A SemEval-2025 system combines semantic role labeling, textual entailment, and logit confidence to detect hallucinated spans, but its confidence formula degenerates to one over unit length.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Span-Level Hallucination Detection for LLM-Generated Answers
A SemEval-2025 system combines semantic role labeling, textual entailment, and logit confidence to detect hallucinated spans, but its confidence formula degenerates to one over unit length.