AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability

Kaitong Cai, Jusheng Zhang, Yijia Fan, Jing Yang, Keze Wang

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Retrieval-augmented reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add contrast prompting (ablation)RaCoT · PopQAaccuracy: 55.1 -> 59.9Improved
add contrast prompting (ablation)RaCoT · TriviaQA-unfilteredaccuracy: 69.6 -> 73.8Improved
add post-retrieval ranking (ablation)RaCoT · PopQAaccuracy: 57.9 -> 59.9Improved
add similarity filtering for contrast question (ablation)RaCoT · TriviaQA-unfilteredaccuracy: 72.5 -> 73.8Improved
use weaker teacher (GPT-4o-mini) (ablation)RaCoT · PopQAaccuracy: 59.9 -> 58.5No clear effect
use RaCoT instead of RankRAGQwen2.5-7B · PopQAaccuracy: 66.4 -> 68.3Improved
use RaCoT instead of RankRAGLLaMA3-8B · PopQAaccuracy: 58.5 -> 59.9Improved
use RaCoT instead of RankRAGQwen2.5-7B · OpenBookQAaccuracy: 87.5 -> 88.2No clear effect
distractor injectionRaCoT · PopQA and ARC-Challengeaccuracy drop: drop of 8.6% vs 16.5% RankRAG, 15.3% IterDRAGImproved
distractor injectionRaCoT · PopQA (retrieval distractors)accuracy drop: -8.7% vs -19.6% for Self-RAG/RQ-RAGImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy