RAG models exhibit a monitoring-control gap: they acknowledge epistemic conflicts in accumulating documents yet fail to constrain unsafe recommendations, with single-turn tests overestimating safety.
Rich knowledge sources bring complex knowledge conflicts: Recalibrating models to reflect conflicting evidence
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
The work identifies a small set of attention heads in VLMs that mediate conflicts between parametric knowledge and visual input, and shows that intervening on them steers model behavior while attention patterns provide precise image-region attribution.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
citing papers explorer
-
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs
RAG models exhibit a monitoring-control gap: they acknowledge epistemic conflicts in accumulating documents yet fail to constrain unsafe recommendations, with single-turn tests overestimating safety.
-
When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models
The work identifies a small set of attention heads in VLMs that mediate conflicts between parametric knowledge and visual input, and shows that intervening on them steers model behavior while attention patterns provide precise image-region attribution.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.