arXiv subjects

Sanjana Gautam

Publications and source records attributed to Sanjana Gautam.

17 recordsLinked to original sources

arXiv2026

What if AI systems weren't chatbots?

The rapid convergence of artificial intelligence (AI) toward conversational chatbot interfaces marks a critical moment for the industry. This paper argues that the chatbot paradigm is not a neutral interface choice, but a dominant sociotechnical configuration whose widespread adoption reshapes social, economic, legal, and environmental systems. We examine how treating AI primarily as conversational assistants has extensive structural downsides. We show how chatbot-based systems often fail to adequately meet user needs, particularly in complex or high-stakes contexts, while projecting confidence and authority. We further analyze how the normalization of chatbot-mediated interaction alters patterns of work, learning, and decision-making, contributing to deskilling, homogenization of knowledge, and shifting expectations of expertise. Finally, we examine broader societal effects, including labor displacement, concentration of economic power, and increased environmental costs driven by sustained investment in large-scale chatbot infrastructures. While acknowledging legitimate benefits, we argue that the current trajectory of AI development reflects specific value choices that prioritize conversational generality over domain specificity, accountability, and long-term social sustainability. We conclude by outlining alternative directions for AI development and governance that move beyond one-size-fits-all chatbots, emphasizing pluralistic system design, task-specific tools, and institutional safeguards to mitigate social and economic harm.

cs.CY↗

arXiv2026

How Researchers Navigate Accountability, Transparency, and Trust When Using AI Tools in Early-Stage Research: A Think-Aloud Study

In the early stages of scientific research, researchers rely on core scholarly judgments to identify relevant literature, assess credible evidence, and determine which directions merit pursuit. As AI tools become increasingly integrated into these early-stage workflows, the scholarly judgments that were once transparent and attributable to individual researchers become obscured, raising critical Responsible AI (RAI) concerns around accountability, transparency, and trust. Yet how these three dimensions manifest in real-time, in-situ scholarly practice remains largely unexplored. To address this gap, we conducted a think-aloud study with 15 researchers to examine how they used AI tools powered by large language models (LLMs) across early-stage research tasks, including literature exploration, synthesis, and research ideation. Our key findings address the tripartite constructs of accountability, transparency, and trust. First, the confident tone of AI outputs misrepresents epistemic uncertainty, making it more difficult for researchers (who are ultimately accountable) to identify which outputs require the greatest scrutiny. Second, opaque retrieval and content construction make provenance difficult to establish for transparency. Third, trust in AI is fragile, context-dependent, and easily eroded. In response, participant researchers were seen to develop compensatory strategies to restore scholarly judgment under uncertainty. Overall, our findings serve to contextualize AI-mediated research as a RAI problem grounded in lived researcher experience and motivate attention to deliberate AI integration that preserves accountability, supports transparency, and fosters informed trust.

cs.CY↗

arXiv2026

Improving the Distributional Alignment of LLMs using Supervision

The ability to accurately align LLMs with diverse population groups on subjective questions would have great value. In this work, we show that adding simple supervision can more consistently improve the alignment of LLM-generated distributions with diverse population groups, as measured across three datasets spanning public health, public opinion, and values and beliefs. Beyond evaluating average alignment, we also report how alignment varies across specific groups. Our broad findings provide insights into the distributional alignment of LLM generations with diverse populations. By conducting evaluation over many LLMs and prompting strategies, we provide a benchmark to stimulate future research.

cs.CL↗

arXiv2026

Who Owns Creativity and Who Does the Work? Trade-offs in LLM-Supported Research Ideation

LLM-based agents offer new potential to accelerate science and reshape research work. However, the quality of researcher contributions can vary significantly depending on human ability to steer agent behaviors. How can we best use these tools to augment scientific creativity without undermining aspects of contribution and ownership that drive research? To investigate this, we developed an agentic research ideation system integrating three roles -- Ideator, Writer, and Evaluator -- across three control levels -- Low, Medium, and Intensive. Our mixed-methods study with 54 researchers suggests three key findings in how LLM-based agents reshape scientific creativity: 1) perceived creativity support does not simply increase linearly with greater control; 2) human effort shifts from ideating to verifying ideas; and 3) ownership becomes a negotiated outcome between human and AI. Our findings suggest that LLM agent design should emphasize researcher empowerment, fostering a sense of ownership over strong ideas rather than reducing researchers to operating an automated AI-driven process.

