让大模型自己找出关键证据，提升回答准确性。
SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence
- 利用深层注意力分数自动标记上下文中的关键信息
- 在多个问答任务上显著提升模型表现，无需额外训练
- 适合需要高可信度回答的场景，如医疗、法律领域
给大模型提供相关证据可显著提升其回答的准确性。然而，现有研究发现，当上下文包含噪声和无关信息时，大模型往往难以充分理解和利用关键证据，这在真实场景中很常见。为此，我们提出SelfElicit，一种推理阶段的方法，通过自引导显式标注来帮助大模型聚焦关键证据。该方法利用大模型深层注意力分数中蕴含的证据识别能力，自动识别并强调输入上下文中的关键信息，从而提升回答准确性和可解释性，且无需额外训练或迭代提示。我们在多个基于证据的问答任务上验证了该方法对不同大模型家族的一致性显著改进，同时保持计算效率。代码与文档已公开于https://github.com/ZhiningLiu1998/SelfElicit。
原文摘要 · Abstract (English)
Providing Language Models (LMs) with relevant evidence in the context (either via retrieval or user-provided) can significantly improve their ability to provide better-grounded responses. However, recent studies have found that LMs often struggle to fully comprehend and utilize key evidence from the context, especially when it contains noise and irrelevant information, an issue common in real-world scenarios. To address this, we propose SelfElicit, an inference-time approach that helps LMs focus on key contextual evidence through self-guided explicit highlighting. By leveraging the inherent evidence-finding capabilities of LMs using the attention scores of deeper layers, our method automatically identifies and emphasizes key evidence within the input context, facilitating more accurate and grounded responses without additional training or iterative prompting. We demonstrate that SelfElicit brings consistent and significant improvement on multiple evidence-based QA tasks for various LM families while maintaining computational efficiency. Our code and documentation are available at https://github.com/ZhiningLiu1998/SelfElicit.
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。