Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.
Axiomatic attribution for deep networks,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Supervised ML models including SVC and BERT achieve 100% F1 on binary malicious/benign MCP tool detection and up to 90.56% on multiclass attack typing, outperforming rule-based baselines.
citing papers explorer
-
Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.
-
Machine Learning-Based Detection of MCP Attacks
Supervised ML models including SVC and BERT achieve 100% F1 on binary malicious/benign MCP tool detection and up to 90.56% on multiclass attack typing, outperforming rule-based baselines.