{"ID":2850065,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.22710","arxiv_id":"2510.22710","title":"RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability","abstract":"Retrieval-Augmented Generation (RAG) faces a core bottleneck with knowledge-sparse and semantically ambiguous long-tail queries, where retrieval noise distorts reasoning and necessitates costly post-processing. To tackle this, we propose RaCoT (Retrieval-aware Contrastive-of-Thought), a novel framework that shifts contrastive thinking to the pre-retrieval stage. By automatically generating a semantically adjacent yet differently answered contrastive question and extracting a $Δ$-Prompt to capture their key differences, RaCoT guides the model to proactively focus on the ``critical details that determine answer divergence.\" This approach allows it to suppress semantic interference within a single retrieval pass, overcoming the theoretical bottleneck of single-vector queries that struggle to simultaneously encode signals for what to attend to and what to ignore. On six authoritative benchmarks, including PopQA and TriviaQA-unfiltered, RaCoT outperforms strong baselines like RankRAG and Self-RAG by 0.9-2.4 percentage points. It exhibits superior robustness, with a performance drop of only 8.6\\% in adversarial tests, far surpassing the over 15\\% degradation in other methods. Furthermore, its low latency (3.12s) and token overhead (11.54) place it on the accuracy-efficiency Pareto frontier, while ablation studies validate the necessity of each component. Ultimately, RaCoT reframes the RAG paradigm from ``post-hoc context cleaning\" to ``a priori shaping of discriminative reasoning\", offering an efficient and robust path toward reliable AI systems for real-time, resource-constrained deployments.","short_abstract":"Retrieval-Augmented Generation (RAG) faces a core bottleneck with knowledge-sparse and semantically ambiguous long-tail queries, where retrieval noise distorts reasoning and necessitates costly post-processing. To tackle this, we propose RaCoT (Retrieval-aware Contrastive-of-Thought), a novel framework that shifts cont...","url_abs":"https://arxiv.org/abs/2510.22710","url_pdf":"https://arxiv.org/pdf/2510.22710v1","authors":"[\"Kaitong Cai\",\"Jusheng Zhang\",\"Yijia Fan\",\"Jing Yang\",\"Keze Wang\"]","published":"2025-10-26T15:06:44Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"RAG\",\"Large Language Model\"]","has_code":false}