Across five LLMs and ten no-consensus datasets, neutrality drops sharply when models act as pairwise judges, pointwise judges, or debaters compared to when they generate answers with an explicit neutral option.
In The Thirty-eighth Annual Conference on Neural Information Processing Systems
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
-
Arbiters of Ambivalence: Challenges of Using LLMs in No-Consensus Tasks
Across five LLMs and ten no-consensus datasets, neutrality drops sharply when models act as pairwise judges, pointwise judges, or debaters compared to when they generate answers with an explicit neutral option.