冲突感知的软提示用于检索增强生成
Conflict-Aware Soft Prompting for Retrieval-Augmented Generation
AI总结：
针对RAG中上下文与模型记忆冲突的问题，提出CARE框架，通过上下文评估器与软提示引导推理，在QA和事实验证基准上平均提升5.0%。
摘要：
检索增强生成（RAG）通过将外部知识纳入输入提示来增强大型语言模型（LLM）的能力。然而，当检索到的上下文与LLM的参数化知识相矛盾时，它往往无法解决错误外部上下文与正确参数化知识之间的冲突，即上下文-记忆冲突。为解决此问题，我们引入了冲突感知的检索增强生成（CARE），由上下文评估器和基础LLM组成。上下文评估器从原始上下文令牌中编码紧凑的记忆令牌嵌入。通过基于事实/对抗性软提示，上下文评估器被训练以辨别不可靠的上下文并捕获引导信号，将推理导向更可靠的知识源。大量实验表明，CARE有效缓解了上下文-记忆冲突，在问答和事实验证基准上平均性能提升5.0%，为可信赖和自适应的RAG系统开辟了有前景的方向。
英文摘要：
Retrieval-augmented generation (RAG) enhances the capabilities of large language models (LLMs) by incorporating external knowledge into their input prompts. However, when the retrieved context contradicts the LLM's parametric knowledge, it often fails to resolve the conflict between incorrect external context and correct parametric knowledge, known as context-memory conflict. To tackle this problem, we introduce Conflict-Aware REtrieval-Augmented Generation (CARE), consisting of a context assessor and a base LLM. The context assessor encodes compact memory token embeddings from raw context tokens. Through grounded/adversarial soft prompting, the context assessor is trained to discern unreliable context and capture a guidance signal that directs reasoning toward the more reliable knowledge source. Extensive experiments show that CARE effectively mitigates context-memory conflicts, leading to an average performance gain of 5.0\% on QA and fact-checking benchmarks, establishing a promising direction for trustworthy and adaptive RAG systems.
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。
