让大模型主动发现并纠正输入中的事实错误，提升可靠性。
From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations
- 三阶段框架：先检测错误，再多角度思考修正策略，最后纠正误解。
- 在多个数据集上显著提升准确率和纠错能力，跨模型效果稳定。
- 适合关注大模型鲁棒性与可信度的研究者和开发者。
大型语言模型在用户输入包含误导性前提时，常产生自信但事实错误的回答，我们将其归因于输入中的事实扰动。现有缓解幻觉的方法通常假设输入可靠，忽视了事实错误如何主动误导模型推理。为此，我们提出 DEDUCE，一种三阶段框架，使大模型从被动响应转为主动纠错。DEDUCE 包括：(1) 通过细粒度事实提取与验证检测错误；(2) 通过多视角反思制定修正策略；(3) 纠正误解并输出可靠答案。我们还构建了 MisFactQA 数据集，包含不同程度的事实错误，并提出新评估指标。在 TruthfulQA、FalseQA 及我们的 MisFactQA 基准上实验表明，DEDUCE 显著提升准确率与纠错能力。在 Qwen、LLaMA 与 Gemma 系列模型上均取得一致增益，验证其有效性与可扩展性。
原文摘要 · Abstract (English)
Large language models (LLMs) frequently produce confident yet factually incorrect responses when user inputs contain misleading premises, a phenomenon we attribute to fact perturbations in the input. Existing approaches to hallucination mitigation typically assume reliable user inputs, overlooking how such factual errors can actively mislead model reasoning. To address this vulnerability, we propose DEDUCE, a three-stage framework that transforms LLMs from passive responders into proactive error correctors. DEDUCE operates in three stages: (1) detect errors through fine-grained fact extraction and verification; (2) devise correction strategies via multi perspective deliberation; and (3) correct misconceptions while delivering reliable answers. We also present MisFactQA, a dataset containing factual errors of varying degrees, and propose new metrics for evaluating model robustness. Experiments on TruthfulQA, FalseQA, and our MisFactQA benchmark demonstrate that DEDUCE significantly improves both accuracy and error correction capability. Consistent gains across Qwen, LLaMA, and Gemma families confirm its effectiveness and scalability.
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。