A multi-LLM prompt optimizer that induces domain-specific formatting policies from reference summaries outperforms generic critique-driven prompt optimizers on enterprise ticket summarization.
In: Proceedings of the International Conference on Learning Representations (ICLR) (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MIDAS: Multi-LLM Iterative Data-Adaptive Summarization
A multi-LLM prompt optimizer that induces domain-specific formatting policies from reference summaries outperforms generic critique-driven prompt optimizers on enterprise ticket summarization.