arXiv subjects

Mahzarin R. Banaji

Publications and source records attributed to Mahzarin R. Banaji.

9 recordsLinked to original sources

arXiv2026

Vision-Language Models Suppress Female Representations Under Ambiguous Input

Alignment teaches vision-language models (VLMs) to avoid expressing demographic biases, and when gender is clearly visible they largely succeed. Far less is known about ambiguous inputs (a worker in full gear, a figure seen from behind), cases common in practice yet rarely studied. We find that minimal prompting pressure exposes occupation-gender defaults when prompting ambiguous input images, with models collapsing to male even for strongly female-stereotyped occupations. But do these outputs reflect what models actually encode internally? We introduce LALS (Latent Association Leaning Score), a zero-shot metric that projects visual-token activations into the model's text-embedding space to measure concept associations per token and layer. Across 15 occupations, over 800 gender-ambiguous images, and four VLMs, internal representations and outputs often become systematically decoupled: models often encode a female association internally yet output male. Layer-wise analysis reveals an asymmetric filter: male signal amplifies end-to-end while female signal peaks mid-network and is suppressed before generation. A color ablation shows that culturally loaded visual cues such as clothing color further modulate these internal associations.

cs.CV↗

arXiv2026

Large Language Models Exhibit Human-Like Bayesian Hypocrisy

Given recent achievements of large language models (LLMs), frontier models are expected to perform well on Bayesian reasoning tasks, at least as well as humans. Furthermore, there is no reason to expect that LLMs will condemn others who offer those very same Bayesian judgments, a fallibility observed in human decision-making (Cao, et al., 2019). In 5 experiments with 48 experimental conditions employing over 5,000 trials, GPT-4o and Claude 3.7 Sonnet were tested on two variations of a Bayesian reasoning task. We also assessed LLM evaluation of the competence and morality of a hypothetical person who had offered the same reasoning task as them. LLMs hovered near human performance on the Bayesian task, though their reasoning was more rule-based and rigid. Surprisingly, like humans but to a greater extent, LLMs also demonstrated the same hypocrisy in condemning others who, like them, had deployed Bayes' rule. In demonstrating Bayesian hypocrisy, LLMs highlight a humanlike error of a dissociation between self-performance and other-judgment, and caution against their use in domains where statistical fidelity and fairness norms collide.

cs.HC↗

arXiv2026

Language Models Embody and Amplify Human Cognitive Distortions: What Is to Be Done?

Human judgment is fundamentally prone to error. A promise of AI is that it will rid decisions of bias and ensure a fairer and safer world for all. Yet research unequivocally demonstrates that LLMs exhibit consequential sociocognitive biases. We alert readers that bias in AI (a) is covert and ironically a feature of alignment goals, (b) is not merely a mirror, but an amplifier of human bias, (c) intensifies across model generations, and (d) even transmits bias to humans. Given the potentially seismic and ubiquitous influence of AI on decision making, we propose countermeasures that are diagnostic, regulatory and operational.

cs.CY↗

arXiv2026

Extreme Self-Preference in Language Models

Self-preference is a fundamental feature of biological organisms. Since large language models (LLMs) lack sentience, they might be expected to avoid such distortions. Yet, across 72 experiments and ~41,000 queries, we discovered massive self-preferences in eight widely used LLMs. In word-association tasks, models overwhelmingly paired positive attributes with their own names, companies, and CEOs over those of competitors. By manipulating LLM self-identification - revealing models' true identities or ascribing false ones - we found that preferences consistently followed assigned, not true, identities. Importantly, these effects were not explained by priming or role-playing and emerged in consequential settings, when evaluating job candidates and AI technologies. These results raise critical questions about whether LLM behavior will be systematically influenced by self-preferential tendencies, including a bias toward their own operation.

cs.AI↗

arXiv2025

Kernels of Selfhood: GPT-4o shows humanlike patterns of cognitive consistency moderated by free choice

Large Language Models (LLMs) show emergent patterns that mimic human cognition. We explore whether they also mirror other, less deliberative human psychological processes. Drawing upon classical theories of cognitive consistency, two preregistered studies tested whether GPT-4o changed its attitudes toward Vladimir Putin in the direction of a positive or negative essay it wrote about the Russian leader. Indeed, GPT displayed patterns of attitude change mimicking cognitive consistency effects in humans. Even more remarkably, the degree of change increased sharply when the LLM was offered an illusion of choice about which essay (positive or negative) to write. This result suggests that GPT-4o manifests a functional analog of humanlike selfhood, although how faithfully the chatbot's behavior reflects the mechanisms of human attitude change remains to be understood.

cs.CY↗

arXiv2024

ChatGPT as Research Scientist: Probing GPT's Capabilities as a Research Librarian, Research Ethicist, Data Generator and Data Predictor

