Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representation

• URL: http://arxiv.org/abs/2410.10489v1
• Date: Mon, 14 Oct 2024 13:33:00 GMT
• Title: Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representation
• Authors: Sharif Kazemi, Gloria Gerhardt, Jonty Katz, Caroline Ida Kuria, Estelle Pan, Umang Prabhakar,
• Abstract summary: We show that the ability of GPT-4o to reflect societal values of a country correlates with the availability of digital resources in that language. Weaker performance in low-resource languages, especially prominent in the Global South, may worsen digital divides.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The training data for LLMs embeds societal values, increasing their familiarity with the language's culture. Our analysis found that 44% of the variance in the ability of GPT-4o to reflect the societal values of a country, as measured by the World Values Survey, correlates with the availability of digital resources in that language. Notably, the error rate was more than five times higher for the languages of the lowest resource compared to the languages of the highest resource. For GPT-4-turbo, this correlation rose to 72%, suggesting efforts to improve the familiarity with the non-English language beyond the web-scraped data. Our study developed one of the largest and most robust datasets in this topic area with 21 country-language pairs, each of which contain 94 survey questions verified by native speakers. Our results highlight the link between LLM performance and digital data availability in target languages. Weaker performance in low-resource languages, especially prominent in the Global South, may worsen digital divides. We discuss strategies proposed to address this, including developing multilingual LLMs from the ground up and enhancing fine-tuning on diverse linguistic datasets, as seen in African language initiatives.

Related papers

• BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages [93.92804151830744]
  We present BRIGHTER, a collection of emotion-annotated datasets in 28 different languages. We describe the data collection and annotation processes and the challenges of building these datasets. We show that BRIGHTER datasets are a step towards bridging the gap in text-based emotion recognition.
  arXiv  Detail & Related papers  (2025-02-17T15:39:50Z)
• INJONGO: A Multicultural Intent Detection and Slot-filling Dataset for 16 African Languages [15.983678567785004]
  Slot-filling and intent detection are well-established tasks in Conversational AI. We introduce Injongo -- a multicultural, open-source benchmark dataset for 16 African languages. We show the advantage of leveraging African-cultural utterances over Western-centric utterances for improving cross-lingual transfer.
  arXiv  Detail & Related papers  (2025-02-13T23:17:10Z)
• Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments [0.9214083577876088]
  This paper creates approximately 1 million human-translated words of new benchmark data in 8 low-resource African languages. Our benchmarks are translations of Winogrande and three sections of MMLU: college medicine, clinical knowledge, and virology. Using the benchmarks translated, we report previously unknown performance gaps between state-of-the-art (SOTA) LLMs in English and African languages.
  arXiv  Detail & Related papers  (2024-12-16T23:50:21Z)
• Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages [55.36534539177367]
  This paper introduces Pangea, a multilingual multimodal large language model (MLLM) trained on a diverse 6M instruction dataset spanning 39 languages. P Pangea significantly outperforms existing open-source models in multilingual settings and diverse cultural contexts. We fully open-source our data, code, and trained checkpoints, to facilitate the development of inclusive and robust multilingual MLLMs.
  arXiv  Detail & Related papers  (2024-10-21T16:19:41Z)
• Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settings [12.507989493130175]
  Large language models (LLMs) have garnered significant interest in natural language processing (NLP) Recent studies have highlighted the limitations of LLMs in low-resource languages. We present datasets for sentiment and hate speech tasks by translating from English to Bangla, Hindi, and Urdu.
  arXiv  Detail & Related papers  (2024-08-05T05:09:23Z)
• Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon [78.12363425794214]
  We focus on zero-shot sentiment analysis tasks across 34 languages, including 6 high/medium-resource languages, 25 low-resource languages, and 3 code-switching datasets. We demonstrate that pretraining using multilingual lexicons, without using any sentence-level sentiment data, achieves superior zero-shot performance compared to models fine-tuned on English sentiment datasets.
  arXiv  Detail & Related papers  (2024-02-03T10:41:05Z)
• 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)
• NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages [54.808217147579036]
  We conduct a case study on Indonesian local languages. We compare the effectiveness of online scraping, human translation, and paragraph writing by native speakers in constructing datasets. Our findings demonstrate that datasets generated through paragraph writing by native speakers exhibit superior quality in terms of lexical diversity and cultural content.
  arXiv  Detail & Related papers  (2023-09-19T14:42:33Z)
• 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)
• LLM-powered Data Augmentation for Enhanced Cross-lingual Performance [24.20730298894794]
  This paper explores the potential of leveraging Large Language Models (LLMs) for data augmentation in commonsense reasoning datasets. To achieve this, we utilise several LLMs, namely Dolly-v2, StableVicuna, ChatGPT, and GPT-4, to augment three datasets: XCOPA, XWinograd, and XStoryCloze. We evaluate the effectiveness of fine-tuning smaller multilingual models, mBERT and XLMR, using the synthesised data.
  arXiv  Detail & Related papers  (2023-05-23T17:33:27Z)
• DN at SemEval-2023 Task 12: Low-Resource Language Text Classification via Multilingual Pretrained Language Model Fine-tuning [0.0]
  Most existing models and datasets for sentiment analysis are developed for high-resource languages, such as English and Chinese. The AfriSenti-SemEval 2023 Shared Task 12 aims to fill this gap by evaluating sentiment analysis models on low-resource African languages. We present our solution to the shared task, where we employed different multilingual XLM-R models with classification head trained on various data.
  arXiv  Detail & Related papers  (2023-05-04T07:28:45Z)

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.