# Question Answering through Transfer Learning from Large Fine-grained Supervision Data

arXiv: https://arxiv.org/abs/1702.02171 · HTML: https://mlsanity.com/paper/1702.02171/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2017.

## Built on by (most cited first, 9 of 9)

- [From LSAT: The Progress and Challenges of Complex Reasoning](https://mlsanity.com/paper/2108.00648/) (2021)
- [Gradual Fine-Tuning for Low-Resource Domain Adaptation](https://mlsanity.com/paper/2103.02205/) (2021)
- [T-RAG: Lessons from the LLM Trenches](https://mlsanity.com/paper/2402.07483/) (2024)
- [On the Usability of Transformers-based models for a French Question-Answering task](https://mlsanity.com/paper/2207.09150/) (2022)
- [Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctness](https://mlsanity.com/paper/2208.04125/) (2022)
- [Improving Question Answering Performance Using Knowledge Distillation and Active Learning](https://mlsanity.com/paper/2109.12662/) (2021)
- [Auto-Transfer: Learning to Route Transferrable Representations](https://mlsanity.com/paper/2202.01011/) (2022)
- [Learning to Rank Question Answer Pairs with Bilateral Contrastive Data Augmentation](https://mlsanity.com/paper/2106.11096/) (2021)
- [Do LLMs Align with My Task? Evaluating Text-to-SQL via Dataset Alignment](https://mlsanity.com/paper/2510.04919/) (2025)

## Abstract (arXiv)

We show that the task of question answering (QA) can significantly benefit from the transfer learning of models trained on a different large, fine-grained QA dataset. We achieve the state of the art in two well-studied QA datasets, WikiQA and SemEval-2016 (Task 3A), through a basic transfer learning technique from SQuAD. For WikiQA, our model outperforms the previous best model by more than 8%. We demonstrate that finer supervision provides better guidance for learning lexical and syntactic information than coarser supervision, through quantitative results and visual analysis. We also show that a similar transfer learning procedure achieves the state of the art on an entailment task.