# QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering

arXiv: https://arxiv.org/abs/2404.19316 · HTML: https://mlsanity.com/paper/2404.19316/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 30 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [Adversarial Training Methods for Semi-Supervised Text Classification](https://mlsanity.com/paper/1605.07725/) (2016)
- [Revisiting Pre-Trained Models for Chinese Natural Language Processing](https://mlsanity.com/paper/2004.13922/) (2020)
- [FreeLB: Enhanced Adversarial Training for Natural Language Understanding](https://mlsanity.com/paper/1909.11764/) (2019)
- [SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization](https://mlsanity.com/paper/1911.03437/) (2019)
- [The Natural Language Decathlon: Multitask Learning as Question Answering](https://mlsanity.com/paper/1806.08730/) (2018)
- [A Unified MRC Framework for Named Entity Recognition](https://mlsanity.com/paper/1910.11476/) (2019)
- [You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle](https://mlsanity.com/paper/1905.00877/) (2019)
- [Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation](https://mlsanity.com/paper/2104.08678/) (2021)
- [Adversarial Training for High-Stakes Reliability](https://mlsanity.com/paper/2205.01663/) (2022)
- [A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets](https://mlsanity.com/paper/2006.11880/) (2020)
- [Improved Text Classification via Contrastive Adversarial Training](https://mlsanity.com/paper/2107.10137/) (2021)
- [ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning](https://mlsanity.com/paper/2104.08350/) (2021)
- [PERT: Pre-training BERT with Permuted Language Model](https://mlsanity.com/paper/2203.06906/) (2022)
- [Block-Skim: Efficient Question Answering for Transformer](https://mlsanity.com/paper/2112.08560/) (2021)
- [DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications](https://mlsanity.com/paper/2004.11142/) (2020)
- [Improving Machine Reading Comprehension via Adversarial Training](https://mlsanity.com/paper/1911.03614/) (2019)

## Abstract (arXiv)

Extractive Question Answering (EQA) in Machine Reading Comprehension (MRC) often faces the challenge of dealing with semantically identical but format-variant inputs. Our work introduces a novel approach, called the ``Query Latent Semantic Calibrator (QLSC)'', designed as an auxiliary module for existing MRC models. We propose a unique scaling strategy to capture latent semantic center features of queries. These features are then seamlessly integrated into traditional query and passage embeddings using an attention mechanism. By deepening the comprehension of the semantic queries-passage relationship, our approach diminishes sensitivity to variations in text format and boosts the model's capability in pinpointing accurate answers. Experimental results on robust Question-Answer datasets confirm that our approach effectively handles format-variant but semantically identical queries, highlighting the effectiveness and adaptability of our proposed method.