Tag: AI auditing
Browse our exclusive articles!
Participatory Provenance: Auditing AI Public Consultations
Discover how participatory provenance enhances AI auditing to ensure accurate, inclusive public consultation summaries and improve policy transparency.
ASMR-Bench: Detecting Sabotage in ML Research Code
ASMR-Bench benchmarks sabotage detection in ML research, helping improve auditing techniques for AI-generated scientific results.
Detecting AI Safety Violations with Meerkat Method
Discover how Meerkat improves detecting rare AI safety violations across agent traces, enhancing auditing beyond traditional methods.
LatentAudit: Real-Time Faithfulness Monitoring for RAG AI
LatentAudit enables real-time, verifiable faithfulness monitoring for retrieval-augmented generation AI, boosting reliability and reducing hallucinations.
Enhancing LLM Honesty Detection with Steering Vectors
Discover how steering vectors improve honesty detection in LLM-judges, boosting reliability and reducing manipulation in AI-generated responses.