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

arXiv: https://arxiv.org/abs/2609.29230 · HTML: https://mlsanity.com/paper/2609.29230/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023)
- [Document-Level Event Argument Extraction by Conditional Generation](https://mlsanity.com/paper/2104.05919/) (2021)
- [Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction](https://mlsanity.com/paper/2106.09232/) (2021)
- [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction](https://mlsanity.com/paper/2310.03668/) (2023)
- [Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning](https://mlsanity.com/paper/2507.00432/) (2025)
- [DEGREE: A Data-Efficient Generation-Based Event Extraction Model](https://mlsanity.com/paper/2108.12724/) (2021)
- [Exploring the Feasibility of ChatGPT for Event Extraction](https://mlsanity.com/paper/2303.03836/) (2023)
- [Code4Struct: Code Generation for Few-Shot Event Structure Prediction](https://mlsanity.com/paper/2210.12810/) (2022)
- [CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors](https://mlsanity.com/paper/2305.05711/) (2023)
- [Cross-media Structured Common Space for Multimedia Event Extraction](https://mlsanity.com/paper/2005.02472/) (2020)
- [Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction](https://mlsanity.com/paper/2202.12109/) (2022)
- [Instruct and Extract: Instruction Tuning for On-Demand Information Extraction](https://mlsanity.com/paper/2310.16040/) (2023)
- [KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction](https://mlsanity.com/paper/2403.07969/) (2024)
- [TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction](https://mlsanity.com/paper/2311.09562/) (2023)
- [ADELIE: Aligning Large Language Models on Information Extraction](https://mlsanity.com/paper/2405.05008/) (2024)
- [Instruction-Tuning LLMs for Event Extraction with Annotation Guidelines](https://mlsanity.com/paper/2502.16377/) (2025)
- [PIVOINE: Instruction Tuning for Open-world Information Extraction](https://mlsanity.com/paper/2305.14898/) (2023)
- [Improving Event Definition Following For Zero-Shot Event Detection](https://mlsanity.com/paper/2403.02586/) (2024)
- [Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation](https://mlsanity.com/paper/2605.21125/) (2026)
- [Towards Better Question Generation in QA-based Event Extraction](https://mlsanity.com/paper/2405.10517/) (2024)

## Abstract (arXiv)

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.