MADISSE assigns LLM evaluators random initial stances (faithful or unfaithful), has them debate in rounds, and adjudicates, improving summary faithfulness evaluation accuracy while introducing an annotated 'ambiguity' dimension.
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
-
Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation
MADISSE assigns LLM evaluators random initial stances (faithful or unfaithful), has them debate in rounds, and adjudicates, improving summary faithfulness evaluation accuracy while introducing an annotated 'ambiguity' dimension.