paper-with-me

Papers

ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation

2026-05-17 · Chenyu Wang, Yueyuan Li, Yingmin Liu, Yang Shu arxiv

Retrieval-Augmented Generation (RAG) systems implicitly assume mutual consistency among retrieved documents -- an assumption that frequently fails in practice. We present ConflictRAG, a conflict-aware RAG framework that detects, classifies, and resolves knowledge conflicts prior to answer generation. The framework introduces three contributions: (1) a two-stage conflict detection module combining a lightweight embedding-based MLP classifier with selective LLM refinement, reducing API costs by 62% while maintaining 90.8% detection accuracy; (2) an Entropy-TOPSIS framework for data-driven source credibility assessment, improving selection accuracy by 7.1% over manual heuristics; and (3) a Conflict-Aware RAG Score (CARS) for diagnostic evaluation of conflict-handling capabilities. Experiments on three benchmarks against six baselines demonstrate 88.7% conflict-detection F1 and consistent 5.3--6.1% correctness gains over the strongest conflict-aware baseline, with the pipeline transferring effectively across backbone LLMs.

📄 PDF Abstract BibTeX arXiv:2605.17301

Code (0)

등록된 구현이 없습니다.

Tasks

Answer Generation

Similar Papers 제목 키워드 기반

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

2024-02-22 · Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu 외

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 k…

Retrieval

TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphs

2025-11-13 · Shuyi Liu, Yuming Shang, Xi Zhang arxiv

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework for enhancing the capabilities of Large Language Models (LLMs) by integrating retrieval-based methods with generative models. As external knowledge…

Knowledge Graphs

Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint

2024-02-19 · Xiaowei Yuan, Zhao Yang, Yequan Wang, Shengping Liu 외

Large language models internalize enormous parametric knowledge during pre-training. Concurrently, realistic applications necessitate external contextual knowledge to aid models on the underlying tasks. This raises a cru…

Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering

2024-12-18 · Yifan Lu, Yigeng Zhou, Jing Li, Yequan Wang 외

Multi-hop question answering (MHQA) poses a significant challenge for large language models (LLMs) due to the extensive knowledge demands involved. Knowledge editing, which aims to precisely modify the LLMs to incorporat…

graph constructionknowledge editingKnowledge GraphsMulti-hop Question Answering+2

REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment

2026-02-15 · Kai Ye, Xianwei Mao, Sheng Zhou, Zirui Shao 외 arxiv

Knowledge-intensive Visual Question Answering (KI-VQA) frequently suffers from severe knowledge conflicts caused by the inherent limitations of open-domain retrieval. However, existing paradigms face critical limitations…

Visual Question Answering