English

$\texttt{COSMIC}$: Mutual Information for Task-Agnostic Summarization Evaluation

Computation and Language 2024-08-15 v3 Artificial Intelligence

Abstract

Assessing the quality of summarizers poses significant challenges. In response, we propose a novel task-oriented evaluation approach that assesses summarizers based on their capacity to produce summaries that are useful for downstream tasks, while preserving task outcomes. We theoretically establish a direct relationship between the resulting error probability of these tasks and the mutual information between source texts and generated summaries. We introduce COSMIC\texttt{COSMIC} as a practical implementation of this metric, demonstrating its strong correlation with human judgment-based metrics and its effectiveness in predicting downstream task performance. Comparative analyses against established metrics like BERTScore\texttt{BERTScore} and ROUGE\texttt{ROUGE} highlight the competitive performance of COSMIC\texttt{COSMIC}.

Keywords

Cite

@article{arxiv.2402.19457,
  title  = {$\texttt{COSMIC}$: Mutual Information for Task-Agnostic Summarization Evaluation},
  author = {Maxime Darrin and Philippe Formont and Jackie Chi Kit Cheung and Pablo Piantanida},
  journal= {arXiv preprint arXiv:2402.19457},
  year   = {2024}
}

Comments

ACL 2024

R2 v1 2026-06-28T15:05:03.967Z