

• "Towards Tracing Factual Knowledge in Language Models Back to the Training Data.", 2022.5

  • Ekin Akyürek, Tolga Bolukbasi, Frederick Liu
  • [Paper]

• "A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity.", 2023.2

  • Yejin Bang, Samuel Cahyawijaya, Nayeon Lee
  • [Paper]

• "Hallucinations in Large Multilingual Translation Models.", 2023.3

  • Nuno Miguel Guerreiro, Duarte M. Alves, Jonas Waldendorf
  • [Paper]

• "Visual Instruction Tuning.", 2023.4

  • Haotian Liu, Chunyuan Li, Qingyang Wu
  • [Paper]

• "Evaluating Object Hallucination in Large Vision-Language Models.", 2023.5

  • Yifan Li, Yifan Du, Kun Zhou
  • [Paper]

• "Sources of Hallucination by Large Language Models on Inference Tasks.", 2023.5

  • Nick McKenna, Tianyi Li, Liang Cheng
  • [Paper]

• "Automatic Evaluation of Attribution by Large Language Models.", 2023.5

  • Xiang Yue, Boshi Wang, Kai Zhang
  • [Paper]

• "Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning.", 2023.6

  • Fuxiao Liu, Kevin Lin, Linjie Li
  • [Paper]

✨Knowledge Gap

• "A Survey of Knowledge-enhanced Text Generation.", 2022.1

  • Wenhao Yu, Chenguang Zhu, Zaitang Li
  • [Paper]

• "Attributed Text Generation via Post-hoc Research and Revision.", 2022.10

  • Luyu Gao, Zhuyun Dai, Panupong Pasupat
  • [Paper]

• "Artificial Hallucinations in ChatGPT: Implications in Scientific Writing.", 2023.2

  • Hussam Alkaissi, Samy I McFarlane
  • [Paper]

• "SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models.", 2023.3

  • Potsawee Manakul, Adian Liusie, Mark J. F. Gales
  • [Paper]

• "Why Does ChatGPT Fall Short in Answering Questions Faithfully?", 2023.4

  • Shen Zheng, Jie Huang, Kevin Chen-Chuan Chang
  • [Paper]

• "Zero-shot Faithful Factual Error Correction.", 2023.5

  • Kung-Hsiang Huang, Hou Pong Chan, Heng Ji
  • [Paper]

• "Mitigating Language Model Hallucination with Interactive Question-Knowledge Alignment.", 2023.5

  • Shuo Zhang, Liangming Pan, Junzhou Zhao
  • [Paper]

• "Adaptive Chameleon or Stubborn Sloth: Unraveling the Behavior of Large Language Models in Knowledge Clashes.", 2023.5

  • Jian Xie, Kai Zhang, Jiangjie Chen
  • [Paper]

• "Evaluating Generative Models for Graph-to-Text Generation.", 2023.7

  • huzhou Yuan, Michael Färber
  • [Paper]

• "Overthinking the Truth: Understanding how Language Models Process False Demonstrations.", 2023.7

  • Danny Halawi, Jean-Stanislas Denain, Jacob Steinhardt
  • [Paper]

✨Optimum Formulation

• "Improved Natural Language Generation via Loss Truncation.", 2020.5

  • Daniel Kang, Tatsunori Hashimoto
  • [Paper]

• "The Curious Case of Hallucinations in Neural Machine Translation.", 2021.4

  • Vikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt
  • [Paper]

• "Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation.", 2022.12

  • Nuno Miguel Guerreiro, Pierre Colombo, Pablo Piantanida
  • [Paper]

• "Elastic Weight Removal for Faithful and Abstractive Dialogue Generation.", 2023.3

  • Nico Daheim, Nouha Dziri, Mrinmaya Sachan
  • [Paper]

• "HistAlign: Improving Context Dependency in Language Generation by Aligning with History.", 2023.5

  • David Wan, Shiyue Zhang, Mohit Bansal
  • [Paper]

• "How Language Model Hallucinations Can Snowball.", 2023.5

  • Muru Zhang, Ofir Press, William Merrill
  • [Paper]

• "Improving Language Models via Plug-and-Play Retrieval Feedback.", 2023.5

  • Wenhao Yu, Zhihan Zhang, Zhenwen Liang
  • [Paper]

