Schema-Constrained Document-Level Event Argument Extraction with Lightweight LLM Fine-Tuning

A new study from dessertlab shows that fine-tuned mid-sized open LLMs can outperform GPT baselines in schema-constrained document-level event argument extraction on the MAVEN-ARG benchmark. The approach combines role-set injection, LoRA fine-tuning, and deterministic decoding, with the best model (Phi-4, 14B) achieving 42.39% F1 at the event-coreference level. Code is publicly available at https://github.com/dessertlab/EAE/.

arXiv:2607.16808v1 Announce Type: new Abstract: Event Argument Extraction EAE converts documents into structured event records by identifying argument spans and assigning them schema-defined roles. Document-level EAE is challenging due to long-range dependencies between triggers and arguments, cross-sentence context, and strict role constraints, which often lead to boundary errors, uncertainty in roles, and inconsistencies with restricted schemas. In this paper, we study whether mid-sized open LLMs can perform schema-constrained EAE reliably at the document level on MAVEN-ARG. Our approach combines i role-set injection in prompts for schema compliance, ii parameter-efficient supervised fine-tuning LoRA using the same JSON-only interface used at inference, and iii deterministic decoding with post-processing that validates JSON, filters invalid roles, de-duplicates arguments, and aligns spans to the document window. Under the official MAVEN-ARG evaluator, fine-tuned mid-sized open models outperform previously reported GPT baselines across mention, entity-coreference, and event-coreference evaluations; our best model Phi-4, 14B reaches 42.39\% F1 at the event-coreference level. Code to reproduce experiments is publicly available at https://github.com/dessertlab/EAE/.