Year: 2026
Type: conference-paper
Abstract: 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 multiplechoice 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 open-domain and multi-hop QA datasets demonstrate that our method significantly improves reasoning accuracy on complex queries while effectively reducing hallucinations, outperforming strong existing baselines.
Institutions: Queen Mary University of London, Chongqing University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166815110