AI Paper Atlas

Research map / Large language models / Agents, code and math

Schema-Guided Event Reasoning: A Plug-and-Play Event Reasoning Framework Based on Large Language Models

Yuying Liu, Xuechen Zhao, Yanyi Huang, Ye Wang, Xin Song, Yue Zhang, Haiyan Liu, Bin Zhou

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 0 citations (OpenAlex)

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 SGER schema guidanceGPT-4o · EV2 S-CECaccuracy: 68.81 -> 72.42Improved
add SGER schema guidanceGPT-3.5 · EV2 I-CECaccuracy: 49.35 -> 47.86Hurt
add SGER schema guidanceGPT-3.5 · EV2 I-CRRaccuracy: 36.56 -> 52.89Improved
add SGER schema guidanceLlama2-7B · EV2 S-CECaccuracy: 39.69 -> 66.24Improved
add SGER schema guidanceOrca2-7B · EV2 I-CECaccuracy: 57 -> 52.47Hurt
add SGER schema guidanceGPT-4o · EV2 I-CECaccuracy: 70.99 -> 71.37No clear effect
add SGER schema guidanceLlama3.2-3B · EV2 I-CRRaccuracy: 50.68 -> 61.05Improved
add schema predictor on top of extractor + reasoner (ablation)Llama2-7B · EV2 I-CECaccuracy: 29.09 -> 54.29Improved
add schema predictor on top of extractor + reasoner (ablation)Llama2-7B · EV2 I-CRRaccuracy: 37.41 -> 61.9Improved
replace extractor+predictor with single mixed-data Reasoning Assistant (ablation)Llama2-7B · EV2 S-CECaccuracy: 66.24 -> 64.69Hurt
replace extractor+predictor with single mixed-data Reasoning Assistant (ablation)Llama2-7B · EV2 I-CECaccuracy: 54.29 -> 65.58Improved
use two-stage schema extraction and prediction instead of mixed RA (ablation)Llama2-7B · MCNC (OOD)accuracy: SGER +5.63 vs RA+R +3.62 over 20.5Improved

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