• "Teaching Language Models to Hallucinate Less with Synthetic Tasks.", 2023.10

  • Erik Jones, Hamid Palangi, Clarisse Simões
  • [Paper]

🪁Taxonomy of LLMs Hallucination in NLP tasks

✨Machine Translation

• "Unsupervised Cross-lingual Representation Learning at Scale.", 2020.7

  • Alexis Conneau, Kartikay Khandelwal, Naman Goyal
  • [Paper]

• "The Curious Case of Hallucinations in Neural Machine Translation.", 2021.4

  • Vikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt
  • [Paper]

• "Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation.", 2022.5

  • Tu Vu, Aditya Barua, Brian Lester
  • [Paper]

• "Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation.", 2022.8

  • Nuno Miguel Guerreiro, Elena Voita, André F. T. Martins
  • [Paper]

• "Prompting PaLM for Translation: Assessing Strategies and Performance.", 2022.11

  • David Vilar, Markus Freitag, Colin Cherry
  • [Paper]

• "The unreasonable effectiveness of few-shot learning for machine translation.", 2023.2

  • Xavier Garcia, Yamini Bansal, Colin Cherry
  • [Paper]

• "How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation.", 2023.2

  • Amr Hendy, Mohamed Abdelrehim, Amr Sharaf
  • [Paper]

• "Hallucinations in Large Multilingual Translation Models.", 2023.3

  • Nuno Miguel Guerreiro, Duarte M. Alves, Jonas Waldendorf
  • [Paper]

• "Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM.", 2023.3

  • Rachel Bawden, François Yvon
  • [Paper]

• "HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation.", 2023.5

  • David Dale, Elena Voita, Janice Lam, Prangthip Hansanti
  • [Paper]

• "mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations.", 2023.5

  • Jonas Pfeiffer, Francesco Piccinno, Massimo Nicosia
  • [Paper]

✨Question and Answer

• "Hurdles to Progress in Long-form Question Answering.", 2021.6

  • Kalpesh Krishna, Aurko Roy, Mohit Iyyer
  • [Paper]

• "Entity-Based Knowledge Conflicts in Question Answering.", 2021.9

  • Shayne Longpre, Kartik Perisetla, Anthony Chen
  • [Paper]

• "TruthfulQA: Measuring How Models Mimic Human Falsehoods.", 2022.5

  • Stephanie Lin, Jacob Hilton, Owain Evans
  • [Paper]

• "Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback.", 2023.2

  • Baolin Peng, Michel Galley, Pengcheng He
  • [Paper]

• "Why Does ChatGPT Fall Short in Answering Questions Faithfully?", 2023.4

  • Shen Zheng, Jie Huang, Kevin Chen-Chuan Chang
  • [Paper]

• "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering.", 2023.7

  • Vaibhav Adlakha, Parishad BehnamGhader, Xing Han Lu
  • [Paper]

• "Med-HALT: Medical Domain Hallucination Test for Large Language Models.", 2023.7

  • Logesh Kumar Umapathi, Ankit Pal, Malaikannan Sankarasubbu
  • [Paper]

✨Dialog System

• "On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?", 2022.7

  • Nouha Dziri, Sivan Milton, Mo Yu
  • [Paper]

• "Contrastive Learning Reduces Hallucination in Conversations.", 2022.12

  • Weiwei Sun, Zhengliang Shi, Shen Gao
  • [Paper]

• "Diving Deep into Modes of Fact Hallucinations in Dialogue Systems.", 2022.12

  • Souvik Das, Sougata Saha, Rohini K. Srihari
  • [Paper]

• "Elastic Weight Removal for Faithful and Abstractive Dialogue Generation.", 2023.3

  • Nico Daheim, Nouha Dziri, Mrinmaya Sachan
  • [Paper]

✨Summarization System

• "Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization.", 2022.5

  • Meng Cao, Yue Dong, Jackie Chi Kit Cheung
  • [Paper]

• "Evaluating the Factual Consistency of Large Language Models.", 2022.11

  • Derek Tam, Anisha Mascarenhas, Shiyue Zhang
  • [Paper]

• "Why is this misleading?": Detecting News Headline Hallucinations with Explanations.", 2023.2

  • Jiaming Shen, Jialu Liu, Dan Finnie
  • [Paper]

• "Detecting and Mitigating Hallucinations in Multilingual Summarisation.", 2023.5

