Research map / Large language models / Retrieval and knowledge
Variational Reasoning for Question Answering With Knowledge Graph
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 |
|---|---|---|---|
| Use VRN instead of the strongest reported baseline | Knowledge-graph QA · Vanilla 3-hop | hits@1: 28.4 -> 62.5 | Helped |
| Use VRN instead of the strongest reported baseline | Knowledge-graph QA · Vanilla-EU 3-hop | hits@1: 26.9 -> 38.3 | Helped |
| Use VRN instead of the strongest reported baseline | Knowledge-graph QA · NTM-EU 1-hop | hits@1: 33.9 -> 81.3 | Helped |
| Use VRN instead of the strongest reported baseline | Knowledge-graph QA · Audio-EU 3-hop | hits@1: 15.3 -> 21.1 | Helped |
| Jointly train the topic-entity recognizer with variational reasoning (ablation) | VRN · Vanilla and NTM entity-unlabeled questions, 1-hop and 2-hop | entity recognition performance | Helped |
| Jointly train the topic-entity recognizer with variational reasoning (ablation) | VRN · Audio-EU 1-hop | entity recognition performance: +10% | Helped |
| Jointly train the topic-entity recognizer with variational reasoning (ablation) | VRN · 3-hop questions | entity recognition performance | Helped |
| Replace reasoning-graph embeddings with a linear combination of reasoning-graph entities (ablation) | VRN · Multi-hop QA | hits@1 | Hurt |
| Increase KV-MemNN internal hops beyond the dataset hop number (ablation) | KV-MemNN · MetaQA | hits@1 | No clear effect |
Closest papers by meaning
- Graph Reasoning Transformers for Knowledge-Aware Question Answering (AAAI 2024 · similarity 0.89)
- Question Calibration and Multi-Hop Modeling for Temporal Question Answering (AAAI 2024 · similarity 0.89)
- Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models (AAAI 2025 · similarity 0.89)
- Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering (AAAI 2025 · similarity 0.88)
- Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking (NeurIPS 2025 · similarity 0.88)
- KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering (NeurIPS 2026 · similarity 0.87)
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.