# Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering

Source: [Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering](<https://www.sota2.com/research/paper/68fa6add1e209131cea2ae53>)

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

Data updated: 2025-10-25T23:35:16.571Z

Authors: Fahim Faisal, Antonios Anastasopoulos

Published: 2021-09-24T15:32:45.000Z

## Abstract

Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers of all languages, they need to operate cross-lingually. In this work we investigate the capabilities of multilingually pre-trained language models on cross-lingual QA. We find that explicitly aligning the representations across languages with a post-hoc fine-tuning step generally leads to improved performance. We additionally investigate the effect of data size as well as the language choice in this fine-tuning step, also releasing a dataset for evaluating cross-lingual QA systems. Code and dataset are publicly available here: https://github.com/ffaisal93/aligned\_qa

## 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/2109.12028>)

[PDF](<https://arxiv.org/pdf/2109.12028.pdf>)