Research map / Large language models / Retrieval and knowledge
A Joint Model for Question Answering over Multiple Knowledge Bases
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 |
|---|---|---|---|
| joint alignment and query construction instead of pipeline (ablation) | ILP joint model · Benchmark | F1: 0.76 -> 0.96 | Helped |
| joint alignment and query construction instead of pipeline (ablation) | ILP joint model · QALD-4 TASK2 | F1: 0.64 -> 0.88 | Helped |
| joint alignment and query construction instead of pipeline (ablation) | ILP joint model · Chinese | F1: 0.72 -> 0.77 | Helped |
| joint instead of pipeline (ablation) | ILP joint model · Chinese | alignment precision: 0.84 -> 0.94 | Helped |
| joint instead of pipeline (ablation) | ILP joint model · Benchmark | alignment precision: 0.80 -> 0.92 | Helped |
| add constraint 3 (selected alignment implies its two triple patterns selected) (ablation) | ILP joint model · all three datasets | F1 and alignment precision | Helped |
| add each of constraints 1, 2, 4, 5 (ablation) | ILP joint model · all three datasets | F1 and alignment precision | Helped |
| joint ILP vs SINA | ILP joint model · Chinese | F1: 0.63 -> 0.77 | Helped |
| joint ILP vs SINA | ILP joint model · QALD-4 TASK2 | F1: 0.79 -> 0.88 | Helped |
Closest papers by meaning
- Cost-efficient Knowledge-based Question Answering with Large Language Models (NeurIPS 2024 · similarity 0.88)
- TrustUQA: A Trustful Framework for Unified Structured Data Question Answering (AAAI 2025 · similarity 0.88)
- FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering (AAAI 2024 · similarity 0.88)
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (AAAI 2025 · similarity 0.88)
- KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search (ICML 2025 · similarity 0.87)
- Listening to the Wise Few: Query–Key Alignment Unlocks Latent Correct Answers in Large Language Models (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.