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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add SGER schema guidance | GPT-4o · EV2 S-CEC | accuracy: 68.81 -> 72.42 | Improved |
| add SGER schema guidance | GPT-3.5 · EV2 I-CEC | accuracy: 49.35 -> 47.86 | Hurt |
| add SGER schema guidance | GPT-3.5 · EV2 I-CRR | accuracy: 36.56 -> 52.89 | Improved |
| add SGER schema guidance | Llama2-7B · EV2 S-CEC | accuracy: 39.69 -> 66.24 | Improved |
| add SGER schema guidance | Orca2-7B · EV2 I-CEC | accuracy: 57 -> 52.47 | Hurt |
| add SGER schema guidance | GPT-4o · EV2 I-CEC | accuracy: 70.99 -> 71.37 | No clear effect |
| add SGER schema guidance | Llama3.2-3B · EV2 I-CRR | accuracy: 50.68 -> 61.05 | Improved |
| add schema predictor on top of extractor + reasoner (ablation) | Llama2-7B · EV2 I-CEC | accuracy: 29.09 -> 54.29 | Improved |
| add schema predictor on top of extractor + reasoner (ablation) | Llama2-7B · EV2 I-CRR | accuracy: 37.41 -> 61.9 | Improved |
| replace extractor+predictor with single mixed-data Reasoning Assistant (ablation) | Llama2-7B · EV2 S-CEC | accuracy: 66.24 -> 64.69 | Hurt |
| replace extractor+predictor with single mixed-data Reasoning Assistant (ablation) | Llama2-7B · EV2 I-CEC | accuracy: 54.29 -> 65.58 | Improved |
| 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 20.5 | Improved |
Closest papers by meaning
- A Comprehensive Evaluation on Event Reasoning of Large Language Models (AAAI 2025 · similarity 0.92)
- CHRONOS: A Schema-Based Event Understanding and Prediction System (AAAI 2024 · similarity 0.86)
- LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning About Actions (AAAI 2025 · similarity 0.85)
- A State-Transition Framework for Efficient LLM Reasoning (ICLR 2026 · similarity 0.84)
- TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios (NeurIPS 2025 · similarity 0.84)
- ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation (AAAI 2026 · similarity 0.83)
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.
