Cultural Value Differences of LLMs: Prompt, Language, and Model Size

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhong, Qishuai, Yun, Yike, Sun, Aixin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911965517971456
author Zhong, Qishuai
Yun, Yike
Sun, Aixin
author_facet Zhong, Qishuai
Yun, Yike
Sun, Aixin
contents Our study aims to identify behavior patterns in cultural values exhibited by large language models (LLMs). The studied variants include question ordering, prompting language, and model size. Our experiments reveal that each tested LLM can efficiently behave with different cultural values. More interestingly: (i) LLMs exhibit relatively consistent cultural values when presented with prompts in a single language. (ii) The prompting language e.g., Chinese or English, can influence the expression of cultural values. The same question can elicit divergent cultural values when the same LLM is queried in a different language. (iii) Differences in sizes of the same model (e.g., Llama2-7B vs 13B vs 70B) have a more significant impact on their demonstrated cultural values than model differences (e.g., Llama2 vs Mixtral). Our experiments reveal that query language and model size of LLM are the main factors resulting in cultural value differences.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16891
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cultural Value Differences of LLMs: Prompt, Language, and Model Size
Zhong, Qishuai
Yun, Yike
Sun, Aixin
Computers and Society
Computation and Language
Our study aims to identify behavior patterns in cultural values exhibited by large language models (LLMs). The studied variants include question ordering, prompting language, and model size. Our experiments reveal that each tested LLM can efficiently behave with different cultural values. More interestingly: (i) LLMs exhibit relatively consistent cultural values when presented with prompts in a single language. (ii) The prompting language e.g., Chinese or English, can influence the expression of cultural values. The same question can elicit divergent cultural values when the same LLM is queried in a different language. (iii) Differences in sizes of the same model (e.g., Llama2-7B vs 13B vs 70B) have a more significant impact on their demonstrated cultural values than model differences (e.g., Llama2 vs Mixtral). Our experiments reveal that query language and model size of LLM are the main factors resulting in cultural value differences.
title Cultural Value Differences of LLMs: Prompt, Language, and Model Size
topic Computers and Society
Computation and Language
url https://arxiv.org/abs/2407.16891