# Context-Aware Answer Extraction in Question Answering

arXiv: https://arxiv.org/abs/2011.02687 · HTML: https://mlsanity.com/paper/2011.02687/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2020.

## Built on by (most cited first, 13 of 13)

- [VLSP 2021 - ViMRC Challenge: Vietnamese Machine Reading Comprehension](https://mlsanity.com/paper/2203.11400/) (2022)
- [Hybrid Graphs for Table-and-Text based Question Answering using LLMs](https://mlsanity.com/paper/2501.17767/) (2025)
- [Bridging the Language Gap: Knowledge Injected Multilingual Question Answering](https://mlsanity.com/paper/2304.03159/) (2023)
- [NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering](https://mlsanity.com/paper/2211.03462/) (2022)
- [AlzheimerRAG: Multimodal Retrieval Augmented Generation for Clinical Use Cases using PubMed articles](https://mlsanity.com/paper/2412.16701/) (2024)
- [Context-guided Triple Matching for Multiple Choice Question Answering](https://mlsanity.com/paper/2109.12996/) (2021)
- [Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation](https://mlsanity.com/paper/2208.05217/) (2022)
- [Machine Reading Comprehension using Case-based Reasoning](https://mlsanity.com/paper/2305.14815/) (2023)
- [Sequencing Matters: A Generate-Retrieve-Generate Model for Building Conversational Agents](https://mlsanity.com/paper/2311.09513/) (2023)
- [How Can Context Help? Exploring Joint Retrieval of Passage and Personalized Context](https://mlsanity.com/paper/2308.13760/) (2023)
- [DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering](https://mlsanity.com/paper/2412.16694/) (2024)
- [Comparative Analysis of 47 Context-Based Question Answer Models Across 8 Diverse Datasets](https://mlsanity.com/paper/2512.00323/) (2025)
- [Improving Answer Extraction in Context-based Question Answering Systems Using LLMs](https://mlsanity.com/paper/2606.06197/) (2026)

## Abstract (arXiv)

Extractive QA models have shown very promising performance in predicting the correct answer to a question for a given passage. However, they sometimes result in predicting the correct answer text but in a context irrelevant to the given question. This discrepancy becomes especially important as the number of occurrences of the answer text in a passage increases. To resolve this issue, we propose BLANC (BLock AttentioN for Context prediction) based on two main ideas: context prediction as an auxiliary task in multi-task learning manner, and a block attention method that learns the context prediction task. With experiments on reading comprehension, we show that BLANC outperforms the state-of-the-art QA models, and the performance gap increases as the number of answer text occurrences increases. We also conduct an experiment of training the models using SQuAD and predicting the supporting facts on HotpotQA and show that BLANC outperforms all baseline models in this zero-shot setting.