paper-with-me

홈 › Papers

Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback

2023-02-24 · Baolin Peng, Michel Galley, Pengcheng He, Hao Cheng, Yujia Xie, Yu Hu, Qiuyuan Huang, Lars Liden, Zhou Yu, Weizhu Chen, Jianfeng Gao

Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical applications remains challenging mainly due to their tendency to generate hallucinations and their inability to use external knowledge. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules. Our system makes the LLM generate responses grounded in external knowledge, e.g., stored in task-specific databases. It also iteratively revises LLM prompts to improve model responses using feedback generated by utility functions, e.g., the factuality score of a LLM-generated response. The effectiveness of LLM-Augmenter is empirically validated on two types of scenarios, task-oriented dialog and open-domain question answering. LLM-Augmenter significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses. We make the source code and models publicly available.

📄 PDF Abstract BibTeX arXiv:2302.12813

Code (0)

등록된 구현이 없습니다.

Tasks

InformativenessOpen-Domain Question AnsweringQuestion Answering

Similar Papers 제목 키워드 기반

Where is Your Evidence: Improving Fact-checking by Justification Modeling

2018-11-01 · WS 2018 11 · Tariq Alhindi, Savvas Petridis, Smar Muresan, a

Fact-checking is a journalistic practice that compares a claim made publicly against trusted sources of facts. Wang (2017) introduced a large dataset of validated claims from the POLITIFACT.com website (LIAR dataset), en…

Argument MiningBIG-bench Machine LearningBinary ClassificationEmotion Recognition+2

Facts Do Care About Your Language: Assessing Answer Quality of Multilingual LLMs

2025-06-03 · Yuval Kansal, Shmuel Berman, Lydia Liu

Factuality is a necessary precursor to useful educational tools. As adoption of Large Language Models (LLMs) in education continues of grow, ensuring correctness in all settings is paramount. Despite their strong English…

Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification

2024-06-28 · Anisha Gunjal, Greg Durrett

Automatic factuality verification of large language model (LLM) generations is becoming more and more widely used to combat hallucinations. A major point of tension in the literature is the granularity of this fact-check…

Fact CheckingFact VerificationLanguage ModelingLanguage Modelling+1

CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval

2026-01-23 · Akshith Reddy Putta, Jacob Devasier, Chengkai Li arxiv

Automated Fact-Checking has largely focused on verifying general knowledge against static corpora, overlooking high-stakes domains like law where truth is evolving and technically complex. We introduce CaseFacts, a bench…

Semantic SimilarityGeneral KnowledgeFact Verification

Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation

2025-12-18 · Musarrat Zeba, Abdullah Al Mamun, Kishoar Jahan Tithee, Debopom Sutradhar 외 arxiv

In healthcare, it is essential for any Large Language Model (LLM)-generated output to be reliable and accurate, particularly in cases involving decision-making and patient safety. However, the outputs are often unreliabl…