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

Source: [QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering](<https://www.sota2.com/research/paper/68fa73091e209131cea5a010>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:40:28.783Z

Authors: Sheng Ouyang, Jianzong Wang, Yong Zhang, Zhitao Li, Ziqi Liang, Xulong Zhang, Ning Cheng, Jing Xiao

Published: 2024-04-30T07:34:42.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2404.19316>)

[PDF](<https://arxiv.org/pdf/2404.19316.pdf>)