Clearing the FoG: Training KG Agents to Retrieve the Evidence Behind Their Answers· 清除 FoG：训练知识图谱代理检索答案背后的证据
Large language models (LLMs) can answer many factual questions correctly, but a correct answer is not necessarily a supported one. For an LLM agent, a knowledge graph (KG) plays two roles: as a source of answers, it supplies facts that the model lacks; as a source of evidence, it supplies the supporting triples that make an answer traceable and auditable. However, existing KG agents treat the KG only as a source of answers: their training data carries answers but not evidence, and their training rewards check the answer but not the retrieved evidence, so agents often answer correctly without retrieving the supporting triples. We propose FoG, a framework that trains KG agents to retrieve the evidence behind their answers. FoG consists of evidence-grounded synthesis, a KG interaction agent,
训练知识图谱代理不仅能正确回答问题，还能追溯答案的证据。
- 核心方法
- 提出 FoG 框架，通过证据支持的合成和知识图谱交互代理，训练模型不仅关注答案正确性，还重视检索支持答案的证据。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 现有知识图谱代理虽然能正确回答问题，但往往未能提供支持答案的证据。
- 关键实验
- 未提供
- 主要贡献
- 首次提出了一种专门训练知识图谱代理同时检索答案和证据的方法，提高了模型的可追踪性和可审查性。
- 意义与局限
- 该研究使知识图谱代理的回答更加可靠和透明，但可能需要更多实验验证其有效性和泛化能力。