EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
Resolving knowledge conflicts in large language models
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
background 2polarities
background 2representative citing papers
SHIFT reformulates neuron editing as learnable gate modulation on under 0.01% parameters to let LLMs adaptively balance contextual and parametric knowledge during RAG generation.
MACR adaptively assesses LLM confidence via semantic entropy then applies inductive multi-agent reasoning with rule-induction, conflict-analysis, and resolution agents to handle unreliable parametric and contextual knowledge.
LLMs prefer document assertions over user assertions, are impressionable to external information, and gain better discrimination after fine-tuning on diverse source-interaction data.
Caesar improves creative synthesis by 13-23% over prior deep research agents by using context-aware web traversal to build a knowledge graph and adversarial refinement to seek novel perspectives.
ConflictRAG introduces a conflict-aware RAG pipeline with two-stage detection (MLP + selective LLM), Entropy-TOPSIS credibility assessment, and a new CARS metric, reporting 88.7% F1 and 5.3-6.1% gains on benchmarks.
DCRD uses attention-map analysis to detect context-memory conflicts in LLMs and conditionally applies either greedy or fidelity-based dynamic decoding, achieving SOTA results on QA tasks across four models and six datasets.
CRVA-TGRAG combines parent-document segmentation, ensemble retrieval, and teacher-guided fine-tuning to mitigate knowledge conflicts and improve accuracy in LLM-based CVE vulnerability analysis.
citing papers explorer
-
SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation
SHIFT reformulates neuron editing as learnable gate modulation on under 0.01% parameters to let LLMs adaptively balance contextual and parametric knowledge during RAG generation.
-
How Large Language Models Balance Internal Knowledge with User and Document Assertions
LLMs prefer document assertions over user assertions, are impressionable to external information, and gain better discrimination after fine-tuning on diverse source-interaction data.
-
ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation
ConflictRAG introduces a conflict-aware RAG pipeline with two-stage detection (MLP + selective LLM), Entropy-TOPSIS credibility assessment, and a new CARS metric, reporting 88.7% F1 and 5.3-6.1% gains on benchmarks.
-
Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
DCRD uses attention-map analysis to detect context-memory conflicts in LLMs and conditionally applies either greedy or fidelity-based dynamic decoding, achieving SOTA results on QA tasks across four models and six datasets.
-
Tug-of-War within A Decade: Conflict Resolution in Vulnerability Analysis via Teacher-Guided Retrieval-Augmented Generations
CRVA-TGRAG combines parent-document segmentation, ensemble retrieval, and teacher-guided fine-tuning to mitigate knowledge conflicts and improve accuracy in LLM-based CVE vulnerability analysis.