  • Yifu Qiu, Yftah Ziser, Anna Korhonen
  • [Paper]

• "LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond.", 2023.5

  • Philippe Laban, Wojciech Kryściński, Divyansh Agarwal
  • [Paper]

• "Evaluating Factual Consistency of Texts with Semantic Role Labeling.", 2023.5

  • Jing Fan, Dennis Aumiller, Michael Gertz
  • [Paper]

• "Summarization is (Almost) Dead.", 2023.9

  • Xiao Pu, Mingqi Gao, Xiaojun Wan
  • [Paper]

✨Knowledge Graphs with LLMs

• "GPT-NER: Named Entity Recognition via Large Language Models.", 2023.4

  • Shuhe Wang, Xiaofei Sun, Xiaoya Li
  • [Paper]

• "LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities.", 2023.5

  • Yuqi Zhu, Xiaohan Wang, Jing Chen
  • [Paper]

• "KoLA: Carefully Benchmarking World Knowledge of Large Language Models.", 2023.6

  • Jifan Yu, Xiaozhi Wang, Shangqing Tu
  • [Paper]

• "Evaluating Generative Models for Graph-to-Text Generation.", 2023.7

  • Shuzhou Yuan, Michael Färber
  • [Paper]

• "Text2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Text.", 2023.8

  • Nandana Mihindukulasooriya, Sanju Tiwari, Carlos F. Enguix
  • [Paper]

✨Cross-modal System

• "Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning.", 2021.10

  • Ali Furkan Biten, Lluís Gómez, Dimosthenis Karatzas
  • [Paper]

• "Simple Token-Level Confidence Improves Caption Correctness.", 2023.5

  • Suzanne Petryk, Spencer Whitehead, Joseph E. Gonzalez
  • [Paper]

• "Evaluating Object Hallucination in Large Vision-Language Models.", 2023.5

  • Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang
  • [Paper]

• "Album Storytelling with Iterative Story-aware Captioning and Large Language Models.", 2023.5

  • Munan Ning, Yujia Xie, Dongdong Chen
  • [Paper]

• "Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning.", 2023.6

  • Fuxiao Liu, Kevin Lin, Linjie Li
  • [Paper]

• "Fact-Checking of AI-Generated Reports.", 2023.7

  • Razi Mahmood, Ge Wang, Mannudeep Kalra
  • [Paper]

✨Others

• "The Scope of ChatGPT in Software Engineering: A Thorough Investigation.", 2023.5

  • Wei Ma, Shangqing Liu, Wenhan Wang
  • [Paper]

• "Generating Benchmarks for Factuality Evaluation of Language Models.", 2023.7

  • Dor Muhlgay, Ori Ram, Inbal Magar
  • [Paper]

🔮 Hallucination Detection

✨Inference Classifier

• "Evaluating the Factual Consistency of Large Language Models Through Summarization.", 2022.11

  • Derek Tam, Anisha Mascarenhas, Shiyue Zhang
  • [Paper]

• "Why is this misleading?": Detecting News Headline Hallucinations with Explanations.", 2023.2

  • Jiaming Shen, Jialu Liu, Daniel Finnie
  • [Paper]

• "HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models.", 2023.5

  • Junyi Li, Xiaoxue Cheng, Wayne Xin Zhao
  • [Paper]

• "Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning.", 2023.6

  • Fuxiao Liu, Kevin Lin, Linjie Li
  • [Paper]

• "Fact-Checking of AI-Generated Reports.", 2023.7

  • Razi Mahmood, Ge Wang, Mannudeep K. Kalra
  • [Paper]

• "Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations.", 2023.10

  • Deren Lei, Yaxi Li, Mengya Hu
  • [Paper]

✨Uncertainty Measure

• "BARTScore: Evaluating Generated Text as Text Generation.", 2021.6

  • Weizhe Yuan, Graham Neubig, Pengfei Liu
  • [Paper]

• "Contrastive Learning Reduces Hallucination in Conversations.", 2022.12

  • Weiwei Sun, Zhengliang Shi, Shen Gao
  • [Paper]

• "Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models.", 2023.5

  • Alfonso Amayuelas, Liangming Pan, Wenhu Chen
  • [Paper]

• "Methods for Measuring, Updating, and Visualizing Factual Beliefs in Language Models.", 2023.5

