Answer matching with recent language models aligns with human grading at near-inter-annotator levels, substantially outperforming multiple-choice evaluation and LLM-as-judge without reference answers.
" " # The response can have more information than the ,→ ground− t r u t h . # I t can be more s p e c i f i c ( f o r example ,
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
-
Answer Matching Outperforms Multiple Choice for Language Model Evaluation
Answer matching with recent language models aligns with human grading at near-inter-annotator levels, substantially outperforming multiple-choice evaluation and LLM-as-judge without reference answers.