Research map / Large language models / Retrieval and knowledge
Reasoning Over Virtual Knowledge Bases With Open Predicate Relations
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Fine-tune the relation encoder on MetaQA data | OPQL-pretrained · MetaQA 2Hop | Hits@1: 84.7 -> 88.5 | Helped |
| Fine-tune the relation encoder on MetaQA data | OPQL-pretrained · MetaQA 3Hop | Hits@1: 84.3 -> 87.1 | Helped |
| Fine-tune the relation encoder on MSF data | OPQL-pretrained · MSF 2Hop | Hits@1: 48.5 -> 49.2 | Helped |
| Fine-tune the relation encoder on MSF data | OPQL-pretrained · MSF 3Hop | Hits@1: 28.1 -> 29.7 | Helped |
| Mix retrieved memory embeddings into LM predictions (ablation) | OPQL-follow · WebQSP | Hits@1: 46.6 -> 51.9; 5.3% | Helped |
| Mix retrieved memory embeddings into LM predictions (ablation) | OPQL-follow · ComplexWebQ | Hits@1: 18.5 -> 40.7; 22.4% | Helped |
| Make the null key depend on the topic entity (ablation) | OPQL-LM · WebQSP | Hits@1: 46.3 -> 51.9 | Helped |
| Make the null key depend on the topic entity (ablation) | OPQL-LM · WebQSP | retrieval accuracy: 69.5 -> 85.4 | Helped |
| Make the null key depend on the topic entity (ablation) | OPQL-LM · ComplexWebQ | Hits@1: 19.3 -> 40.7 | Helped |
| Add question-entity-specific pairs to the memory | OPQL-LM · WebQSP | Hits@1: 51.9 -> 53.7 | Helped |
| Add question-entity-specific pairs to the memory | OPQL-LM · WebQSP questions with relevant memory pairs | retrieval accuracy: 85.4% to 62.2% | Hurt |
Closest papers by meaning
- Reasoning of Large Language Models over Knowledge Graphs with Super-Relations (ICLR 2025 · similarity 0.86)
- FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering (AAAI 2024 · similarity 0.86)
- OpenTab: Advancing Large Language Models as Open-domain Table Reasoners (ICLR 2024 · similarity 0.85)
- A Foundation Model for Zero-shot Logical Query Reasoning (NeurIPS 2024 · similarity 0.85)
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph (ICLR 2024 · similarity 0.85)
- LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoning (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.