  • Peter Hase, Mona Diab, Asli Celikyilmaz
  • [Paper]

• "Measuring and Modifying Factual Knowledge in Large Language Models.", 2023.6

  • Pouya Pezeshkpour
  • [Paper]

• "LLM Calibration and Automatic Hallucination Detection via Pareto Optimal Self-supervision.", 2023.6

  • Theodore Zhao, Mu Wei, J. Samuel Preston
  • [Paper]

• "A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation.", 2023.7

  • Neeraj Varshney, Wenlin Yao, Hongming Zhang
  • [Paper]

✨Self-Evaluation

• "Language Models (Mostly) Know What They Know.", 2022.7

  • Saurav Kadavath, Tom Conerly, Amanda Askell
  • [Paper]

• "SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models.", 2023.3

  • Potsawee Manakul, Adian Liusie, Mark J. F. Gales
  • [Paper]

• "Do Language Models Know When They’re Hallucinating References?", 2023.5

  • Ayush Agrawal, Lester Mackey, Adam Tauman Kalai
  • [Paper]

• "Evaluating Object Hallucination in Large Vision-Language Models.", 2023.5

  • Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang
  • [Paper]

• "Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models.", 2023.5

  • Miaoran Li, Baolin Peng, Zhu Zhang
  • [Paper]

• "LM vs LM: Detecting Factual Errors via Cross Examination.", 2023.5

  • Roi Cohen, May Hamri, Mor Geva
  • [Paper]

• "Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation.", 2023.5

  • Niels Mündler, Jingxuan He, Slobodan Jenko
  • [Paper]

• "A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection.", 2023.10

  • Shiping Yang, Renliang Sun, Xiaojun Wan
  • [Paper]

✨Evidence Retrieval

• "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation.", 2023.5

  • Sewon Min, Kalpesh Krishna, Xinxi Lyu
  • [Paper]

• "Complex Claim Verification with Evidence Retrieved in the Wild.", 2023.5

  • Jifan Chen, Grace Kim, Aniruddh Sriram
  • [Paper]

• "Retrieving Supporting Evidence for LLMs Generated Answers.", 2023.6

  • Siqing Huo, Negar Arabzadeh, Charles L. A. Clarke
  • [Paper]

• "FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios.", 2023.7

  • I-Chun Chern, Steffi Chern, Shiqi Chen
  • [Paper]

🪄 Hallucination Correction

✨Parameter Enhancement

• "Factuality Enhanced Language Models for Open-Ended Text Generation.", 2022.6

  • Nayeon Lee, Wei Ping, Peng Xu
  • [Paper]

• "Contrastive Learning Reduces Hallucination in Conversations.", 2022.12

  • Weiwei Sun, Zhengliang Shi, Shen Gao
  • [Paper]

• "Editing Models with Task Arithmetic.", 2023.2

  • Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman
  • [Paper]

• "Elastic Weight Removal for Faithful and Abstractive Dialogue Generation.", 2023.3

  • Nico Daheim, Nouha Dziri, Mrinmaya Sachan
  • [Paper]

• "HISTALIGN: Improving Context Dependency in Language Generation by Aligning with History.", 2023.5

  • David Wan, Shiyue Zhang, Mohit Bansal
  • [Paper]

• "mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations.", 2023.5

  • Jonas Pfeiffer, Francesco Piccinno, Massimo Nicosia
  • [Paper]

• "Trusting Your Evidence: Hallucinate Less with Context-aware Decoding.", 2023.5

  • Weijia Shi, Xiaochuang Han, Mike Lewis
  • [Paper]

• "PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions.", 2023.5

  • Anthony Chen, Panupong Pasupat, Sameer Singh
  • [Paper]

• "Augmented Large Language Models with Parametric Knowledge Guiding.", 2023.5

  • Ziyang Luo, Can Xu, Pu Zhao, Xiubo Geng
  • [Paper]

• "Inference-Time Intervention: Eliciting Truthful Answers from a Language Model.", 2023.6

  • Kenneth Li, Oam Patel, Fernanda Viégas
  • [Paper]

• "TRAC: Trustworthy Retrieval Augmented Chatbot.", 2023.7

  • Shuo Li, Sangdon Park, Insup Lee
  • [Paper]

