Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data
Not on the map. Why?
Abstract (arXiv)
Question answering over mixed sources, like text and tables, has been advanced by verbalizing all contents and encoding it with a language model. A prominent case of such heterogeneous data is personal information: user devices log vast amounts of data every day, such as calendar entries, workout statistics, shopping records, streaming history, and more. Information needs range from simple look-ups to queries of analytical nature. The challenge is to provide humans with convenient access with small footprint, so that all personal data stays on the user devices. We present ReQAP, a novel method that creates an executable operator tree for a given question, via recursive decomposition. Operators are designed to enable seamless integration of structured and unstructured sources, and the execution of the operator tree yields a traceable answer. We further release the PerQA benchmark, with persona-based data and questions, covering a diverse spectrum of realistic user needs.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 17 of its 39 references that are in the map. First posted on arXiv 17 May 2025.
Builds on
17 of 39 references.
References · 17
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
- 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 737
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
- 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 398
- 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
- 2020Pretrained Transformers for Text Ranking: BERT and Beyondcited by 267
- 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 235
- 2022From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effectivecited by 98
- 2022Conversational Question Answering on Heterogeneous Sourcescited by 26
5 more
- 2024A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADEcited by 18
- 2023Querying Large Language Models with SQLcited by 14
- 2024Faithful Temporal Question Answering over Heterogeneous Sourcescited by 13
- 2024SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsingcited by 11
- 2023TimelineQA: A Benchmark for Question Answering over Timelinescited by 10
Built on by
Citing papers per year: 2025: 1.
1 paper.