← Back to all news
arXiv Computation and Language By Omar Adjali, Siting Liang, Omair Shahzad Bhatti, Daniel Sonntag

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

Read the original on arXiv Computation and Language →

EAGER is a reinforcement learning framework for generative event extraction that uses fine‑grained verifiable rewards and Schema‑Contrastive Advantage Estimation to address advantage collapse in sparse binary reward settings. The reward design focuses on structural validity, extraction accuracy, groundedness, coverage, over‑generation, and span precision. Across seven benchmark datasets, EAGER outperforms prompting, supervised fine‑tuning, and previous reinforcement learning baselines, achieving a substantial improvement over the strongest prior method.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Aug 25

A Multi-Domain and Multi-Task Generative Framework with Explicit Task and Domain Conditioning for Cross-Domain Event Extraction

The paper introduces a unified multi-domain and multi-task generative framework for event extraction that incorporates explicit domain conditioning signals and task-specific prompts. This design allows a single model to adapt dynamically to different event schemas without needing full event label sets during inference, supporting both pipeline and end-to-end extraction. Experiments on various benchmarks show competitive performance, strong cross-domain generalization, and practical scalability while maintaining domain-specific precision.

By Siting Liang, Omar Adjali, Daniel Sonntag
llmsfine-tuningbenchmarks
More like this →
arXiv Computation and Language
Aug 25

A Scalable Cross-Domain Event Extraction System via a Unified Generative Training Framework

The paper introduces a scalable cross‑domain event extraction system built on a unified generative sequence‑to‑sequence framework. It jointly handles event detection and argument extraction, allowing both pipeline and end‑to‑end configurations. By fine‑tuning pretrained language models on multiple event datasets from diverse domains, the system retains domain‑specific semantics while generalizing across large, evolving label spaces, and offers a web‑based application for researchers to upload documents, extract events, visualize triggers and arguments, and compare configurations.

By Siting Liang, Omar Adjali, Omair Shahzad Bhatti, Daniel Sonntag
llmsfine-tuning
More like this →
arXiv Computation and Language
Sep 25

Do not be greedy, Think Twice: Sampling and Selection for Document-level Information Extraction

The paper introduces ThinkTwice, a framework that uses sampling and selection to improve document‑level information extraction. Instead of relying on greedy decoding, the method generates multiple candidate templates and selects the best one via an unsupervised agreement‑based approach or a supervised reward model. It also proposes a rejection‑sampling technique to create silver training data for reasoning traces, and experimental results show that ThinkTwice consistently outperforms greedy baselines and the current supervised state‑of‑the‑art.

By Mikel Zubillaga, Oscar Sainz, Oier Lopez de Lacalle, Eneko Agirre
llmsbenchmarks
More like this →
arXiv Machine Learning
Jun 9

ConSteer-RL: Steering Reasoning Capabilities in Large Language Models via Confidence-Aware Reinforcement Learning

arXiv:2606. 08088v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has recently become a key paradigm for improving the reasoning abilities of Large Language Models (LLMs), yet it remains limited by sparse binary rewards and its ignorance of model-internal uncertainty.

By Qing Miao, Yiming Zhao, Jing Yang, Chenxi Liu, Yuehai Chen, Yuewen Liu, Shaoyi Du, Badong Chen
llmsreinforcement-learning
More like this →