自校正RAG：通过MMKP上下文选择和NLI引导的MCTS增强忠实性
Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
AI总结：
本研究提出Self-Correcting RAG框架，通过MMKP上下文选择和NLI引导的MCTS机制，提升复杂推理任务中的准确性和减少幻觉。
摘要：
检索增强生成（RAG）显著扩展了大语言模型的知识边界。然而，处理复杂推理任务时仍面临两个主要挑战：低上下文利用率和频繁的幻觉。为了解决这些问题，我们提出了Self-Correcting RAG，一个统一的框架，将检索和生成重新表述为约束优化和路径规划。在输入侧，我们超越传统的贪心检索，并首次将上下文选择形式化为多维多选背包问题（MMKP），从而在严格令牌预算下最大化信息密度并去除冗余。在输出侧，我们引入了自然语言推理（NLI）引导的蒙特卡洛树搜索（MCTS）机制，利用测试时计算动态探索推理轨迹并验证生成答案的忠实性。在六个多跳问答和事实核查数据集上的实验表明，我们的方法在复杂查询上显著提高了推理准确性，同时有效减少了幻觉，优于现有强大的基线方法。我们的代码可在https://github.com/xjiacs/Self-Correcting-RAG获得。
英文摘要：
Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges when handling complex reasoning tasks: low context utilization and frequent hallucinations. To address these issues, we propose Self-Correcting RAG, a unified framework that reformulates retrieval and generation as constrained optimization and path planning. On the input side, we move beyond traditional greedy retrieval and, for the first time, formalize context selection as a multi-dimensional multiple-choice knapsack problem (MMKP), thereby maximizing information density and removing redundancy under a strict token budget. On the output side, we introduce a natural language inference (NLI)-guided Monte Carlo Tree Search (MCTS) mechanism, which leverages test-time compute to dynamically explore reasoning trajectories and validate the faithfulness of generated answers. Experiments on six multi-hop question answering and fact-checking datasets demonstrate that our method significantly improves reasoning accuracy on complex queries while effectively reducing hallucinations, outperforming strong existing baselines.Our code is available at https://github.com/xjiacs/Self-Correcting-RAG .
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。
