arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.04568cs.CLcs.AI
收藏

面向属性化大语言模型学习细粒度有据引用

Learning Fine-Grained Grounded Citations for Attributed Large Language Models

Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）；Huawei Inc.（华为公司）

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

备注：
Accepted by ACL 2024 Findings
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出训练框架FRONT，通过细粒度支持性引文引导LLM生成有据回复，在ALCE基准上以LLaMA-2-7B实现引用质量平均提升14.21%，超越ChatGPT。

摘要：

尽管大语言模型（LLMs）在信息查询任务上表现优异，但仍存在幻觉问题。属性化大语言模型通过在生成文本中附加行内引用，已显示出缓解幻觉和提高可验证性的潜力。然而，现有方法由于依赖上下文学习，引用质量欠佳。此外，仅引用粗粒度文档标识符的做法使用户难以进行细粒度验证。本文提出FRONT，一个旨在训练大语言模型生成细粒度有据引用的训练框架。通过将模型输出锚定在细粒度支持性引文上，这些引文引导生成有据且一致的回复，不仅提升引用质量，还便于细粒度验证。在ALCE基准上的实验证明了FRONT在生成优质有据回复和高度支持性引用方面的有效性。使用LLaMA-2-7B，该框架显著优于所有基线方法，在所有数据集上的引用质量平均提升14.21%，甚至超越ChatGPT。

英文摘要：

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, have shown 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 citing only coarse document identifiers makes it challenging for users to perform fine-grained verification. In this work, we introduce FRONT, a training framework designed to teach LLMs to generate Fine-Grained Grounded Citations. By grounding model outputs in fine-grained supporting quotes, these quotes guide the generation of grounded and consistent responses, not only improving citation quality but also facilitating fine-grained verification. 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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