I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models
We explored cultural biases-individualism vs. collectivism-in ChatGPT across three Western languages (i.e., English, German, and French) and three Eastern languages (i.e., Chinese, Japanese, and Korean). When ChatGPT adopted an individualistic persona in Western languages, its collectivism scores (i.e., out-group values) exhibited a more negative trend, surpassing their positive orientation towards individualism (i.e., in-group values). Conversely, when a collectivistic persona was assigned to ChatGPT in Eastern languages, a similar pattern emerged with more negative responses toward individualism (i.e., out-group values) as compared to collectivism (i.e., in-group values). The results indicate that when imbued with a particular social identity, ChatGPT discerns in-group and out-group, embracing in-group values while eschewing out-group values. Notably, the negativity towards the out-group, from which prejudices and discrimination arise, exceeded the positivity towards the in-group. The experiment was replicated in the political domain, and the results remained consistent. Furthermore, this replication unveiled an intrinsic Democratic bias in Large Language Models (LLMs), aligning with earlier findings and providing integral insights into mitigating such bias through prompt engineering. Extensive robustness checks were performed using varying hyperparameter and persona setup methods, with or without social identity labels, across other popular language models.
Code (0)
등록된 구현이 없습니다.
Tasks
Prompt EngineeringSimilar Papers 제목 키워드 기반
Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption
Drawing parallels between human cognition and artificial intelligence, we explored how large language models (LLMs) internalize identities imposed by targeted prompts. Informed by Social Identity Theory, these identity a…
Debiasing Personal Identities in Toxicity Classification
As Machine Learning models continue to be relied upon for making automated decisions, the issue of model bias becomes more and more prevalent. In this paper, we approach training a text classifica-tion model and optimize…
BIG-bench Machine LearningClassificationGeneral ClassificationDecomposition Attacks Across Unlinkable Identities: Limits of Stateful Defenses for LLM Services
Most large language model services use stateless defenses, which judge only the current request, to refuse harmful tasks. Decomposition attacks exploit this limitation by splitting a harmful task into individually permis…
Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation
Large language models (LLMs) have been shown to exhibit social bias, however, bias towards non-protected stigmatized identities remain understudied. Furthermore, what social features of stigmas are associated with bias i…
Social Bias Probing: Fairness Benchmarking for Language Models
While the impact of social biases in language models has been recognized, prior methods for bias evaluation have been limited to binary association tests on small datasets, limiting our understanding of bias complexities…
BenchmarkingFairnessProbing Language Models