cs.HC↗

arXiv2025

Towards Experience-Centered AI: A Framework for Integrating Lived Experience in Design and Development

Lived experiences fundamentally shape how individuals interact with AI systems, influencing perceptions of safety, trust, and usability. While prior research has focused on developing techniques to emulate human preferences, and proposed taxonomies to categorize risks (such as psychological harms and algorithmic biases), these efforts have provided limited systematic understanding of lived human experiences or actionable strategies for embedding them meaningfully into the AI development lifecycle. This work proposes a framework for meaningfully integrating lived experience into the design and evaluation of AI systems. We synthesize interdisciplinary literature across lived experience philosophy, human-centered design, and human-AI interaction, arguing that centering lived experience can lead to models that more accurately reflect the retrospective, emotional, and contextual dimensions of human cognition. Drawing from a wide body of work across psychology, education, healthcare, and social policy, we present a targeted taxonomy of lived experiences with specific applicability to AI systems. To ground our framework, we examine three application domains (i) education, (ii) healthcare, and (iii) cultural alignment, illustrating how lived experience informs user goals, system expectations, and ethical considerations in each context. We further incorporate insights from AI system operators and human-AI partnerships to highlight challenges in responsibility allocation, mental model calibration, and long-term system adaptation. We conclude with actionable recommendations for developing experience-centered AI systems that are not only technically robust but also empathetic, context-aware, and aligned with human realities. This work offers a foundation for future research that bridges technical development with the lived experiences of those impacted by AI systems.

cs.CY↗

arXiv2025

Embracing Transparency: A Study of Open Science Practices Among Early Career HCI Researchers

Many fields of science, including Human-Computer Interaction (HCI), have heightened introspection in the wake of concerns around reproducibility and replicability of published findings. Notably, in recent years the HCI community has worked to implement policy changes and mainstream open science practices. Our work investigates early-career HCI researchers' perceptions of open science and engagement with best practices through 18 semi-structured interviews. Our findings highlight key barriers to the widespread adoption of data and materials sharing, and preregistration, namely: lack of clear incentives; cultural resistance; limited training; time constraints; concerns about intellectual property; and data privacy issues. We observe that small changes at major conferences like CHI could meaningfully impact community norms. We offer recommendations to address these barriers and to promote transparency and openness in HCI. While these findings provide valuable and interesting insights about the open science practices by early career HCI researchers, their applicability is limited to the USA only. The interview study relies on self-reported data; therefore, it can be subject to biases like recall bias. Future studies will include the scope to expand HCI researchers from different levels of experience and different countries, allowing for more justifiable examples.

cs.HC↗

arXiv2025

Documenting Patterns of Exoticism of Marginalized Populations within Text-to-Image Generators

A significant majority of AI fairness research studying the harmful outcomes of GAI tools have overlooked non-Western communities and contexts, necessitating a stronger coverage in this vein. We extend our previous work on exoticism (Ghosh et al., 2024) of 'Global South' countries from across the world, as depicted by GAI tools. We analyze generated images of individuals from 13 countries -- India, Bangladesh, Papua New Guinea, Egypt, Ethiopia, Tunisia, Sudan, Libya, Venezuela, Colombia, Indonesia, Honduras, and Mexico -- performing everyday activities (such as being at home, going to work, getting groceries, etc.), as opposed to images for the same activities being performed by persons from 3 'Global North' countries -- USA, UK, Australia. While outputs for 'Global North' demonstrate a difference across images and people clad in activity-appropriate attire, individuals from 'Global South' countries are depicted in similar attire irrespective of the performed activity, indicative of a pattern of exoticism where attire or other cultural features are overamplified at the cost of accuracy. We further show qualitatively-analyzed case studies that demonstrate how exoticism is not simply performed upon 'Global South' countries but also upon marginalized populations even in Western contexts, as we observe a similar exoticization of Indigenous populations in the 'Global North', and doubly upon marginalized populations within 'Global South' countries. We document implications for harm-aware usage patterns of such tools, and steps towards designing better GAI tools through community-centered endeavors.

