AVAditya Vashistha

Aditya Vashistha

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Aditya Vashistha has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Disability Across Cultures: A Human-Centered Audit of Ableism in Western and Indic LLMs

    by Mahika Phutane, Aditya Vashistha

    People with disabilities (PwD) experience disproportionately high levels of discrimination and hate online, particularly in India, where entrenched stigma and limited resources intensify these challenges. Large language models (LLMs) are increasingly used to identify and mitigate online hate, yet most research on online ableism focuses on Western audiences with Western AI models. Are these models adequately equipped to recognize ableist harm in non-Western places like India? Do localized, Indic language models perform better? To investigate these questions, we adopted and translated a publicly available ableist speech dataset to Hindi, and prompted eight LLMs—four developed in the U.S. (GPT-4, Gemini, Claude, Llama) and four in India (Krutrim, Nanda, Gajendra, Airavata)—to score and explain ableism. In parallel, we recruited 175 PwD from both the U.S. and India to perform the same task, revealing stark differences between groups. Western LLMs consistently overestimated ableist harm, while Indic LLMs underestimated it. Even more concerning, all LLMs were more tolerant of ableism when it was expressed in Hindi and asserted Western framings of ableist harm. In contrast, Indian PwD interpreted harm through intention, relationality, and resilience---emphasizing a desire to inform and educate perpetrators. This work provides groundwork for global, inclusive standards of ableism, demonstrating the need to center local disability experiences in the design and evaluation of AI systems.


  • Open Access

    How Deep Is Representational Bias in LLMs? The Cases of Caste and Religion

    by Agrima Seth, Monojit Choudhury, Sunayana Sitaram, Kentaro Toyama, Aditya Vashistha, Kalika Bali

    Representational bias in large language models (LLMs) has predominantly been measured through single-response interactions and has focused on Global North-centric identities like race and gender. We expand on that research by conducting a systematic audit of GPT-4 Turbo to reveal how deeply encoded representational biases are and how they extend to less-explored dimensions of identity. We prompt GPT-4 Turbo to generate over 7,200 stories about significant life events (such as weddings) in India, using prompts designed to encourage diversity to varying extents. Comparing the diversity of religious and caste representation in the outputs against the actual population distribution in India as recorded in census data, we quantify the presence and “stickiness” of representational bias in the LLM for religion and caste. We find that GPT-4 responses consistently overrepresent culturally dominant groups far beyond their statistical representation, despite prompts intended to encourage representational diversity. Our findings also suggest that representational bias in LLMs has a winner-takes-all quality that is more biased than the likely distribution bias in their training data, and repeated prompt-based nudges have limited and inconsistent efficacy in dislodging these biases. These results suggest that diversifying training data alone may not be sufficient to correct LLM bias, highlighting the need for more fundamental changes in model development.


  • Open Access

    Think Outside the Data: Colonial Biases and Systemic Issues in Automated Moderation Pipelines for Low-Resource Languages

    by Farhana Shahid, Mona Elswah, Aditya Vashistha

    Most social media users come from the Global South, where harmful content usually appears in local languages. Yet, AI-driven moderation systems struggle with low-resource languages spoken in these regions. Through semi-structured interviews with 22 AI experts working on harmful content detection in four low-resource languages: Tamil (South Asia), Swahili (East Africa), Maghrebi Arabic (North Africa), and Quechua (South America)--we examine systemic issues in building automated moderation tools for these languages. Our findings reveal that beyond data scarcity, socio-political factors such as tech companies' monopoly on user data and lack of investment in moderation for low-profit Global South markets exacerbate historic inequities. Even if more data were available, the English-centric and data-intensive design of language models and preprocessing techniques overlooks the need to design for morphologically complex, linguistically diverse, and code-mixed languages. We argue these limitations are not just technical gaps caused by "data scarcity" but reflect structural inequities, rooted in colonial suppression of non-Western languages. We discuss multi-stakeholder approaches to strengthen local research capacity, democratize data access, and support language-aware solutions to improve automated moderation for low-resource languages.


  • Open Access

    ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios

    by Mahika Phutane, Hayoung Jung, Matthew Kim, Tanushree Mitra, Aditya Vashistha

    Large language models (LLMs) are increasingly under scrutiny for perpetuating identity-based discrimination in high-stakes domains such as hiring, particularly against people with disabilities (PwD). However, existing research remains largely Western-centric, overlooking how intersecting forms of marginalization--such as gender and caste--shape experiences of PwD in the Global South. We conduct a comprehensive audit of six LLMs across 2,820 hiring scenarios spanning diverse disability, gender, nationality, and caste profiles. To capture subtle intersectional harms and biases, we introduce ABLEIST (Ableism, Inspiration, Superhumanization, and Tokenism), a set of five ableism-specific and three intersectional harm metrics grounded in disability studies literature. Our results reveal significant increases in ABLEIST harms towards disabled candidates--harms that many state-of-the-art models failed to detect. These harms were further amplified by sharp increases in intersectional harms (e.g., Tokenism) for gender and caste-marginalized disabled candidates, highlighting critical blind spots in current safety tools and the need for intersectional safety evaluations of frontier models in high-stakes domains like hiring.


