PaperScope
LIVE · 2026-09-25 05:40 UTC

EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards

Omar Adjali, Siting Liang, Omair Shahzad Bhatti, Daniel Sonntag

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.29230 v1
Category
Submitted
2026-09-24

Abstract

End-to-end event extraction remains challenging for large language models as it requires simultaneous identification of event triggers, classification of event types, and extraction of schema-grounded argument spans. We present EAGER, a reinforcement learning framework for generative event extraction that combines fine-grained verifiable rewards with Schema-Contrastive Advantage Estimation to alleviate advantage collapse under sparse binary rewards. Our reward design explicitly targets structural validity, extraction accuracy, groundedness, coverage, over-generation, and span precision. Experiments across seven benchmark datasets show that EAGER consistently outperforms prompting, supervised fine-tuning, and prior reinforcement learning baselines, achieving a substantial improvement over the strongest prior method. Results demonstrate that task-aligned verifiable rewards and contrastive advantage estimation substantially improve structured extraction.

Comment: Accepted to EMNLP 2026 Findings

arXiv abs page · PDF · same-day batch