让大模型学会识别外部知识冲突，自动选择更可靠的来源。
Conflict-Aware Soft Prompting for Retrieval-Augmented Generation
- 用软提示机制训练评估器，判断外部信息可信度。
- 在问答与事实核查任务上平均提升5.0%性能。
- 适合需要高可靠性的智能问答系统使用。
检索增强生成（RAG）通过将外部知识融入大语言模型（LLM）的输入提示来增强其能力。然而，当检索到的上下文与模型参数化知识矛盾时，模型常无法解决外部上下文错误与正确参数知识之间的冲突，即上下文-记忆冲突。为此，我们提出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编码出紧凑的记忆令牌嵌入，并通过有根基/对抗性软提示进行训练，以辨别不可靠上下文并捕捉引导推理向更可靠知识源的信号。大量实验表明，CARE能有效缓解上下文-记忆冲突，在问答与事实核查基准上平均性能提升5.0%，为可信且自适应的RAG系统指明了新方向。
原文摘要 · Abstract (English)
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.
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。