Functional clustering uses self-generated tests to group LLM code by exact output behavior, and abstains when the largest group is too small, trading answer coverage for lower error rates.
Semantic uncertainty: Linguistic invari- ances for uncertainty estimation in natural language generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Eliminating Hallucination-Induced Errors in LLM Code Generation with Functional Clustering
Functional clustering uses self-generated tests to group LLM code by exact output behavior, and abstains when the largest group is too small, trading answer coverage for lower error rates.