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

arXiv:2609.29230 · cs.CL · Submitted 2026-09-24 · Read on arXiv

cs.CL

Submitted: 2026-09-24

Updated: 2026-09-24

Comments: Accepted to EMNLP 2026 Findings

Code: https://github.com/huggingface/trl

License: http://creativecommons.org/licenses/by/4.0/

The gist: 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

Terminology

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.

Sources

Related papers