Research map / Large language models / Retrieval and knowledge
From Extraction to Deduction: Resolving Functional Misalignment in RAG via a Collaborative Critic-Reasoner Framework
Yufei Chen, Yao Wang, Haibin Zhang, Hualin zhou, Tao Gu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add DPO stage after SFT (ablation) | Critic-Reasoner (Llama3.1-8B) · IR-QA | answer accuracy: 52.92% -> 70.58% | Improved |
| add SFT stage before DPO (ablation) | Critic-Reasoner (Llama3.1-8B) · IR-QA | answer accuracy: 55.58% -> 70.58% | Improved |
| add SFT and DPO together vs either alone (ablation) | Critic-Reasoner (Llama3.1-8B) · dCR (CR-QA) | answer accuracy: 57.17% -> 80.14% | Improved |
| add reasoning data to SFT mixture (ablation) | Critic-Reasoner (Llama3.1-8B) · IR-QA | answer accuracy: 59.90% -> 70.58% | Improved |
| add reasoning data to SFT mixture (ablation) | Critic-Reasoner (Llama3.1-8B) · II-MC | answer accuracy: 30.67% -> 74.00% | Improved |
| add [MASK] data to SFT mixture (ablation) | Critic-Reasoner (Llama3.1-8B) · 2Wiki | answer accuracy: 13.75% -> 67.25% | Improved |
| add [MASK] data to SFT mixture (ablation) | Critic-Reasoner (Llama3.1-8B) · IR-NQ | answer accuracy: 31.05% -> 63.55% | Improved |
| add [MASK] data to SFT mixture (ablation) | Critic-Reasoner (Llama3.1-8B) · IM-QA | answer accuracy: 51.08% -> 67.58% | Mixed |
| use Critic-Reasoner instead of standard RAG prompting | Llama3.1-8B · IR-QA | answer accuracy: 38.00% -> 70.58% | Improved |
| use Critic-Reasoner instead of standard RAG prompting | Llama3.1-8B · II-MC | answer accuracy: 16.08% -> 74.00% | Improved |
| use Critic-Reasoner instead of standard RAG prompting | Llama3.1-8B · CR-QA (correct context) | answer accuracy: 78.32% -> 80.14% | No clear effect |
| use Critic-Reasoner on smaller 3B model | Qwen2.5-3B · IR-NQ | answer accuracy: 64.35% -> 60.85% | Hurt |
Closest papers by meaning
- Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization (NeurIPS 2025 · similarity 0.91)
- Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals (NeurIPS 2025 · similarity 0.88)
- RAGGED: Towards Informed Design of Scalable and Stable RAG Systems (ICML 2025 · similarity 0.88)
- Improving Consistency in Retrieval Augmented Systems With Group Similarity Rewards (NeurIPS 2026 · similarity 0.88)
- Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting (ICLR 2025 · similarity 0.87)
- SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG (NeurIPS 2025 · similarity 0.87)
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.