• "EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models", 2023.8

  • Peng Wang, Ningyu Zhang, Xin Xie
  • [Paper]

• "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models", 2023.9

  • Yung-Sung Chuang, Yujia Xie, Hongyin Luo
  • [Paper]

✨Post-hoc Attribution and Edit Technology

• "Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding.", 2021.4

  • Nouha Dziri, Andrea Madotto, Osmar Zaïane
  • [Paper]

• "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.", 2022.1

  • Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma
  • [Paper]

• "Teaching language models to support answers with verified quotes.", 2022.3

  • Jacob Menick, Maja Trebacz, Vladimir Mikulik
  • [Paper]

• "ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data.", 2022.5

  • Xiaochuang Han, Yulia Tsvetkov
  • [Paper]

• "Large Language Models are Zero-Shot Reasoners.", 2022.5

  • Takeshi Kojima, Shixiang Shane Gu, Machel Reid
  • [Paper]

• "Rethinking with Retrieval: Faithful Large Language Model Inference.", 2023.1

  • Hangfeng He, Hongming Zhang, Dan Roth
  • [Paper]

• "TRAK: Attributing Model Behavior at Scale.", 2023.3

  • Sung Min Park, Kristian Georgiev, Andrew Ilyas
  • [Paper]

• "Data Portraits: Recording Foundation Model Training Data.", 2023.3

  • Marc Marone, Benjamin Van Durme
  • [Paper]

• "Self-Refine: Iterative Refinement with Self-Feedback.", 2023.3

  • Aman Madaan, Niket Tandon, Prakhar Gupta
  • [Paper]

• "Reflexion: an autonomous agent with dynamic memory and self-reflection.", 2023.3

  • Noah Shinn, Beck Labash, Ashwin Gopinath
  • [Paper]

• "According to ..." Prompting Language Models Improves Quoting from Pre-Training Data.", 2023.5

  • Orion Weller, Marc Marone, Nathaniel Weir
  • [Paper]

• "Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework.", 2023.5

  • Ruochen Zhao, Xingxuan Li, Shafiq Joty
  • [Paper]

• "Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning.", 2023.9

  • Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu
  • [Paper]

• "Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations.", 2023.10

  • Deren Lei, Yaxi Li, Mengya Hu
  • [Paper]

✨Utilizing Programming Languages

• "PAL: Program-aided Language Models.", 2022.11

  • Luyu Gao, Aman Madaan, Shuyan Zhou
  • [Paper]

• "Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks.", 2022.11

  • Wenhu Chen, Xueguang Ma, Xinyi Wang
  • [Paper]

• "Teaching Algorithmic Reasoning via In-context Learning.", 2022.11

  • Hattie Zhou, Azade Nova, Hugo Larochelle
  • [Paper]

• "Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification.", 2023.8

  • Aojun Zhou, Ke Wang, Zimu Lu
  • [Paper]

✨Leverage External Knowledge

• "Improving Language Models by Retrieving from Trillions of Tokens.", 2021.12

  • Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann
  • [Paper]

• "Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions., 2022.12

  • Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot
  • [Paper]

• "When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories.", 2022.12

  • Alex Mallen, Akari Asai, Victor Zhong
  • [Paper]

• "Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback.", 2023.2

  • Baolin Peng, Michel Galley, Pengcheng He
  • [Paper]

• "In-Context Retrieval-Augmented Language Models.", 2023.2

  • Ori Ram, Yoav Levine, Itay Dalmedigos
  • [Paper]

• "cTBL: Augmenting Large Language Models for Conversational Tables.", 2023.3

  • Anirudh S. Sundar, Larry Heck
  • [Paper]

• "GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information.", 2023.4

  • Qiao Jin, Yifan Yang, Qingyu Chen
  • [Paper]

• "Active Retrieval Augmented Generation.", 2023.5

  • Zhengbao Jiang, Frank F. Xu, Luyu Gao
  • [Paper]

• "Chain of Knowledge: A Framework for Grounding Large Language Models with Structured Knowledge Bases.", 2023.5

  • Xingxuan Li, Ruochen Zhao, Yew Ken Chia
  • [Paper]

• "Gorilla: Large Language Model Connected with Massive APIs.", 2023.5

  • Shishir G. Patil, Tianjun Zhang, Xin Wang
  • [Paper]