How good a research scientist is ChatGPT? We systematically probed the capabilities of GPT-3.5 and GPT-4 across four central components of the scientific process: as a Research Librarian, Research Ethicist, Data Generator, and Novel Data Predictor, using psychological science as a testing field. In Study 1 (Research Librarian), unlike human researchers, GPT-3.5 and GPT-4 hallucinated, authoritatively generating fictional references 36.0% and 5.4% of the time, respectively, although GPT-4 exhibited an evolving capacity to acknowledge its fictions. In Study 2 (Research Ethicist), GPT-4 (though not GPT-3.5) proved capable of detecting violations like p-hacking in fictional research protocols, correcting 88.6% of blatantly presented issues, and 72.6% of subtly presented issues. In Study 3 (Data Generator), both models consistently replicated patterns of cultural bias previously discovered in large language corpora, indicating that ChatGPT can simulate known results, an antecedent to usefulness for both data generation and skills like hypothesis generation. Contrastingly, in Study 4 (Novel Data Predictor), neither model was successful at predicting new results absent in their training data, and neither appeared to leverage substantially new information when predicting more versus less novel outcomes. Together, these results suggest that GPT is a flawed but rapidly improving librarian, a decent research ethicist already, capable of data generation in simple domains with known characteristics but poor at predicting novel patterns of empirical data to aid future experimentation.

cs.AI↗

arXiv2022

Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics

The statistical regularities in language corpora encode well-known social biases into word embeddings. Here, we focus on gender to provide a comprehensive analysis of group-based biases in widely-used static English word embeddings trained on internet corpora (GloVe 2014, fastText 2017). Using the Single-Category Word Embedding Association Test, we demonstrate the widespread prevalence of gender biases that also show differences in: (1) frequencies of words associated with men versus women; (b) part-of-speech tags in gender-associated words; (c) semantic categories in gender-associated words; and (d) valence, arousal, and dominance in gender-associated words. First, in terms of word frequency: we find that, of the 1,000 most frequent words in the vocabulary, 77% are more associated with men than women, providing direct evidence of a masculine default in the everyday language of the English-speaking world. Second, turning to parts-of-speech: the top male-associated words are typically verbs (e.g., fight, overpower) while the top female-associated words are typically adjectives and adverbs (e.g., giving, emotionally). Gender biases in embeddings also permeate parts-of-speech. Third, for semantic categories: bottom-up, cluster analyses of the top 1,000 words associated with each gender. The top male-associated concepts include roles and domains of big tech, engineering, religion, sports, and violence; in contrast, the top female-associated concepts are less focused on roles, including, instead, female-specific slurs and sexual content, as well as appearance and kitchen terms. Fourth, using human ratings of word valence, arousal, and dominance from a ~20,000 word lexicon, we find that male-associated words are higher on arousal and dominance, while female-associated words are higher on valence.

cs.CY↗

arXiv2022

Evidence for Hypodescent in Visual Semantic AI

We examine the state-of-the-art multimodal "visual semantic" model CLIP ("Contrastive Language Image Pretraining") for the rule of hypodescent, or one-drop rule, whereby multiracial people are more likely to be assigned a racial or ethnic label corresponding to a minority or disadvantaged racial or ethnic group than to the equivalent majority or advantaged group. A face morphing experiment grounded in psychological research demonstrating hypodescent indicates that, at the midway point of 1,000 series of morphed images, CLIP associates 69.7% of Black-White female images with a Black text label over a White text label, and similarly prefers Latina (75.8%) and Asian (89.1%) text labels at the midway point for Latina-White female and Asian-White female morphs, reflecting hypodescent. Additionally, assessment of the underlying cosine similarities in the model reveals that association with White is correlated with association with "person," with Pearson's rho as high as 0.82 over a 21,000-image morph series, indicating that a White person corresponds to the default representation of a person in CLIP. Finally, we show that the stereotype-congruent pleasantness association of an image correlates with association with the Black text label in CLIP, with Pearson's rho = 0.48 for 21,000 Black-White multiracial male images, and rho = 0.41 for Black-White multiracial female images. CLIP is trained on English-language text gathered using data collected from an American website (Wikipedia), and our findings demonstrate that CLIP embeds the values of American racial hierarchy, reflecting the implicit and explicit beliefs that are present in human minds. We contextualize these findings within the history and psychology of hypodescent. Overall, the data suggests that AI supervised using natural language will, unless checked, learn biases that reflect racial hierarchies.

cs.CV↗

arXiv2021

Learning Representations by Humans, for Humans

When machine predictors can achieve higher performance than the human decision-makers they support, improving the performance of human decision-makers is often conflated with improving machine accuracy. Here we propose a framework to directly support human decision-making, in which the role of machines is to reframe problems rather than to prescribe actions through prediction. Inspired by the success of representation learning in improving performance of machine predictors, our framework learns human-facing representations optimized for human performance. This "Mind Composed with Machine" framework incorporates a human decision-making model directly into the representation learning paradigm and is trained with a novel human-in-the-loop training procedure. We empirically demonstrate the successful application of the framework to various tasks and representational forms.

cs.LG↗