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.
Pencils down! automatic rubric-based evaluation of retrieve/generate systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 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.