# RetinaQA: A Robust Knowledge Base Question Answering Model for both Answerable and Unanswerable Questions

arXiv: https://arxiv.org/abs/2403.10849 · HTML: https://mlsanity.com/paper/2403.10849/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 16 Mar 2024.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases](https://mlsanity.com/paper/2011.07743/) (2020)
- [RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses](https://mlsanity.com/paper/2210.10634/) (2022)
- [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://mlsanity.com/paper/2104.08762/) (2021)
- [Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering](https://mlsanity.com/paper/2202.13296/) (2022)
- [RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering](https://mlsanity.com/paper/2109.08678/) (2021)
- [Few-shot In-context Learning for Knowledge Base Question Answering](https://mlsanity.com/paper/2305.01750/) (2023)
- [TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases](https://mlsanity.com/paper/2210.12925/) (2022)
- [Program Transfer for Answering Complex Questions over Knowledge Bases](https://mlsanity.com/paper/2110.05743/) (2021)
- [Knowledge Base Question Answering by Case-based Reasoning over Subgraphs](https://mlsanity.com/paper/2202.10610/) (2022)
- [A Two-Stage Approach towards Generalization in Knowledge Base Question Answering](https://mlsanity.com/paper/2111.05825/) (2021)
- [Do I have the Knowledge to Answer? Investigating Answerability of Knowledge Base Questions](https://mlsanity.com/paper/2212.10189/) (2022)
- [Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning](https://mlsanity.com/paper/2311.08894/) (2023)

## Built on by (most cited first, 2 of 2)

- [FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM Extraction](https://mlsanity.com/paper/2504.05607/) (2025)
- [AutoSchema: Live Schema Grounding for Agentic Text-to-Sparql over Heterogeneous Knowledge Graphs](https://mlsanity.com/paper/2608.14228/) (2026)

## Abstract (arXiv)

An essential requirement for a real-world Knowledge Base Question Answering (KBQA) system is the ability to detect the answerability of questions when generating logical forms. However, state-of-the-art KBQA models assume all questions to be answerable. Recent research has found that such models, when superficially adapted to detect answerability, struggle to satisfactorily identify the different categories of unanswerable questions, and simultaneously preserve good performance for answerable questions. Towards addressing this issue, we propose RetinaQA, a new KBQA model that unifies two key ideas in a single KBQA architecture: (a) discrimination over candidate logical forms, rather than generating these, for handling schema-related unanswerability, and (b) sketch-filling-based construction of candidate logical forms for handling data-related unaswerability. Our results show that RetinaQA significantly outperforms adaptations of state-of-the-art KBQA models in handling both answerable and unanswerable questions and demonstrates robustness across all categories of unanswerability. Notably, RetinaQA also sets a new state-of-the-art for answerable KBQA, surpassing existing models.