Research map / Large language models / Retrieval and knowledge
Open Rule Induction
Wanyun Cui, Xingran Chen
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 |
|---|---|---|---|
| Induce open rules from LM knowledge using Orion | BART rule generation · OpenRule155 | BLEU-1: 21.58 -> 45.41 | Improved |
| Use supported beam search instead of standard beam search (ablation) | Orion · OpenRule155 | BLEU-1: 44.92 -> 45.41 | Improved |
| Continue training the instance generator P(ins|r_p) (ablation) | Orion · OpenRule155 | BLEU-1: 15.85 -> 45.41 | Improved |
| Continue training the hypothesis generator P(r_h|ins) (ablation) | Orion · OpenRule155 | BLEU-1: 19.17 -> 45.41 | Improved |
| Replace manually annotated rule descriptions with Orion open rules | ExpBERT · Spouse | F1: 76.04 ± 0.47 -> 76.05 ± 0.52 | No clear effect |
| Replace manually annotated rule descriptions with Orion open rules | ExpBERT · Disease | F1: 56.92 ± 0.82 -> 57.68 ± 1.34 | Improved |
| Use Orion to induce rules for relation extraction premises | Rule induction · FewRel | ROUGE-L: 15.35 -> 38.72 | Improved |
| Increase the number of rules returned to k=20 | Orion · Yago2 two-variable rules | Accuracy: 50.0 -> 49.2 -> 51.3 | No clear effect |
Closest papers by meaning
- RuAG: Learned-rule-augmented Generation for Large Language Models (ICLR 2025 · similarity 0.88)
- LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs (AAAI 2025 · similarity 0.87)
- Inductive Learning of Logical Theories with LLMs: A Expressivity-graded Analysis (AAAI 2025 · similarity 0.84)
- RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning (ICML 2025 · similarity 0.84)
- Automated Creation of Reusable and Diverse Toolsets for Enhancing LLM Reasoning (AAAI 2025 · similarity 0.83)
- Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts (NeurIPS 2024 · 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.