cs.CY↗

arXiv2024

Inspo: Writing with Crowds Alongside AI

The use of artificial intelligence (AI) to support creative writing has bloomed in recent years. However, it is less well understood how AI compares to on-demand human support. We explored how writers interact with both AI and crowd worker writing assistants in creative writing. We replicated the interface of the prior crowd-writing system, Heteroglossia, and developed Inspo, a text editor allowing users to request suggestions from AI models and crowd workers. In a one-week deployment study involving eight creative writers, we examined how often participants selected crowd workers when fluent AI text generators were also available. Findings showed a consistent decline in crowd worker usage, with participants favoring AI due to its faster responses and more consistent quality. We conclude with suggestions for future systems, recommending designs that account for the unique strengths and weaknesses of human versus AI assistants, strategies to address automation bias, and sociocultural views of writing.

cs.HC↗

arXiv2024

Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approach

Our research investigates the impact of Generative Artificial Intelligence (GAI) models, specifically text-to-image generators (T2Is), on the representation of non-Western cultures, with a focus on Indian contexts. Despite the transformative potential of T2Is in content creation, concerns have arisen regarding biases that may lead to misrepresentations and marginalizations. Through a community-centered approach and grounded theory analysis of 5 focus groups from diverse Indian subcultures, we explore how T2I outputs to English prompts depict Indian culture and its subcultures, uncovering novel representational harms such as exoticism and cultural misappropriation. These findings highlight the urgent need for inclusive and culturally sensitive T2I systems. We propose design guidelines informed by a sociotechnical perspective, aiming to address these issues and contribute to the development of more equitable and representative GAI technologies globally. Our work also underscores the necessity of adopting a community-centered approach to comprehend the sociotechnical dynamics of these models, complementing existing work in this space while identifying and addressing the potential negative repercussions and harms that may arise when these models are deployed on a global scale.

cs.CY↗

arXiv2024

Blind Spots and Biases: Exploring the Role of Annotator Cognitive Biases in NLP

With the rapid proliferation of artificial intelligence, there is growing concern over its potential to exacerbate existing biases and societal disparities and introduce novel ones. This issue has prompted widespread attention from academia, policymakers, industry, and civil society. While evidence suggests that integrating human perspectives can mitigate bias-related issues in AI systems, it also introduces challenges associated with cognitive biases inherent in human decision-making. Our research focuses on reviewing existing methodologies and ongoing investigations aimed at understanding annotation attributes that contribute to bias.

cs.HC↗

arXiv2024

From Melting Pots to Misrepresentations: Exploring Harms in Generative AI

With the widespread adoption of advanced generative models such as Gemini and GPT, there has been a notable increase in the incorporation of such models into sociotechnical systems, categorized under AI-as-a-Service (AIaaS). Despite their versatility across diverse sectors, concerns persist regarding discriminatory tendencies within these models, particularly favoring selected `majority' demographics across various sociodemographic dimensions. Despite widespread calls for diversification of media representations, marginalized racial and ethnic groups continue to face persistent distortion, stereotyping, and neglect within the AIaaS context. In this work, we provide a critical summary of the state of research in the context of social harms to lead the conversation to focus on their implications. We also present open-ended research questions, guided by our discussion, to help define future research pathways.

cs.HC↗

arXiv2023

ECHO: An Automated Contextual Inquiry Framework for Anonymous Qualitative Studies using Conversational Assistants

