提升大模型回答的可追溯性，让每句话都有据可查。
Enhancing Answer Attribution for Faithful Text Generation with Large Language Models
- 将回答拆解为独立且上下文相关的语义片段，增强可追踪性。
- 在多个数据集上验证，证据召回率显著提升。
- 适合关注大模型可信度与可解释性的研究者与开发者。
近年来，大型语言模型（LLMs）的普及改变了用户与基于AI的对话系统互动的方式。提高生成答案的可信度，关键在于能够将回答中的每个主张追溯到支持它的相关来源，这一过程称为答案归属（answer attribution）。尽管已有研究探索该任务，但仍存在挑战。本文首先通过案例研究分析现有归属方法在回答分割与证据检索子任务上的表现，发现其局限性。基于此，我们提出新方法，生成更独立、更具上下文信息的主张片段，以改善检索与归属效果。实验表明，新方法有效提升了各组件性能。最后，我们讨论了未来方向。
原文摘要 · Abstract (English)
The increasing popularity of Large Language Models (LLMs) in recent years has changed the way users interact with and pose questions to AI-based conversational systems. An essential aspect for increasing the trustworthiness of generated LLM answers is the ability to trace the individual claims from responses back to relevant sources that support them, the process known as answer attribution. While recent work has started exploring the task of answer attribution in LLMs, some challenges still remain. In this work, we first perform a case study analyzing the effectiveness of existing answer attribution methods, with a focus on subtasks of answer segmentation and evidence retrieval. Based on the observed shortcomings, we propose new methods for producing more independent and contextualized claims for better retrieval and attribution. The new methods are evaluated and shown to improve the performance of answer attribution components. We end with a discussion and outline of future directions for the task.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。