Cleanse detects hallucinated LLM answers by computing the share of hidden-embedding cosine similarity that falls inside semantic clusters, and it beats several baselines in AUROC across four models and two QA benchmarks.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs
Cleanse detects hallucinated LLM answers by computing the share of hidden-embedding cosine similarity that falls inside semantic clusters, and it beats several baselines in AUROC across four models and two QA benchmarks.