Activation patching reveals that citation decisions in Llama-3.1-8B RAG are implemented by a distributed attributional ensemble of heads and layers; targeted interventions fix most missed and spurious citations on PopQA.
Creating trustworthy llms: Dealing with hallucinations in healthcare ai
5 Pith papers cite this work, alongside 19 external citations. Polarity classification is still indexing.
5
Pith papers citing it
19
external citations · external index
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Evaluation of 6233 MedGPTs finds 25-30% with low factual accuracy, 33.6-54.3% violating operational thresholds, and 57% of action-enabled models lacking privacy disclosures.
Uncertainty-aware fine-tuning with a decision-theory-based loss produces better-calibrated uncertainty estimates than standard training on free-form QA tasks.
FullCite introduces three strategies for structured inline citation generation in QA and finds LLMs identify relevant documents well but struggle with precise evidence spans on ASQA, BioASQ, and ExpertQA.
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
citing papers explorer
-
How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
Activation patching reveals that citation decisions in Llama-3.1-8B RAG are implemented by a distributed attributional ensemble of heads and layers; targeted interventions fix most missed and spurious citations on PopQA.
-
Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models
Evaluation of 6233 MedGPTs finds 25-30% with low factual accuracy, 33.6-54.3% violating operational thresholds, and 57% of action-enabled models lacking privacy disclosures.
-
Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning
Uncertainty-aware fine-tuning with a decision-theory-based loss produces better-calibrated uncertainty estimates than standard training on free-form QA tasks.
-
Explicit Evidence Grounding via Structured Inline Citation Generation
FullCite introduces three strategies for structured inline citation generation in QA and finds LLMs identify relevant documents well but struggle with precise evidence spans on ASQA, BioASQ, and ExpertQA.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.