AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Open Rule Induction

Wanyun Cui, Xingran Chen

NeurIPS 2021 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 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
Induce open rules from LM knowledge using OrionBART rule generation · OpenRule155BLEU-1: 21.58 -> 45.41Improved
Use supported beam search instead of standard beam search (ablation)Orion · OpenRule155BLEU-1: 44.92 -> 45.41Improved
Continue training the instance generator P(ins|r_p) (ablation)Orion · OpenRule155BLEU-1: 15.85 -> 45.41Improved
Continue training the hypothesis generator P(r_h|ins) (ablation)Orion · OpenRule155BLEU-1: 19.17 -> 45.41Improved
Replace manually annotated rule descriptions with Orion open rulesExpBERT · SpouseF1: 76.04 ± 0.47 -> 76.05 ± 0.52No clear effect
Replace manually annotated rule descriptions with Orion open rulesExpBERT · DiseaseF1: 56.92 ± 0.82 -> 57.68 ± 1.34Improved
Use Orion to induce rules for relation extraction premisesRule induction · FewRelROUGE-L: 15.35 -> 38.72Improved
Increase the number of rules returned to k=20Orion · Yago2 two-variable rulesAccuracy: 50.0 -> 49.2 -> 51.3No 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