Papers
arxiv:2410.01691

FactAlign: Long-form Factuality Alignment of Large Language Models

Published on Oct 2
· Submitted by chaoweihuang on Oct 3
Authors:

Abstract

Large language models have demonstrated significant potential as the next-generation information access engines. However, their reliability is hindered by issues of hallucination and generating non-factual content. This is particularly problematic in long-form responses, where assessing and ensuring factual accuracy is complex. In this paper, we address this gap by proposing FactAlign, a novel alignment framework designed to enhance the factuality of LLMs' long-form responses while maintaining their helpfulness. We introduce fKTO, a fine-grained, sentence-level alignment algorithm that extends the Kahneman-Tversky Optimization (KTO) alignment method. Leveraging recent advances in automatic factuality evaluation, FactAlign utilizes fine-grained factuality assessments to guide the alignment process. Our experiments on open-domain prompts and information-seeking questions demonstrate that FactAlign significantly improves the factual accuracy of LLM responses while also improving their helpfulness. Further analyses identify that FactAlign is capable of training LLMs to provide more information without losing factual precision, thus improving the factual F1 score. Our source code, datasets, and trained models are publicly available at https://github.com/MiuLab/FactAlign

Community

Paper author Paper submitter

Our paper "FactAlign: Long-form Factuality Alignment of Large Language Models" has been accepted to EMNLP 2024 Findings!

FactAlign is a alignment framework designed to enhance the factuality of LLMs' long-form responses. FactAlign leverages recent advances in automatic factuality assessment to guide the alignment process. Additionally, we introduce fKTO, a fine-grained, sentence-level alignment algorithm that extends the Kahneman-Tversky Optimization (KTO) alignment method.

FactAlign significantly improves the factual accuracy of LLM responses on benchmarks such as LongFact and FactScore.

Paper: https://arxiv.org/abs/2410.01691
Code: https://github.com/MiuLab/FactAlign/

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 3

Datasets citing this paper 3

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2410.01691 in a Space README.md to link it from this page.

Collections including this paper 2