Evaluating and Mitigating Linguistic Discrimination in Large Language Models

• URL: http://arxiv.org/abs/2404.18534v2
• Date: Fri, 10 May 2024 07:09:02 GMT
• Title: Evaluating and Mitigating Linguistic Discrimination in Large Language Models
• Authors: Guoliang Dong, Haoyu Wang, Jun Sun, Xinyu Wang,
• Abstract summary: Large language models (LLMs) can exhibit linguistic discrimination due to uneven distribution of training data across languages. We propose LDFighter, a similarity-based voting, to mitigate the linguistic discrimination in LLMs.
• Score: 7.634003893271555
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: By training on text in various languages, large language models (LLMs) typically possess multilingual support and demonstrate remarkable capabilities in solving tasks described in different languages. However, LLMs can exhibit linguistic discrimination due to the uneven distribution of training data across languages. That is, LLMs are hard to keep the consistency of responses when faced with the same task but depicted in different languages. In this study, we first explore the consistency in the LLMs' outputs responding to queries in various languages from two aspects: safety and quality. We conduct this analysis with two datasets (AdvBench and NQ) based on four LLMs (Llama2-13b, Gemma-7b, GPT-3.5-turbo and Gemini-pro). The results show that LLMs exhibit stronger human alignment capabilities with queries in English, French, Russian, and Spanish (only 1.04\% of harmful queries successfully jailbreak on average) compared to queries in Bengali, Georgian, Nepali and Maithili (27.7\% of harmful queries jailbreak successfully on average). Moreover, for queries in English, Danish, Czech and Slovenian, LLMs tend to produce responses with a higher quality (with 0.1494 $F_1$ score on average) compared to the other languages. Upon these findings, we propose LDFighter, a similarity-based voting, to mitigate the linguistic discrimination in LLMs. LDFighter ensures consistent service for different language speakers. We evaluate LDFighter with both benign queries and harmful queries. The results show that LDFighter not only significantly reduces the jailbreak success rate but also improve the response quality on average, demonstrating its effectiveness.

