Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Chenyu, Wen, Yilin, Su, Du, Tan, Hexiang, Sun, Fei, Chen, Muhan, Bao, Chenfu, Lyu, Zhonghou
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910032162979840
author Lin, Chenyu
Wen, Yilin
Su, Du
Tan, Hexiang
Sun, Fei
Chen, Muhan
Bao, Chenfu
Lyu, Zhonghou
author_facet Lin, Chenyu
Wen, Yilin
Su, Du
Tan, Hexiang
Sun, Fei
Chen, Muhan
Bao, Chenfu
Lyu, Zhonghou
contents Retrieval-augmented generation (RAG) improves performance on knowledge-intensive tasks but can be derailed by wrong, irrelevant, or conflicting retrieved text, causing models to rely on inaccurate evidence and cascade errors. We propose Knowledgeable-R1, a reinforcement-learning framework that explicitly trains large language models to use parametric knowledge (PK) to resist contextual interference while still exploiting external context when it is reliably helpful. Knowledgeable-R1 introduces a joint sampling scheme that generates paired responses with and without retrieval, and learns both local advantages (within each decoding regime) and global advantages under the same input to quantify when to ignore misleading context versus adopt it. We employ an asymmetric advantage transformation that amplifies exploratory behaviors toward parametric knowledge. Experiments show that Knowledgeable-R1 significantly improves robustness and reasoning accuracy in knowledge conflict scenarios and general RAG scenarios, outperforming SOTA baselines by +22.89% in counterfactual scenarios, and without degradation when the retrieved context is fully accurate.Our code are available at https://github.com/lcy80366872/knowledgeable-R1.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05154
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement
Lin, Chenyu
Wen, Yilin
Su, Du
Tan, Hexiang
Sun, Fei
Chen, Muhan
Bao, Chenfu
Lyu, Zhonghou
Computation and Language
Artificial Intelligence
Information Retrieval
Retrieval-augmented generation (RAG) improves performance on knowledge-intensive tasks but can be derailed by wrong, irrelevant, or conflicting retrieved text, causing models to rely on inaccurate evidence and cascade errors. We propose Knowledgeable-R1, a reinforcement-learning framework that explicitly trains large language models to use parametric knowledge (PK) to resist contextual interference while still exploiting external context when it is reliably helpful. Knowledgeable-R1 introduces a joint sampling scheme that generates paired responses with and without retrieval, and learns both local advantages (within each decoding regime) and global advantages under the same input to quantify when to ignore misleading context versus adopt it. We employ an asymmetric advantage transformation that amplifies exploratory behaviors toward parametric knowledge. Experiments show that Knowledgeable-R1 significantly improves robustness and reasoning accuracy in knowledge conflict scenarios and general RAG scenarios, outperforming SOTA baselines by +22.89% in counterfactual scenarios, and without degradation when the retrieved context is fully accurate.Our code are available at https://github.com/lcy80366872/knowledgeable-R1.
title Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2506.05154