AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation

Hua Ye, Siyuan Chen, Ziqi Zhong, Canran Xiao, Haoliang Zhang, Yuhan Wu, Fei Shen

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 5 citations (OpenAlex)

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 TCR conflict-aware soft prompt over plain promptingLlama-3-8B RAG · Wikidata-Conflict-5KF1: 71.2 -> 84.3Improved
add TCRLlama-3-8B RAG · ConflictTQAKGRR: 42.4 -> 69.2Improved
add TCRLlama-3-8B RAG · ConflictTQAMCOR: 19.5 -> 61.9Mixed
add TCRLlama-3-8B RAG · 30% distractor injectionEM drop: 18.4 -> 7.2Improved
combine TCR with RAATTCR · 30% distractor injectionEM drop: 7.2 -> 6.1Improved
add contrastive decoding CD2 to TCRTCR · Wikidata-Conflict-5KAUROC: 0.901 -> 0.905No clear effect
add TCR over Astute RAG on single-document NQRAG pipeline · Natural Questions (single top-1 page)accuracy (%): 51.2 -> 54.8Improved
add self-answerability signal (ablation)TCR · ConflictTQA/PQA ablationMCOR/KGRR: removing SA drops ~18/26 ppImproved
use SNR-based dynamic weighting instead of a fixed scalar (ablation)TCR · ConflictTQA/PQA ablationMCOR/KGRR: fixed degrades 17/20 ppImproved
add signal integration (soft-prompt fusion) (ablation)TCR · ConflictTQA/PQA ablationMCOR/KGRR: removing SI collapses 55/53 ppImproved
higher self-answerability bin (>0.7 vs <0.3)TCR · flip rate analysisflip rate: 41.3% -> 4.7%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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