MSumBench is a new English/Chinese benchmark that grades summaries across six domains on faithfulness, completeness, and conciseness, using domain-specific key-facts and multi-agent-debate-assisted human annotations, plus evaluations of eight summarizers and four LLM-based judges.
</note> <instructions>
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
-
Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages
MSumBench is a new English/Chinese benchmark that grades summaries across six domains on faithfulness, completeness, and conciseness, using domain-specific key-facts and multi-agent-debate-assisted human annotations, plus evaluations of eight summarizers and four LLM-based judges.