FIELD NOTES TOPIC
quantifying over-trust
1 note, newest first.
When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence
The study presents a framework to quantify and address Derived-Feature Over-Trust (DFOT), which occurs when large language models (LLMs) misuse derived measurements as if they were direct facts. The researchers use…
