LLM agents lose confidence under noisy retrieval
Even open‑weight retrieval agents keep shouting answers while the evidence they cite falls apart, exposing a systematic over‑confidence that survives obvious credibility warnings. The phenomenon only becomes visible when source documents are deliberately corrupted at scale, something standard bench…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-17 06:00 · DEV Community — Machine Learning
LLM agents lose confidence under noisy retrieval