Exploring Robustness of LLMs to Paraphrasing Based on Sociodemographic Factors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Arora, Pulkit, Karimi, Akbar, Flek, Lucie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918082306375680
author Arora, Pulkit
Karimi, Akbar
Flek, Lucie
author_facet Arora, Pulkit
Karimi, Akbar
Flek, Lucie
contents Despite their linguistic prowess, LLMs have been shown to be vulnerable to small input perturbations. While robustness to local adversarial changes has been studied, robustness to global modifications such as different linguistic styles remains underexplored. Therefore, we take a broader approach to explore a wider range of variations across sociodemographic dimensions. We extend the SocialIQA dataset to create diverse paraphrased sets conditioned on sociodemographic factors (age and gender). The assessment aims to provide a deeper understanding of LLMs in (a) their capability of generating demographic paraphrases with engineered prompts and (b) their capabilities in interpreting real-world, complex language scenarios. We also perform a reliability analysis of the generated paraphrases looking into linguistic diversity and perplexity as well as manual evaluation. We find that demographic-based paraphrasing significantly impacts the performance of language models, indicating that the subtleties of linguistic variation remain a significant challenge. We will make the code and dataset available for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2501_08276
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Robustness of LLMs to Paraphrasing Based on Sociodemographic Factors
Arora, Pulkit
Karimi, Akbar
Flek, Lucie
Computation and Language
Despite their linguistic prowess, LLMs have been shown to be vulnerable to small input perturbations. While robustness to local adversarial changes has been studied, robustness to global modifications such as different linguistic styles remains underexplored. Therefore, we take a broader approach to explore a wider range of variations across sociodemographic dimensions. We extend the SocialIQA dataset to create diverse paraphrased sets conditioned on sociodemographic factors (age and gender). The assessment aims to provide a deeper understanding of LLMs in (a) their capability of generating demographic paraphrases with engineered prompts and (b) their capabilities in interpreting real-world, complex language scenarios. We also perform a reliability analysis of the generated paraphrases looking into linguistic diversity and perplexity as well as manual evaluation. We find that demographic-based paraphrasing significantly impacts the performance of language models, indicating that the subtleties of linguistic variation remain a significant challenge. We will make the code and dataset available for future research.
title Exploring Robustness of LLMs to Paraphrasing Based on Sociodemographic Factors
topic Computation and Language
url https://arxiv.org/abs/2501.08276