2 papers
cs.CL2024
Cost-Effective Hallucination Detection for LLMs
Simon Valentin, Jinmiao Fu, Gianluca Detommaso +3
Large language models (LLMs) can be prone to hallucinations - generating unreliable outputs that are unfaithful to their inputs, external facts or internally inconsistent. In this…
stat.ML2024
Multicalibration for Confidence Scoring in LLMs
Gianluca Detommaso, Martin Bertran, Riccardo Fogliato +1
This paper proposes the use of "multicalibration" to yield interpretable and reliable confidence scores for outputs generated by large language models (LLMs). Multicalibration asks…