Research map / Large language models / Language, safety and interpretability
Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning
Xiaoming Shi, Siqiao Xue, Kangrui Wang, Fan Zhou, James Y. Zhang, JUN ZHOU, Chenhao Tan, Hongyuan Mei
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 LLM abductive reasoning and evidence ranking (LAMP) on top of base event models | event sequence models (NHP, KE, DyRep, ANHP) · GDELT predicate-object prediction | mean rank: around 40 -> around 20 | Improved |
| add LAMP to base event models | event sequence models · ICEWS object prediction | mean rank: around 90 -> about 20 | Improved |
| use Llama-2-chat 13B instead of GPT-3.5 as the LLM (ablation) | LAMP · GDELT predicate/object prediction | mean rank | No clear effect |
| use GPT-3-davinci instead of GPT-3.5 or Llama (ablation) | LAMP · GDELT | mean rank | Hurt |
| increase retrieved evidence events from 5 to 10, then beyond 10 (ablation) | LAMP · GDELT | mean rank | Mixed |
| use more demonstrations in the prompt (ablation) | LAMP · GDELT | mean rank | Improved |
| replace half of the demonstrations (P1 to P2) (ablation) | LAMP · GDELT | mean rank | No clear effect |
| use LLM-generated causes for retrieval instead of random, recent, same-predicate, same-object or SBERT retrieval (ablation) | LAMP · GDELT | mean rank | Improved |
| use similarity threshold instead of fixed number of retrieved events (ablation) | LAMP · GDELT | mean rank | No clear effect |
| use edit distance instead of SBERT cosine similarity for retrieval (ablation) | LAMP · GDELT | mean rank | Hurt |
Closest papers by meaning
- A Comprehensive Evaluation on Event Reasoning of Large Language Models (AAAI 2025 · similarity 0.88)
- Is a Large Language Model a Good Annotator for Event Extraction? (AAAI 2024 · similarity 0.86)
- Training Language Models to Reason Efficiently (NeurIPS 2025 · similarity 0.85)
- DynaAct: Large Language Model Reasoning with Dynamic Action Spaces (NeurIPS 2025 · similarity 0.85)
- From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information? (ICML 2025 · similarity 0.85)
- NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models (AAAI 2026 · similarity 0.85)
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.
