On frozen candidate pools, constraining an LLM judge with an evidence-certificate gate is worth more than the judge is; unconstrained, the same judge can be worse than majority vote.
Factscore: Fine-grained atomic evaluation of factual precision in long form text generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When the Judge Should Not Decide: Evidence-Locked, Non-Compensatory Selection Bounds LLM-Judge Failure in Reasoning Pipelines
On frozen candidate pools, constraining an LLM judge with an evidence-certificate gate is worth more than the judge is; unconstrained, the same judge can be worse than majority vote.