Research map / Graph learning / Knowledge and temporal graphs
SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning
Mattia Atzeni, Jasmina Bogojeska, Andreas Loukas
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 key-value memory network edge-level refinement to unrefined relation-level model (ablation) | SQALER Unrefined · WebQSP | Hits@1: 70.6 -> 72.1 | Improved |
| add GNN edge-level refinement to unrefined relation-level model (ablation) | SQALER Unrefined · WebQSP | Hits@1: 70.6 -> 76.1 | Improved |
| use GNN instead of KV-MemNN for refinement (ablation) | SQALER · WebQSP | Hits@1: 72.1 -> 76.1 | Improved |
| add refinement step (KV-MemNN or GNN) on MetaQA (ablation) | SQALER Unrefined · MetaQA 2 and 3 | Hits@1: 99.9 -> 99.9 | No clear effect |
| use relation-level model only versus EmQL on WebQSP | SQALER Unrefined · WebQSP | Hits@1: 75.5 -> 70.6 | Hurt |
| use SQALER Unrefined instead of EmQL on MetaQA 3 | EmQL · MetaQA 3 | Hits@1: 99.1 -> 99.9 | Improved |
| use SQALER-GNN instead of PullNet on incomplete KG (50% edges) | PullNet · WebQSP 50% KG | Hits@1: 50.3 -> 53.5 | Improved |
| use SQALER-GNN instead of PullNet on incomplete KG plus text | PullNet · WebQSP 50% KG + Text | Hits@1: 51.9 -> 55.2 | Improved |
| add Wikipedia text documents to 50% KG | SQALER -- GNN · WebQSP | Hits@1: 53.5 -> 55.2 | Improved |
| use SQALER-GNN instead of HPD on CFQ MCD-mean | HPD · CFQ | accuracy: 0.673 -> 0.671 | No clear effect |
| use SQALER-GNN instead of T5-11B-mod on CFQ MCD-mean | T5-11B-mod · CFQ | accuracy: 0.421 -> 0.671 | Improved |
| increase number of sampled relation sequences from 3 to 10 (ablation) | SQALER relation-level model · WebQSP | recall: 0.91 -> 0.95 | Improved |
Closest papers by meaning
- Tree-of-Reasoning Question Decomposition for Complex Question Answering with Large Language Models (AAAI 2024 · similarity 0.91)
- Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models (AAAI 2025 · similarity 0.90)
- Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering (AAAI 2025 · similarity 0.90)
- Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking (NeurIPS 2025 · similarity 0.89)
- Question Calibration and Multi-Hop Modeling for Temporal Question Answering (AAAI 2024 · similarity 0.89)
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (AAAI 2025 · similarity 0.88)
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.
