Pith. sign in

REVIEW 4 cited by

Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.14409 v1 pith:DWA23P3W submitted 2024-02-22 cs.CL cs.AIcs.IR

Zhuoran Jin , Pengfei Cao , Yubo Chen , Kang Liu , Xiaojian Jiang , Jiexin Xu , Qiuxia Li , Jun Zhao This is my paper
classification cs.CLcs.AIcs.IR
keywords knowledgeralmsconflictsevidenceinternalmemoryexternalsources
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-augmented language models (RALMs) have demonstrated significant potential in refining and expanding their internal memory by retrieving evidence from external sources. However, RALMs will inevitably encounter knowledge conflicts when integrating their internal memory with external sources. Knowledge conflicts can ensnare RALMs in a tug-of-war between knowledge, limiting their practical applicability. In this paper, we focus on exploring and resolving knowledge conflicts in RALMs. First, we present an evaluation framework for assessing knowledge conflicts across various dimensions. Then, we investigate the behavior and preference of RALMs from the following two perspectives: (1) Conflicts between internal memory and external sources: We find that stronger RALMs emerge with the Dunning-Kruger effect, persistently favoring their faulty internal memory even when correct evidence is provided. Besides, RALMs exhibit an availability bias towards common knowledge; (2) Conflicts between truthful, irrelevant and misleading evidence: We reveal that RALMs follow the principle of majority rule, leaning towards placing trust in evidence that appears more frequently. Moreover, we find that RALMs exhibit confirmation bias, and are more willing to choose evidence that is consistent with their internal memory. To solve the challenge of knowledge conflicts, we propose a method called Conflict-Disentangle Contrastive Decoding (CD2) to better calibrate the model's confidence. Experimental results demonstrate that our CD2 can effectively resolve knowledge conflicts in RALMs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Ten leading VLMs mostly fail to report removed essential object parts as missing, and simulated detector evidence, image tools, longer reasoning, and an easier fine-tune barely improve accuracy.

  2. Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models

    cs.CL 2025-08 conditional novelty 4.0 of 10

    A decoding-time method that steers a large LLM's context-faithfulness continuously by adding a scaled difference of two fine-tuned small proxy models' output distributions.

  3. RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context Divergence

    cs.CL 2025-06 reject novelty 4.0 of 10

    Introduces an entity-context divergence metric and a DPO-based training objective to improve retrieval-augmented generation, with weak empirical validation.

  4. CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation

    cs.CL 2025-06 conditional novelty 4.0 of 10

    CCRS is a zero-shot LLM-as-a-judge framework whose five metrics discriminate between RAG systems on BioASQ with comparable or better power than RAGChecker at lower compute.

Pith tools