让大模型逐步验证推理，提升多跳问答准确性
SAFE: An LLM-as-Verifier Framework for Evidence-Grounded Multi-Hop Reasoning
- 将推理拆解为可验证的知识图谱三元组，逐步检查
- 在三个基准上平均准确率提升8.8个百分点
- 适合需要可靠推理过程的严谨问答场景
多跳问答基准常奖励大语言模型（LLMs）的虚假正确性，即通过无效中间推理得到正确答案。我们提出SAFE，一种以大模型为验证器的证据锚定多跳问答框架。不同于生成后仅判断最终答案，SAFE在生成过程中通过比对提供的文本和先前推理轨迹，验证中间步骤。为使该过程可验证，SAFE将推理分解为原子化的、基于证据的单位，以知识图谱（KG）三元组表示。训练时，SAFE在KG约束下验证基准监督数据，并构建可靠的验证器训练数据。推理时，外部验证器检查每一步生成内容，识别无效推理并提供修正反馈，防止错误传播。在三个多跳问答基准上，SAFE平均准确率提升8.8个百分点。结果表明，证据锚定的多跳问答可通过将评估从事后答案判断转向逐步推理验证获益。
原文摘要 · Abstract (English)
Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, where models reach correct answers through invalid intermediate reasoning. We propose SAFE, an LLM-as-verifier framework for evidence-grounded multi-hop QA. Rather than judging only the final answer after generation, SAFE verifies reasoning during generation by checking intermediate steps against the provided passages and previous reasoning trajectory. To make this process checkable, SAFE decomposes reasoning into atomic, evidence-grounded units represented with Knowledge Graph (KG) triples. At train-time, SAFE verifies benchmark supervision under KG-grounded constraints and constructs reliable verifier training data. At inference-time, an external verifier checks each generated step, identifies invalid reasoning, and provides correction feedback before errors propagate. Across three multi-hop QA benchmarks, SAFE improves accuracy by 8.8 pp on average. These results show that evidence-grounded multi-hop QA benefits from shifting LLM-based evaluation from post-hoc answer judgment to stepwise reasoning verification.
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。