Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption

• URL: http://arxiv.org/abs/2409.03843v1
• Date: Thu, 5 Sep 2024 18:08:47 GMT
• Title: Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption
• Authors: Wenchao Dong, Assem Zhunis, Dongyoung Jeong, Hyojin Chin, Jiyoung Han, Meeyoung Cha,
• Abstract summary: We show that outgroup bias manifests as strongly as ingroup favoritism. Our findings highlight the potential to develop more equitable and balanced language models.
• Score: 10.35915254696156
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 assignments lead LLMs to distinguish between "we" (the ingroup) and "they" (the outgroup). This self-categorization generates both ingroup favoritism and outgroup bias. Nonetheless, existing literature has predominantly focused on ingroup favoritism, often overlooking outgroup bias, which is a fundamental source of intergroup prejudice and discrimination. Our experiment addresses this gap by demonstrating that outgroup bias manifests as strongly as ingroup favoritism. Furthermore, we successfully mitigated the inherent pro-liberal, anti-conservative bias in LLMs by guiding them to adopt the perspectives of the initially disfavored group. These results were replicated in the context of gender bias. Our findings highlight the potential to develop more equitable and balanced language models.

Related papers

• The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models [58.130894823145205]
  We center transgender, nonbinary, and other gender-diverse identities to investigate how alignment procedures interact with pre-existing gender-diverse bias. Our findings reveal that DPO-aligned models are particularly sensitive to supervised finetuning. We conclude with recommendations tailored to DPO and broader alignment practices.
  arXiv  Detail & Related papers  (2024-11-06T06:50:50Z)
• The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models [78.69526166193236]
  Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases. We propose sc Social Bias Neurons to accurately pinpoint units (i.e., neurons) in a language model that can be attributed to undesirable behavior, such as social bias. As measured by prior metrics from StereoSet, our model achieves a higher degree of fairness while maintaining language modeling ability with low cost.
  arXiv  Detail & Related papers  (2024-06-14T15:41:06Z)
• Protected group bias and stereotypes in Large Language Models [2.1122940074160357]
  This paper investigates the behavior of Large Language Models (LLMs) in the domains of ethics and fairness. We find bias across minoritized groups, but in particular in the domains of gender and sexuality, as well as Western bias.
  arXiv  Detail & Related papers  (2024-03-21T00:21:38Z)
• I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models [11.77633171656753]
  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. 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
  arXiv  Detail & Related papers  (2024-02-16T03:54:48Z)
• Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes [73.12947922129261]
  We leverage the zero-shot capabilities of large language models to reduce stereotyping. We show that self-debiasing can significantly reduce the degree of stereotyping across nine different social groups. We hope this work opens inquiry into other zero-shot techniques for bias mitigation.
  arXiv  Detail & Related papers  (2024-02-03T01:40:11Z)
• On the steerability of large language models toward data-driven personas [98.9138902560793]
  Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs.
  arXiv  Detail & Related papers  (2023-11-08T19:01:13Z)
• Generative Language Models Exhibit Social Identity Biases [17.307292780517653]
  We investigate whether ingroup solidarity and outgroup hostility, fundamental social identity biases, are present in 56 large language models. We find that almost all foundational language models and some instruction fine-tuned models exhibit clear ingroup-positive and outgroup-negative associations when prompted to complete sentences. Our findings suggest that modern language models exhibit fundamental social identity biases to a similar degree as humans.
  arXiv  Detail & Related papers  (2023-10-24T13:17:40Z)
• Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models [0.0]
  This paper investigates bias along less-studied but still consequential, dimensions, such as age and beauty. We ask whether LLMs hold wide-reaching biases of positive or negative sentiment for specific social groups similar to the "what is beautiful is good" bias found in people in experimental psychology.
  arXiv  Detail & Related papers  (2023-09-16T07:07:04Z)
• Evaluating Biased Attitude Associations of Language Models in an Intersectional Context [2.891314299138311]
  Language models are trained on large-scale corpora that embed implicit biases documented in psychology. We study biases related to age, education, gender, height, intelligence, literacy, race, religion, sex, sexual orientation, social class, and weight. We find that language models exhibit the most biased attitudes against gender identity, social class, and sexual orientation signals in language.
  arXiv  Detail & Related papers  (2023-07-07T03:01:56Z)
• "I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation [69.25368160338043]
  Transgender and non-binary (TGNB) individuals disproportionately experience discrimination and exclusion from daily life. We assess how the social reality surrounding experienced marginalization of TGNB persons contributes to and persists within Open Language Generation. We introduce TANGO, a dataset of template-based real-world text curated from a TGNB-oriented community.
  arXiv  Detail & Related papers  (2023-05-17T04:21:45Z)
• Fair Group-Shared Representations with Normalizing Flows [68.29997072804537]
  We develop a fair representation learning algorithm which is able to map individuals belonging to different groups in a single group. We show experimentally that our methodology is competitive with other fair representation learning algorithms.
  arXiv  Detail & Related papers  (2022-01-17T10:49:49Z)

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.