LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912097008353280 |
|---|---|
| author | Tran, Hieu Wang, Junda Ting, Yujan Huang, Weijing Chen, Terrence |
| author_facet | Tran, Hieu Wang, Junda Ting, Yujan Huang, Weijing Chen, Terrence |
| contents | Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, yet they often struggle with maintaining factual accuracy, particularly in knowledge-intensive domains like healthcare. This study introduces LEAF: Learning and Evaluation Augmented by Fact-Checking, a novel approach designed to enhance the factual reliability of LLMs, with a focus on medical question answering (QA). LEAF utilizes a dual strategy to enhance the factual accuracy of responses from models such as Llama 3 70B Instruct and Llama 3 8B Instruct. The first strategy, Fact-Check-Then-RAG, improves Retrieval-Augmented Generation (RAG) by incorporating fact-checking results to guide the retrieval process without updating model parameters. The second strategy, Learning from Fact-Checks via Self-Training, involves supervised fine-tuning (SFT) on fact-checked responses or applying Simple Preference Optimization (SimPO) with fact-checking as a ranking mechanism, both updating LLM parameters from supervision. These findings suggest that integrating fact-checked responses whether through RAG enhancement or self-training enhances the reliability and factual correctness of LLM outputs, offering a promising solution for applications where information accuracy is crucial. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_23526 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models Tran, Hieu Wang, Junda Ting, Yujan Huang, Weijing Chen, Terrence Computation and Language Artificial Intelligence Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, yet they often struggle with maintaining factual accuracy, particularly in knowledge-intensive domains like healthcare. This study introduces LEAF: Learning and Evaluation Augmented by Fact-Checking, a novel approach designed to enhance the factual reliability of LLMs, with a focus on medical question answering (QA). LEAF utilizes a dual strategy to enhance the factual accuracy of responses from models such as Llama 3 70B Instruct and Llama 3 8B Instruct. The first strategy, Fact-Check-Then-RAG, improves Retrieval-Augmented Generation (RAG) by incorporating fact-checking results to guide the retrieval process without updating model parameters. The second strategy, Learning from Fact-Checks via Self-Training, involves supervised fine-tuning (SFT) on fact-checked responses or applying Simple Preference Optimization (SimPO) with fact-checking as a ranking mechanism, both updating LLM parameters from supervision. These findings suggest that integrating fact-checked responses whether through RAG enhancement or self-training enhances the reliability and factual correctness of LLM outputs, offering a promising solution for applications where information accuracy is crucial. |
| title | LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.23526 |