Italo Luis Da Silva


2024

pdf bib
Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems
Italo Luis Da Silva | Hanqi Yan | Lin Gui | Yulan He
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

The inherent ambiguity of cause and effect boundaries poses a challenge in evaluating causal event extraction tasks. Traditional metrics like Exact Match and BertScore poorly reflect model performance, so we trained evaluation models to approximate human evaluation, achieving high agreement. We used them to perform Reinforcement Learning with extraction models to align them with human preference, prioritising semantic understanding. We successfully explored our approach through multiple datasets, including transferring an evaluator trained on one dataset to another as a way to decrease the reliance on human-annotated data. In that vein, we also propose a weak-to-strong supervision method that uses a fraction of the annotated data to train an evaluation model while still achieving high performance in training an RL model.