# Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data

arXiv: https://arxiv.org/abs/2505.11900 · HTML: https://mlsanity.com/paper/2505.11900/

## Key facts

- Cited by 2 papers 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 (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective](https://mlsanity.com/paper/2205.04733/) (2022)
- [Conversational Question Answering on Heterogeneous Sources](https://mlsanity.com/paper/2204.11677/) (2022)
- [A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE](https://mlsanity.com/paper/2403.10407/) (2024)
- [Querying Large Language Models with SQL](https://mlsanity.com/paper/2304.00472/) (2023)
- [Faithful Temporal Question Answering over Heterogeneous Sources](https://mlsanity.com/paper/2402.15400/) (2024)
- [SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing](https://mlsanity.com/paper/2406.00562/) (2024)
- [TimelineQA: A Benchmark for Question Answering over Timelines](https://mlsanity.com/paper/2306.01069/) (2023)

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

- [Deep Research: A Systematic Survey](https://mlsanity.com/paper/2512.02038/) (2025)
- [The ReQAP System for Question Answering over Personal Information](https://mlsanity.com/paper/2508.06880/) (2025)

## 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.