mlsanityData to 14 Oct 2026

A Learn-Then-Reason Model Towards Generalization in Knowledge Base Question Answering

arXiv 2406.14763 ↗First posted 20 Jun 2024cs.CL cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Large-scale knowledge bases (KBs) like Freebase and Wikidata house millions of structured knowledge. Knowledge Base Question Answering (KBQA) provides a user-friendly way to access these valuable KBs via asking natural language questions. In order to improve the generalization capabilities of KBQA models, extensive research has embraced a retrieve-then-reason framework to retrieve relevant evidence for logical expression generation. These multi-stage efforts prioritize acquiring external sources but overlook the incorporation of new knowledge into their model parameters. In effect, even advanced language models and retrievers have knowledge boundaries, thereby limiting the generalization capabilities of previous KBQA models. Therefore, this paper develops KBLLaMA, which follows a learn-then-reason framework to inject new KB knowledge into a large language model for flexible end-to-end KBQA. At the core of KBLLaMA, we study (1) how to organize new knowledge about KBQA and (2) how to facilitate the learning of the organized knowledge. Extensive experiments on various KBQA generalization tasks showcase the state-of-the-art performance of KBLLaMA. Especially on the general benchmark GrailQA and domain-specific benchmark Bio-chemical, KBLLaMA respectively derives a performance gain of up to 3.8% and 9.8% compared to the baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 10 of its 35 references that are in the map. First posted on arXiv 20 Jun 2024.

Builds on

10 of 35 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLM31 Dec

Other references · 9

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2023LIMA: Less Is More for Alignmentcited by 1,100
  4. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  5. 2023Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Familycited by 71
  6. 2023FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answeringcited by 51
  7. 2023ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Modelscited by 44
  8. 2023Code-Style In-Context Learning for Knowledge-Based Question Answeringcited by 13
  9. 2022EMAKG: An Enhanced Version Of The Microsoft Academic Knowledge Graphcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models
  2. 2026Joint Knowledge Base Completion and Question Answering by Combining Large Language Models and Small Language Models
  3. 2025KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
  4. 2025KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
  5. 2025Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering
  6. 2025iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answering
  7. 2026Co-Evolving Structured Knowledge and Reasoning in Language Models
  8. 2023KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph