UMBRELA relevance judgments made with DeepSeek V3 are close to GPT-4o, and even small models preserve leaderboard rankings although per-document agreement with humans drops.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Does UMBRELA Work on Other LLMs?
UMBRELA relevance judgments made with DeepSeek V3 are close to GPT-4o, and even small models preserve leaderboard rankings although per-document agreement with humans drops.