AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Counterfactual Reasoning for Retrieval-Augmented Generation

Huaiyu Qin, Chunyu Wei, Yueguo Chen, Yunhai Wang

ICLR 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation

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 causal verification (causal discrimination score) (ablation)CF-RAG · HotpotQAexact match (%): 73.19 -> 88.58Improved
add causal verification (ablation)CF-RAG · PopQAexact match (%): 63.47 -> 73.57Improved
add counterfactual exploration (ablation)CF-RAG · HotpotQAexact match (%): 78.52 -> 88.58Improved
add counterfactual exploration (ablation)CF-RAG · PopQAexact match (%): 69.03 -> 73.57Improved
add evidence division (stratified parallel drafts) (ablation)CF-RAG · HotpotQAexact match (%): 84.29 -> 88.58Improved
add evidence division (ablation)CF-RAG · PopQAexact match (%): 67.29 -> 73.57Improved
use balanced causal weight lambda=0.4 instead of 0 or 1 (ablation)CF-RAG · HotpotQAexact match (%): 84.00 / 80.00 -> 88.58Improved
increase number of parallel drafts to M=3 from M=1 (ablation)CF-RAG · HotpotQAexact match (%): 82.23 -> 88.58Improved
increase counterfactual queries beyond N=3 (ablation)CF-RAG · HotpotQAexact match (%): 88.58 -> 86.29 (N=5)Hurt
use CF-RAG instead of Speculative-RAG under 16 adversarial distractors (ablation)Speculative-RAG · HotpotQAexact match (%): 20.64 -> 60.57Improved
use CF-RAG (Llama-3-8B) instead of best baseline (ablation)Speculative-RAG · HotpotQAexact match (%): 49.00 -> 88.58Improved
use CF-RAG instead of Self-CRAG / Speculative-RAGbest baseline · PubHealthexact match (%): 76.60 -> 83.36Improved

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