# Parameter-Efficient Abstractive Question Answering over Tables or Text

arXiv: https://arxiv.org/abs/2204.03357 · HTML: https://mlsanity.com/paper/2204.03357/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 7 Apr 2022.

## Builds on (most cited first, 29 of 29)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [AdapterDrop: On the Efficiency of Adapters in Transformers](https://mlsanity.com/paper/2010.11918/) (2020)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting](https://mlsanity.com/paper/2004.12651/) (2020)
- [Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2004.03829/) (2020)
- [Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems](https://mlsanity.com/paper/1508.01745/) (2015)
- [HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation](https://mlsanity.com/paper/2108.06712/) (2021)
- [Open Domain Question Answering over Tables via Dense Retrieval](https://mlsanity.com/paper/2103.12011/) (2021)
- [Commonsense for Generative Multi-Hop Question Answering Tasks](https://mlsanity.com/paper/1809.06309/) (2018)
- [AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry](https://mlsanity.com/paper/2106.12944/) (2021)
- [Incorporating BERT into Parallel Sequence Decoding with Adapters](https://mlsanity.com/paper/2010.06138/) (2020)
- [Neural Generative Question Answering](https://mlsanity.com/paper/1512.01337/) (2015)
- [DS-TOD: Efficient Domain Specialization for Task Oriented Dialog](https://mlsanity.com/paper/2110.08395/) (2021)
- [Summarizing and Exploring Tabular Data in Conversational Search](https://mlsanity.com/paper/2005.11490/) (2020)
- [Learning Recurrent Span Representations for Extractive Question Answering](https://mlsanity.com/paper/1611.01436/) (2016)
- [Multi-style Generative Reading Comprehension](https://mlsanity.com/paper/1901.02262/) (2019)
- [A Comparative Study of Transformer-Based Language Models on Extractive Question Answering](https://mlsanity.com/paper/2110.03142/) (2021)
- [QRFA: A Data-Driven Model of Information-Seeking Dialogues](https://mlsanity.com/paper/1812.10720/) (2018)

## Built on by (most cited first, 11 of 11)

- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering](https://mlsanity.com/paper/2305.12820/) (2023)
- [FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answering](https://mlsanity.com/paper/2305.04329/) (2023)
- [CABINET: Content Relevance based Noise Reduction for Table Question Answering](https://mlsanity.com/paper/2402.01155/) (2024)
- [SheetAgent: Towards A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models](https://mlsanity.com/paper/2403.03636/) (2024)
- [FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answering](https://mlsanity.com/paper/2306.05523/) (2023)
- [QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs](https://mlsanity.com/paper/2405.05109/) (2024)
- [Table Question Answering for Low-resourced Indic Languages](https://mlsanity.com/paper/2410.03576/) (2024)
- [Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance](https://mlsanity.com/paper/2506.04427/) (2025)
- [Parameter-Efficient Sparse Retrievers and Rerankers using Adapters](https://mlsanity.com/paper/2303.13220/) (2023)
- [MedLogic-AQA: Enhancing Medical Question Answering with Abstractive Models Focusing on Logical Structures](https://mlsanity.com/paper/2410.15463/) (2024)

## Abstract (arXiv)

A long-term ambition of information seeking QA systems is to reason over multi-modal contexts and generate natural answers to user queries. Today, memory intensive pre-trained language models are adapted to downstream tasks such as QA by fine-tuning the model on QA data in a specific modality like unstructured text or structured tables. To avoid training such memory-hungry models while utilizing a uniform architecture for each modality, parameter-efficient adapters add and train small task-specific bottle-neck layers between transformer layers. In this work, we study parameter-efficient abstractive QA in encoder-decoder models over structured tabular data and unstructured textual data using only 1.5% additional parameters for each modality. We also ablate over adapter layers in both encoder and decoder modules to study the efficiency-performance trade-off and demonstrate that reducing additional trainable parameters down to 0.7%-1.0% leads to comparable results. Our models out-perform current state-of-the-art models on tabular QA datasets such as Tablesum and FeTaQA, and achieve comparable performance on a textual QA dataset such as NarrativeQA using significantly less trainable parameters than fine-tuning.