AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement

Chenyu Lin, Yilin Wen, Du Su, Hexiang Tan, Fei Sun, Muhan Chen, Chenfu Bao, Zhonghou Lv

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 the J_RPK objective (robust-PK re-evaluation under context) (ablation)Knowledgeable-R1 · ConFiQA MR (TIFE: PK right, context wrong)accuracy: 46.50% -> 75.80% (MC TIFE, with J_PK removed in both)Improved
add the J_PK objective (ablation)Knowledgeable-R1 · ConFiQA PC-MR & NC-MR avgaverage accuracy: 64.42% -> 65.40%Improved
add the global advantage for CK (ablation)Knowledgeable-R1 · ConFiQA PC-MR & NC-MR avgaverage accuracy: 60.95% -> 65.40%Improved
add the local advantage for CK (ablation)Knowledgeable-R1 · ConFiQA PC-MR & NC-MR avgaverage accuracy: 64.69% -> 65.40%Improved
use adaptive beta instead of a fixed beta (ablation)Knowledgeable-R1 · ConFiQA PC-MR & NC-MR avgaverage accuracy: 56.95% -> 65.40%Improved
use adaptive beta instead of best fixed beta (0.01) (ablation)Knowledgeable-R1 · ConFiQA MC-avgMC-avg accuracy: 56.03% -> 56.43%Improved
replace GRPO w/ RAG with Knowledgeable-R1 trainingQwen2.5-7B-Instruct · ConFiQA NC-MREM accuracy: 26.94% -> 43.94%Improved
replace GRPO w/ RAG with Knowledgeable-R1 trainingQwen2.5-7B-Instruct · ConFiQA PC-MR (correct context)EM accuracy: 77.56% -> 75.08%Hurt
replace GRPO w/ RAG with Knowledgeable-R1 trainingQwen2.5-7B-Instruct · ConFiQA SC (self-conflicting)EM accuracy: 75.33% -> 76.33%No clear effect
raise CK objective weight to 1:2:1 (ablation)Knowledgeable-R1 · ConFiQA-MCS1 vs S2 accuracy: S1 75.51% -> 78.04%; S2 37.34% -> 32.73%Mixed
use local+global CK advantage instead of local only (ablation)Knowledgeable-R1 · ConFiQA avg scoreaverage score: 60.95 -> 65.40Improved
train with only 1% bad context (ablation)Knowledgeable-R1 · ConFiQA-MR S2accuracy: GRPO 14.31% -> 17.34%Improved

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