An official website of the United States government
Mental health stigma prevents many individuals from receiving the appropriate care, and social psychology studies have shown that mental health tends to be overlooked in men. In this work, we investigate gendered mental health stigma in masked language models. In doing so, we operationalize mental health stigma by developing a framework grounded in psychology research: we use clinical psychology literature to curate prompts, then evaluate the models’ propensity to generate gendered words. We find that masked language models capture societal stigma about gender in mental health: models are consistently more likely to predict female subjects than male in sentences about having a mental health condition (32% vs. 19%), and this disparity is exacerbated for sentences that indicate treatment-seeking behavior. Furthermore, we find that different models capture dimensions of stigma differently for men and women, associating stereotypes like anger, blame, and pity more with women with mental health conditions than with men. In showing the complex nuances of models’ gendered mental health stigma, we demonstrate that context and overlapping dimensions of identity are important considerations when assessing computational models’ social biases.
more »
« less
Mental Health Stigma across Diverse Genders in Large Language Models
Mental health stigma manifests differently for different genders, often being more associated with women and overlooked with men. Prior work in NLP has shown that gendered mental health stigmas are captured in large language models (LLMs). However, in the last year, LLMs have changed drastically: newer, generative models not only require different methods for measuring bias, but they also have become widely popular in society, interacting with millions of users and increasing the stakes of perpetuating gendered mental health stereotypes. In this paper, we examine gendered mental health stigma in GPT3.5-Turbo, the model that powers OpenAI’s popular ChatGPT. Building off of prior work, we conduct both quantitative and qualitative analyses to measure GPT3.5-Turbo’s bias between binary genders, as well as to explore its behavior around non-binary genders, in conversations about mental health. We find that, though GPT3.5-Turbo refrains from explicitly assuming gender, it still contains implicit gender biases when asked to complete sentences about mental health, consistently preferring female names over male names. Additionally, though GPT3.5-Turbo shows awareness of the nuances of non-binary people’s experiences, it often over-fixates on non-binary gender identities in free-response prompts. Our preliminary results demonstrate that while modern generative LLMs contain safeguards against blatant gender biases and have progressed in their inclusiveness of non-binary identities, they still implicitly encode gendered mental health stigma, and thus risk perpetuating harmful stereotypes in mental health contexts.
more »
« less
- Award ID(s):
- 2142739
- PAR ID:
- 10520213
- Publisher / Repository:
- Machine Learning for Cognitive and Mental Health Workshop (ML4CMH), AAAI 2024
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Mental health stigma prevents many individuals from receiving the appropriate care, and social psychology studies have shown that mental health tends to be overlooked in men. In this work, we investigate gendered mental health stigma in masked language models. In doing so, we operationalize mental health stigma by developing a framework grounded in psychology research: we use clinical psychology literature to curate prompts, then evaluate the models’ propensity to generate gendered words. We find that masked language models capture societal stigma about gender in mental health: models are consistently more likely to predict female subjects than male in sentences about having a mental health condition (32% vs. 19%), and this disparity is exacerbated for sentences that indicate treatment-seeking behavior. Furthermore, we find that different models capture dimensions of stigma differently for men and women, associating stereotypes like anger, blame, and pity more with women with mental health conditions than with men. In showing the complex nuances of models’ gendered mental health stigma, we demonstrate that context and overlapping dimensions of identity are important considerations when assessing computational models’ social biases.more » « less
-
To recognize and mitigate the harms of generative AI systems, it is crucial to consider who is represented in the outputs of generative AI systems and how people are represented. A critical gap emerges when naively improving who is represented, as this does not imply bias mitigation efforts have been applied to address how people are represented. We critically examined this by investigating gender representation in occupation across state-of-the-art large language models. We first show evidence suggesting that over time there have been interventions to models altering the resulting gender distribution, and we find that women are more represented than men when models are prompted to generate biographies or personas. We then demonstrate that representational biases persist in how different genders are represented by examining statistically significant word differences across genders. This results in a proliferation of representational harms, stereotypes, and neoliberalism ideals that, despite existing interventions to increase female representation, reinforce existing systems of oppression.more » « less
-
We investigated how gender is represented in children’s books using a novel 200,000 word corpus comprising 247 popular, contemporary books for young children. Using human judgments and word co-occurrence data, we quantified gender biases of words in individual books and in the whole corpus. We find that children’s books contain many words that adults judge as gendered. Semantic analyses based on co-occurrence data yielded word clusters related to gender stereotypes (e.g., feminine: emotions; masculine: tools). Co-occurrence data also indicate that many books instantiate gender stereotypes identified in other research (e.g., girls are better at reading and boys at math). Finally, we used large-scale data to estimate the gender distribution of the audience for individual books, and find that children are more often exposed to gender stereotypes for their own gender. Together the data suggest that children’s books may be an early source of gender associations and stereotypes.more » « less
-
Abstract Informed by decades of literature, water interventions increasingly deploy “gender‐sensitive” or even “gender transformative” approaches that seek to redress the disproportionate harms women face from water insecurity. These efforts recognize the role of gendered social norms and unequal power relations but often focus narrowly on the differences and dynamics between cisgender (cis) men and women. This approach renders less visible the ways that living with water insecurity can differentially affect all individuals through the dynamics of gender, sexuality, and linked intersecting identities. Here, we first share a conceptual toolkit that explains gender as fluid, negotiated, and diverse beyond the cis‐binary. Using this as a starting point, we then review what is known and can be theorized from current literature, identifying limited observations from water‐insecure communities to identify examples of contexts where gendered mechanisms (such as social norms) differentiate experiences of water insecurity, such as elevating risks of social stigma, physical harm, or psychological distress. We then apply this approach to consider expanded ways to include transgender, non‐binary, and gender and sexual diversity to deepen, nuance and expand key thematics and approaches for water insecurity research. Reconceptualizing gender in these ways widens theoretical possibilities, changes how we collect data, and imagines new possibilities for effective and just water interventions. This article is categorized under:Human Water > Value of WaterEngineering Water > Water, Health, and SanitationHuman Water > Water as Imagined and RepresentedHuman Water > Methodsmore » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Workshop Report:
- The DOI is not currently available.
