Explicit reasoning LLMs do not improve dialogue summarization quality and tend to be more verbose and less faithful than their non-reasoning counterparts.
Title resolution pending
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
-
Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization
Explicit reasoning LLMs do not improve dialogue summarization quality and tend to be more verbose and less faithful than their non-reasoning counterparts.