Learning Fine-Grained Grounded Citations for Attributed Large Language Models

Lei Huang, Xiaocheng Feng, Weitao Ma, Yuxuan Gu, Weihong Zhong, Xiachong Feng, Weijiang Yu, Weihua Peng, Duyu Tang, Dandan Tu, Bing Qin


Abstract
Despite the impressive performance on information-seeking tasks, large language models (LLMs) still struggle with hallucinations. Attributed LLMs, which augment generated text with in-line citations, demonstrate potential in mitigating hallucinations and improving verifiability. However, current approaches suffer from suboptimal citation quality due to their reliance on in-context learning. Furthermore, the practice of merely citing document identifiers complicates the process for users to pinpoint specific supporting evidence. In this work, we introduce FRONT, a training framework that teaches LLMs to generate Fine-grained grounded citations. By initially grounding fine-grained supporting quotes, which then guide the generation process, these quotes not only provide supervision signals to improve citation quality but also serve as fine-grained attributions. Experiments on the ALCE benchmark demonstrate the efficacy of FRONT in generating superior grounded responses and highly supportive citations. With LLaMA-2-7B, the framework significantly outperforms all the baselines, achieving an average of 14.21% improvement in citation quality across all datasets, even surpassing ChatGPT.
Anthology ID:
2024.findings-acl.838
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14095–14113
Language:
URL:
https://aclanthology.org/2024.findings-acl.838
DOI:
10.18653/v1/2024.findings-acl.838
Bibkey:
Cite (ACL):
Lei Huang, Xiaocheng Feng, Weitao Ma, Yuxuan Gu, Weihong Zhong, Xiachong Feng, Weijiang Yu, Weihua Peng, Duyu Tang, Dandan Tu, and Bing Qin. 2024. Learning Fine-Grained Grounded Citations for Attributed Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 14095–14113, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Learning Fine-Grained Grounded Citations for Attributed Large Language Models (Huang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.838.pdf