# Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

arXiv: https://arxiv.org/abs/2011.07743 · HTML: https://mlsanity.com/paper/2011.07743/

## Key facts

- Cited by 171 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2020.

## Built on by (most cited first, 30 of 171)

- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022)
- [KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph](https://mlsanity.com/paper/2402.11163/) (2024)
- [QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension](https://mlsanity.com/paper/2107.12708/) (2021)
- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering](https://mlsanity.com/paper/2109.08678/) (2021)
- [DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases](https://mlsanity.com/paper/2210.00063/) (2022)
- [A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions](https://mlsanity.com/paper/2105.11644/) (2021)
- [Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs](https://mlsanity.com/paper/2410.23875/) (2024)
- [LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners](https://mlsanity.com/paper/2505.11942/) (2025)
- [Few-shot In-context Learning for Knowledge Base Question Answering](https://mlsanity.com/paper/2305.01750/) (2023)
- [Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering](https://mlsanity.com/paper/2210.01613/) (2022)
- [Agent Lumos: Unified and Modular Training for Open-Source Language Agents](https://mlsanity.com/paper/2311.05657/) (2023)
- [Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family](https://mlsanity.com/paper/2303.07992/) (2023)
- [KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation](https://mlsanity.com/paper/2409.13731/) (2024)
- [PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths](https://mlsanity.com/paper/2502.14902/) (2025)
- [TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases](https://mlsanity.com/paper/2210.12925/) (2022)
- [UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training](https://mlsanity.com/paper/2202.12359/) (2022)
- [Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments](https://mlsanity.com/paper/2212.09736/) (2022)
- [InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment](https://mlsanity.com/paper/2402.08785/) (2024)
- [Complex Knowledge Base Question Answering: A Survey](https://mlsanity.com/paper/2108.06688/) (2021)
- [FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering](https://mlsanity.com/paper/2308.12060/) (2023)
- [ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering](https://mlsanity.com/paper/2204.08109/) (2022)
- [ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models](https://mlsanity.com/paper/2310.08975/) (2023)
- [Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning](https://mlsanity.com/paper/2410.14211/) (2024)
- [Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments](https://mlsanity.com/paper/2402.14672/) (2024)

## Abstract (arXiv)

Existing studies on question answering on knowledge bases (KBQA) mainly operate with the standard i.i.d assumption, i.e., training distribution over questions is the same as the test distribution. However, i.i.d may be neither reasonably achievable nor desirable on large-scale KBs because 1) true user distribution is hard to capture and 2) randomly sample training examples from the enormous space would be highly data-inefficient. Instead, we suggest that KBQA models should have three levels of built-in generalization: i.i.d, compositional, and zero-shot. To facilitate the development of KBQA models with stronger generalization, we construct and release a new large-scale, high-quality dataset with 64,331 questions, GrailQA, and provide evaluation settings for all three levels of generalization. In addition, we propose a novel BERT-based KBQA model. The combination of our dataset and model enables us to thoroughly examine and demonstrate, for the first time, the key role of pre-trained contextual embeddings like BERT in the generalization of KBQA.