Research map / Large language models / Retrieval and knowledge
Declarative Question Answering over Knowledge Bases Containing Natural Language Text with Answer Set Programming
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 |
|---|---|---|---|
| Apply ASP reasoning with generated hypotheses and textual entailment validation rather than using the entailment function as a standalone solver | Life-cycle QA · Question Split | accuracy: 62.40; 77.80 | Helped |
| Apply ASP reasoning with generated hypotheses and textual entailment validation rather than using the entailment function as a standalone solver | Life-cycle QA · Text Split | accuracy: 61.98; 80.70 | Helped |
| Replace KDG attribute extraction with Custom-KDG's search-based attribute extraction | ASP QA with textual entailment · Question Split | accuracy: 74.61 -> 77.80 | Helped |
| Replace KDG attribute extraction with Custom-KDG's search-based attribute extraction | ASP QA with textual entailment · Text Split | accuracy: 76.17 -> 80.70 | Helped |
| Use NGram-LS-3 instead of NGram-LS-1 entailment | Gold question representation system · Question Split | accuracy: 78.95 -> 79.28 | Helped |
| Use NGram-LS-3 instead of NGram-LS-1 entailment | Gold question representation system · Text Split | accuracy: 84.06 -> 83.77 | Hurt |
| Use Custom-KDG instead of KDG question parsing | ASP QA with textual entailment [cite] · Question Split | accuracy: 70.60 -> 72.40 | Helped |
| Use Custom-KDG instead of KDG question parsing | ASP QA with textual entailment [cite] · Text Split | accuracy: 72.51 -> 76.68 | Helped |
Closest papers by meaning
- KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search (ICML 2025 · similarity 0.85)
- Promoting Knowledge Base Question Answering by Directing LLMs to Generate Task-relevant Logical Forms (AAAI 2025 · similarity 0.85)
- FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering (AAAI 2024 · similarity 0.84)
- Decompose, Analyze and Rethink: Solving Intricate Problems with Human-like Reasoning Cycle (NeurIPS 2024 · similarity 0.84)
- Cost-efficient Knowledge-based Question Answering with Large Language Models (NeurIPS 2024 · similarity 0.84)
- Code-Style In-Context Learning for Knowledge-Based Question Answering (AAAI 2024 · similarity 0.84)
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.