Related papers

• Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results [16.391752298134474]
  We study the performance of different large language models (LLMs) across languages.<n>We find that there exists a non-negligible and consistent gap in the performance of the models across languages.<n>We propose a method for automatic quality assurance to address the first issue at scale, and give recommendations to address the second one.
  arXiv  Detail & Related papers  (2025-11-07T11:30:10Z)
• Do LLMs exhibit the same commonsense capabilities across languages? [4.177608674029413]
  We introduce MULTICOM, a novel benchmark that extends the COCOTEROS dataset to four languages: English, Spanish, Dutch, and Valencian.<n>The task involves generating a commonsensical sentence that includes a given triplet of words.<n>Results consistently show superior performance in English, with significantly lower performance in less-resourced languages.
  arXiv  Detail & Related papers  (2025-09-08T07:47:00Z)
• mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks [11.996399504336624]
  We introduce mSTEB, a new benchmark to evaluate the performance of large language models (LLMs) on a wide range of tasks.<n>We evaluate the performance of leading LLMs such as Gemini 2.0 Flash and GPT-4o (Audio) and state-of-the-art open models such as Qwen 2 Audio and Gemma 3 27B.
  arXiv  Detail & Related papers  (2025-06-10T03:15:08Z)
• Found in Translation: Measuring Multilingual LLM Consistency as Simple as Translate then Evaluate [36.641755706551336]
  Large language models (LLMs) provide detailed and impressive responses to queries in English.<n>But are they really consistent at responding to the same query in other languages?<n>We propose a framework to evaluate LLM's cross-lingual consistency based on a simple Translate then Evaluate strategy.
  arXiv  Detail & Related papers  (2025-05-28T06:00:21Z)
• Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models [55.14276067678253]
  This paper introduces a novel methodology for efficiently identifying inherent cross-lingual weaknesses in Large Language Models (LLMs)<n>We construct a new dataset of over 6,000 bilingual pairs across 16 languages using this methodology, demonstrating its effectiveness in revealing weaknesses even in state-of-the-art models.<n>Further experiments investigate the relationship between linguistic similarity and cross-lingual weaknesses, revealing that linguistically related languages share similar performance patterns.
  arXiv  Detail & Related papers  (2025-05-24T12:31:27Z)
• PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts [79.84059473102778]
  PolyMath is a multilingual mathematical reasoning benchmark covering 18 languages and 4 easy-to-hard difficulty levels. Our benchmark ensures difficulty comprehensiveness, language diversity, and high-quality translation.
  arXiv  Detail & Related papers  (2025-04-25T15:39:04Z)
• Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization [108.6908427615402]
  Cross-lingual summarization ( CLS) aims to generate a summary for the source text in a different target language. Currently, instruction-tuned large language models (LLMs) excel at various English tasks. Recent studies have shown that LLMs' performance on CLS tasks remains unsatisfactory even with few-shot settings.
  arXiv  Detail & Related papers  (2024-10-26T00:39:44Z)
• Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings [12.507989493130175]
  GPT-4, Llama 2, and Gemini are evaluated for their effectiveness in English compared to other low-resource languages from South Asia. Findings suggest GPT-4 outperformed Llama 2 and Gemini in all five prompt settings and across all languages.
  arXiv  Detail & Related papers  (2024-10-17T02:12:30Z)
• INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages [25.402797722575805]
  Indic QA Benchmark is a dataset for context grounded question answering in 11 major Indian languages. Evaluations revealed weak performance in low resource languages due to a strong English language bias in their training data. We also investigated the Translate Test paradigm,where inputs are translated to English for processing and the results are translated back into the source language for output.
  arXiv  Detail & Related papers  (2024-07-18T13:57:16Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts. We find that Llama Instruct and Mistral models exhibit high degrees of language confusion. We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:03:51Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, effectively being crosslingual? This study evaluates six state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages [51.301942056881146]
  We investigate how large language models (LLMs) function as rerankers in cross-lingual information retrieval systems for African languages. Our implementation covers English and four African languages (Hausa, Somali, Swahili, and Yoruba) We examine cross-lingual reranking with queries in English and passages in the African languages.
  arXiv  Detail & Related papers  (2023-12-26T18:38:54Z)
• BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP [17.362068473064717]
  Large Language Models (LLMs) have emerged as one of the most important breakthroughs in NLP. This paper introduces BenLLM-Eval, which consists of a comprehensive evaluation of LLMs to benchmark their performance in the Bengali language. Our experimental results demonstrate that while in some Bengali NLP tasks, zero-shot LLMs could achieve performance on par, or even better than current SOTA fine-tuned models.
  arXiv  Detail & Related papers  (2023-09-22T20:29:34Z)
• Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts [75.33019401706188]
  Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. We propose to assemble synthetic exemplars from a diverse set of high-resource languages to prompt the LLMs to translate from any language into English. Our unsupervised prompting method performs on par with supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages.
  arXiv  Detail & Related papers  (2023-06-20T08:27:47Z)
• Multilingual Large Language Models Are Not (Yet) Code-Switchers [41.47534626749588]
  Large Language Models (LLMs) have recently shown great capabilities in a wide range of tasks. The practice of alternating languages within an utterance remains relatively uncharted. We argue that current "multilingualism" in LLMs does not inherently imply proficiency with code-switching texts.
  arXiv  Detail & Related papers  (2023-05-23T16:50:48Z)
• Chain-of-Dictionary Prompting Elicits Translation in Large Language Models [100.47154959254937]
  Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) We present a novel method, CoD, which augments LLMs with prior knowledge with the chains of multilingual dictionaries for a subset of input words to elicit translation abilities.
  arXiv  Detail & Related papers  (2023-05-11T05:19:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.