Research map / Large language models / Retrieval and knowledge
Enhancing LLMs for Knowledge Base Question Answering by Chain-of-Decomposition
Yonggang Zhang, Jianqi Gao, Jie Lu
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 |
|---|---|---|---|
| decompose KBQA into trained retrieval, rule-based reformulation, and LLM reasoning (CoD) | Llama2-7B · WebQSP | Hits@1: 84.39 -> 86.54 (vs FiDeLis GPT-4) | Improved |
| CoD vs strongest baseline | Llama2-7B · CWQ | Hits@1: 71.47 -> 77.42 | Improved |
| CoD vs strongest baseline | Llama2-7B · CWQ | F1: 64.32 -> 65.70 | Improved |
| use dedicated trained retriever instead of DPR/BM25/Sentence-BERT | CoD · WebQSP retrieval | top5-acc: 35.02 -> 91.04 (vs DPR) | Improved |
| swap trained retriever for DPR in CoD (ablation) | CoD · WebQSP | Hits@1: 86.54 -> 83.37 | Hurt |
| combine logical-form executed answers and generated answers (ablation) | CoD · WebQSP and CWQ (bm=5) | F1: CWQ F1 49.40 / 51.37 -> 65.70 | Improved |
| increase beam size from 1 to 3 (ablation) | CoD · WebQSP | F1: 75.56 -> 80.87 | Improved |
| increase beam size from 3 to 5 (ablation) | CoD · CWQ | F1: 68.27 -> 65.70 | Hurt |
| use deductive reasoning prompt instead of direct generation (ablation) | CoD · WebQSP | F1: 77.53 -> 81.24 | Improved |
| use deductive prompt instead of CoT prompt (ablation) | CoD · WebQSP | F1: 79.36 -> 81.24 | Improved |
| change backbone LLM from Llama2-7B to Qwen2.5-7B (ablation) | CoD · WebQSP | F1: 81.24 -> 80.39 | No clear effect |
Closest papers by meaning
- Promoting Knowledge Base Question Answering by Directing LLMs to Generate Task-relevant Logical Forms (AAAI 2025 · similarity 0.92)
- FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering (AAAI 2024 · similarity 0.91)
- Explore What LLM Does Not Know in Complex Question Answering (AAAI 2025 · similarity 0.91)
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (AAAI 2025 · similarity 0.91)
- Tree-of-Reasoning Question Decomposition for Complex Question Answering with Large Language Models (AAAI 2024 · similarity 0.91)
- Cost-efficient Knowledge-based Question Answering with Large Language Models (NeurIPS 2024 · similarity 0.90)
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.