• "RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit.", 2023.6

  • Jiongnan Liu, Jiajie Jin, Zihan Wang
  • [Paper]

• "User-Controlled Knowledge Fusion in Large Language Models: Balancing Creativity and Hallucination.", 2023.7

  • SChen Zhang
  • [Paper]

• "KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases.", 2023.8

  • Xintao Wang, Qianwen Yang, Yongting Qiu
  • [Paper]

✨Assessment Feedback

• "Learning to summarize with human feedback.", 2020.12

  • Nisan Stiennon, Long Ouyang, Jeffrey Wu
  • [Paper]

• "BRIO: Bringing Order to Abstractive Summarization.", 2022.3

  • Yixin Liu, Pengfei Liu, Dragomir R. Radev
  • [Paper]

• "Language Models (Mostly) Know What They Know.", 2022.7

  • Saurav Kadavath, Tom Conerly, Amanda Askell
  • [Paper]

• "Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback.", 2023.2

  • Baolin Peng, Michel Galley, Pengcheng He
  • [Paper]

• "Chain of Hindsight Aligns Language Models with Feedback.", 2023.2

  • Hao Liu, Carmelo Sferrazza, Pieter Abbeel
  • [Paper]

• "Zero-shot Faithful Factual Error Correction.", 2023.5

  • Kung-Hsiang Huang, Hou Pong Chan, Heng Ji
  • [Paper]

• "CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing.", 2023.5

  • Zhibin Gou, Zhihong Shao, Yeyun Gong
  • [Paper]

• "Album Storytelling with Iterative Story-aware Captioning and Large Language Models.", 2023.5

  • Munan Ning, Yujia Xie, Dongdong Chen
  • [Paper]

• "How Language Model Hallucinations Can Snowball.", 2023.5

  • Muru Zhang, Ofir Press, William Merrill
  • [Paper]

• "Mitigating Language Model Hallucination with Interactive Question-Knowledge Alignment.", 2023.5

  • Shuo Zhang, Liangming Pan, Junzhou Zhao
  • [Paper]

• "Improving Language Models via Plug-and-Play Retrieval Feedback.", 2023.5

  • Wenhao Yu, Zhihan Zhang, Zhenwen Liang
  • [Paper]

• "PaD: Program-aided Distillation Specializes Large Models in Reasoning.", 2023.5

  • Xuekai Zhu, Biqing Qi, Kaiyan Zhang
  • [Paper]

• "Enabling Large Language Models to Generate Text with Citations.", 2023.5

  • Tianyu Gao, Howard Yen, Jiatong Yu
  • [Paper]

• "Do Language Models Know When They’re Hallucinating References?", 2023.5

  • Ayush Agrawal, Lester Mackey, Adam Tauman Kalai
  • [Paper]

• "Improving Factuality of Abstractive Summarization via Contrastive Reward Learning.", 2023.7

  • I-Chun Chern, Zhiruo Wang, Sanjan Das
  • [Paper]

• "Towards Mitigating Hallucination in Large Language Models via Self-Reflection.", 2023.10

  • Ziwei Ji, Tiezheng Yu, Yan Xu
  • [Paper]

✨Mindset Society

• "Hallucinations in Large Multilingual Translation Models.", 2023.3

  • Nuno Miguel Guerreiro, Duarte M. Alves, Jonas Waldendorf
  • [Paper]

• "Improving Factuality and Reasoning in Language Models through Multiagent Debate.", 2023.5

  • Yilun Du, Shuang Li, Antonio Torralba
  • [Paper]

• "Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate.", 2023.5

  • Tian Liang, Zhiwei He, Wenxiang Jiao
  • [Paper]

• "Examining the Inter-Consistency of Large Language Models: An In-depth Analysis via Debate.", 2023.5

  • Kai Xiong, Xiao Ding, Yixin Cao
  • [Paper]

• "LM vs LM: Detecting Factual Errors via Cross Examination.", 2023.5

  • Roi Cohen, May Hamri, Mor Geva
  • [Paper]

• "PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations.", 2023.7

  • Ruosen Li, Teerth Patel, Xinya Du
  • [Paper]

• "Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration.", 2023.7

  • Zhenhailong Wang, Shaoguang Mao, Wenshan Wu
  • [Paper]

🌟 TIPS

If you find this repository useful to your research or work, it is really appreciate to star this repository.