  • Open Access

    Designing with Culture: How Social Norms Shape Trust and Preference in Health Chatbots

    by Arpita Wadhwa, Aditya Vashistha, Mohit Jain

    AI-driven chatbots are increasingly used to support community health workers (CHWs) in developing regions, yet little is known about how cultural framings in chatbot design shape trust in collectivist contexts where decisions are rarely made in isolation. This paper examines how CHWs in rural India responded to chatbots that delivered identical health content but varied in one specific cultural lever -- social norms. Through a mixed-methods study with 61 ASHAs who compared four normative framings -- neutral, descriptive, narrative identity, and injunctive authority -- we (1) analyze how framings influence preferences and trust, and (2) compare effects across low- and high-ambiguity scenarios. Results show that narrative framings were most preferred but encouraged uncritical overreliance, while authority framings were least preferred yet supported calibrated trust. We conclude with design recommendations for dynamic framing strategies that adapt to context and argue for calibrated trust -- following correct advice and resisting incorrect advice -- as a critical evaluation metric for safe, culturally-grounded AI.

  • Open Access

    Disability Across Cultures: A Human-Centered Audit of Ableism in Western and Indic LLMs

    by Mahika Phutane, Aditya Vashistha

    People with disabilities (PwD) experience disproportionately high levels of discrimination and hate online, particularly in India, where entrenched stigma and limited resources intensify these challenges. Large language models (LLMs) are increasingly used to identify and mitigate online hate, yet most research on online ableism focuses on Western audiences with Western AI models. Are these models adequately equipped to recognize ableist harm in non-Western places like India? Do localized, Indic language models perform better? To investigate, we adopted and translated a publicly available ableist speech dataset to Hindi, and prompted eight LLMs--four developed in the U.S. (GPT-4, Gemini, Claude, Llama) and four in India (Krutrim, Nanda, Gajendra, Airavata)--to score and explain ableism. In parallel, we recruited 175 PwD from both the U.S. and India to perform the same task, revealing stark differences between groups. Western LLMs consistently overestimated ableist harm, while Indic LLMs underestimated it. Even more concerning, all LLMs were more tolerant of ableism when it was expressed in Hindi and asserted Western framings of ableist harm. In contrast, Indian PwD interpreted harm through intention, relationality, and resilience--emphasizing a desire to inform and educate perpetrators. This work provides groundwork for global, inclusive standards of ableism, demonstrating the need to center local disability experiences in the design and evaluation of AI systems.

  • Open Access

    Global Patterns of Viral Content on WhatsApp

    by Kiran Garimella, Princessa Cintaqia, Juan José Rojas-Constain, Bharat Kumar Nayak, Aditya Vashistha

    This paper explores the nature and spread of viral WhatsApp content among everyday users in three diverse countries: India, Indonesia, and Colombia. By analyzing hundreds of viral messages collected with participants’ consent from private WhatsApp groups, we provide one of the first cross-cultural categorizations of viral content on WhatsApp. Despite the differences in cultural and geographic settings, our findings reveal striking similarities in the types of groups users engage with and the viral content they receive, particularly in the prevalence of misinformation. Our comparative analysis shows that viral content often includes political and religious narratives, with misinformation frequently recirculated despite prior debunking by fact-checking organizations. These parallels suggest that closed messaging platforms like WhatsApp facilitate similar patterns of information dissemination across different cultural contexts. This work contributes to the broader understanding of global digital communication ecosystems and provides a foundation for future research on information flow and moderation strategies in private messaging platforms.


  • Open Access

    Voice Interfaces for Underserved Communities

    by Aditya Vashistha, Agha Ali Raza

    Internet technologies – like social media platforms and discussion forums – have transformed how people communicate with each other. In addition to improving access to information, news, and entertainment, they have impacted governance, politics, civil society movements, crisis response, marketplaces, and healthcare, among other parts of our lives. Although concerns regarding data misuse, privacy breaches, and overuse have grown recently, these technologies are continuing to soar, mostly among literate, urban, and connected communities, all across the world. However, despite their promises (and pitfalls), these technologies currently exclude billions of people worldwide who are too remote to access the Internet, too low-literate to navigate the mostly text-driven Internet, or too poor to afford Internet-enabled devices. This chapter presents the innovation, implementation, and adaptation of voice forums that have evolved over the last two decades, discusses challenges that plagued their growth, and highlights ingenious solutions that were used to address their pain points.


  • Open Access

    “#DisabledOnIndianTwitter” : A Dataset towards Understanding the Expression of People with Disabilities on Indian Twitter

    by Ishani Mondal, Sukhnidh Kaur, Kalika Bali, Aditya Vashistha, Manohar Swaminathan

    Ishani Mondal, Sukhnidh Kaur, Kalika Bali, Aditya Vashistha, Manohar Swaminathan. Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022. 2022.