AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction

Quanjiang Guo, Sijie Wang, Jinchuan Zhang, Ben Zhang, Zhao Kang, Ling Tian, Ke Yan

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Retrieval Agent exemplar generation (ablation)AEC · ACE 2005 trigger identificationF1: 49.8 -> 57.0 (Llama3-70B)Improved
add planning rationales (ablation)AEC · ACE 2005 trigger identificationF1: 52.6 -> 57.0 (Llama3-70B)Improved
add verification loop (ablation)AEC · ACE 2005 argument classificationF1: 28.5 -> 34.7 (Llama3-70B)Improved
add structural check (ablation)AEC · FewEvent trigger identificationF1: 39.8 -> 42.1 (Llama3-70B)Improved
replace baselines with AEC multi-agent code frameworkLlama3-70B · ACE 2005 trigger identificationF1: 51.5 -> 57.0 (best baseline CEDAR)Improved
replace DecomposeEE with AECGPT3.5-turbo · ACE 2005 argument classificationF1: DecomposeEE 27.4 vs AEC 29.8 on GENIA AC, but CASIE AC 27.6 vs 26.7Mixed
increase hypotheses k from 1 to 3 (t=3) (ablation)AEC with GPT4o · ACE 2005 event identificationF1: 56.8 -> 61.8Improved
increase k and t from 3 to 5 (ablation)AEC with GPT4o · FewEvent / ACEF1: 44.6 -> 45.1 (FewEvent TI), 58.3 -> 58.3 (ACE TI)No clear effect
use more than three verification test cases (ablation)AEC with GPT4o · FewEvent, ACEscoreNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy