Retrieval-state lock-in causes zero-dispersion errors in 42% of KG-RAG and 59% of dense-retrieval failures; a three-object check rule reaches 91.9% pooled precision at 7.7% coverage.
ClashE- val: Quantifying the tug-of-war between an LLM’s internal prior and external evidence
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
CAREATTACK adapts closed-form parameter editing with graph-based conflict resolution and lightweight anchor repair to promote malicious passages in RAG retrieval while limiting side effects on non-target queries.
A five-step decomposition probe and a new conflict benchmark show that RAG context compliance is measurable, and that accuracy gains from decomposition can transfer across model families even when causal coupling to the reasoning trace does not.
Faithfulness-QA is a 99k-sample dataset created via counterfactual entity substitution on existing QA benchmarks to train and evaluate context-faithful RAG models.
citing papers explorer
-
When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG
Retrieval-state lock-in causes zero-dispersion errors in 42% of KG-RAG and 59% of dense-retrieval failures; a three-object check rule reaches 91.9% pooled precision at 7.7% coverage.
-
Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems
CAREATTACK adapts closed-form parameter editing with graph-based conflict resolution and lightweight anchor repair to promote malicious passages in RAG retrieval while limiting side effects on non-target queries.
-
Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
A five-step decomposition probe and a new conflict benchmark show that RAG context compliance is measurable, and that accuracy gains from decomposition can transfer across model families even when causal coupling to the reasoning trace does not.
-
Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
Faithfulness-QA is a 99k-sample dataset created via counterfactual entity substitution on existing QA benchmarks to train and evaluate context-faithful RAG models.