Improving Factual Consistency of News Summarization by Contrastive Preference Optimization

Huawen Feng, Yan Fan, Xiong Liu, Ting-En Lin, Zekun Yao, Yuchuan Wu, Fei Huang, Yongbin Li, Qianli Ma


Abstract
Despite the recent progress in news summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known as “hallucinations” in text generation. Unlike previous small models (e.g., BART, T5), current LLMs make fewer silly mistakes but more sophisticated ones, such as imposing cause and effect, adding false details, overgeneralizing, etc. These hallucinations are challenging to detect through traditional methods, which poses great challenges for improving the factual consistency of text summarization. In this paper, we propose Contrastive Preference Optimization (CPO) to disentangle the LLMs’ propensities to generate faithful and fake content. Furthermore, we adopt a probing-based specific training method to improve their capacity of distinguishing two types of propensities. In this way, LLMs can execute the instructions more accurately and have enhanced perception of hallucinations. Experimental results show that CPO significantly improves the reliability of summarization based on LLMs.
Anthology ID:
2024.findings-emnlp.648
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11084–11100
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.648/
DOI:
10.18653/v1/2024.findings-emnlp.648
Bibkey:
Cite (ACL):
Huawen Feng, Yan Fan, Xiong Liu, Ting-En Lin, Zekun Yao, Yuchuan Wu, Fei Huang, Yongbin Li, and Qianli Ma. 2024. Improving Factual Consistency of News Summarization by Contrastive Preference Optimization. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11084–11100, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Improving Factual Consistency of News Summarization by Contrastive Preference Optimization (Feng et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.648.pdf