Qualitative research studies often employ a contextual inquiry, or a field study that involves in-depth observation and interviews of a small sample of study participants, in-situ, to gain a robust understanding of the reasons and circumstances that led to the participant's thoughts, actions, and experiences regarding the domain of interest. Contextual inquiry, especially in sensitive data studies, can be a challenging task due to reasons such as participant privacy, as well as physical constraints such as in-person presence and manual analysis of the qualitative data gathered. In this work, we discuss Enquête Contextuelle Habile Ordinateur (ECHO); a virtual-assistant framework to automate the erstwhile manual process of conducting contextual inquiries and analysing the respondents' subjective qualitative data. ECHO automates the contextual inquiry pipeline, while not compromising on privacy preservation or response integrity. Its adaptive conversational interface enables respondents to provide unstructured or semi-structured responses in free-form natural language, allowing researchers to explore larger narratives in participant response data. It supports response-driven exploratory questions and automates coding methodologies for qualitative data, thus enabling the inquirer to dive deeper into correlated questions and to do better cause-effect analysis. It focuses on addressing the limitations of manual annotation, bringing standardisation to free-form text, and eliminating perspective bias amongst different reviewers of subjective responses. A participatory mental health study was conducted on 167 young adults bifurcated into two focus groups; one of which was administered a conventional contextual inquiry, and the other via ECHO, virtually. ECHO outperformed on participant transparency, response detail and median time required for end-to-end inquiry completion, per participant.

cs.HC↗

arXiv2023

The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis

We conduct an inquiry into the sociotechnical aspects of sentiment analysis (SA) by critically examining 189 peer-reviewed papers on their applications, models, and datasets. Our investigation stems from the recognition that SA has become an integral component of diverse sociotechnical systems, exerting influence on both social and technical users. By delving into sociological and technological literature on sentiment, we unveil distinct conceptualizations of this term in domains such as finance, government, and medicine. Our study exposes a lack of explicit definitions and frameworks for characterizing sentiment, resulting in potential challenges and biases. To tackle this issue, we propose an ethics sheet encompassing critical inquiries to guide practitioners in ensuring equitable utilization of SA. Our findings underscore the significance of adopting an interdisciplinary approach to defining sentiment in SA and offer a pragmatic solution for its implementation.

cs.CL↗

arXiv2023

Unmasking Nationality Bias: A Study of Human Perception of Nationalities in AI-Generated Articles

We investigate the potential for nationality biases in natural language processing (NLP) models using human evaluation methods. Biased NLP models can perpetuate stereotypes and lead to algorithmic discrimination, posing a significant challenge to the fairness and justice of AI systems. Our study employs a two-step mixed-methods approach that includes both quantitative and qualitative analysis to identify and understand the impact of nationality bias in a text generation model. Through our human-centered quantitative analysis, we measure the extent of nationality bias in articles generated by AI sources. We then conduct open-ended interviews with participants, performing qualitative coding and thematic analysis to understand the implications of these biases on human readers. Our findings reveal that biased NLP models tend to replicate and amplify existing societal biases, which can translate to harm if used in a sociotechnical setting. The qualitative analysis from our interviews offers insights into the experience readers have when encountering such articles, highlighting the potential to shift a reader's perception of a country. These findings emphasize the critical role of public perception in shaping AI's impact on society and the need to correct biases in AI systems.

cs.CL↗

arXiv2023

Nationality Bias in Text Generation

Little attention is placed on analyzing nationality bias in language models, especially when nationality is highly used as a factor in increasing the performance of social NLP models. This paper examines how a text generation model, GPT-2, accentuates pre-existing societal biases about country-based demonyms. We generate stories using GPT-2 for various nationalities and use sensitivity analysis to explore how the number of internet users and the country's economic status impacts the sentiment of the stories. To reduce the propagation of biases through large language models (LLM), we explore the debiasing method of adversarial triggering. Our results show that GPT-2 demonstrates significant bias against countries with lower internet users, and adversarial triggering effectively reduces the same.

cs.CL↗

arXiv2022

In Alexa, We Trust. Or Do We? : An analysis of People's Perception of Privacy Policies

Smart home devices have found their way through people's homes as well as hearts. One such smart device is Amazon Alexa. Amazon Alexa is a voice-controlled application that is rapidly gaining popularity. Alexa was primarily used for checking weather forecasts, playing music, and controlling other devices. This paper tries to explore the extent to which people are aware of the privacy policies pertaining to the Amazon Alexa devices. We have evaluated behavioral change towards their interactions with the device post being aware of the adverse implications. Resulting knowledge will give researchers new avenues of research and interaction designers new insights into improving their systems.

cs.HC↗

arXiv2022

Understanding Twitters behavior during the pandemic: Fake News and Fear

The outbreak of the SARS-CoV-2 novel coronavirus (COVID-19) has been accompanied by a large amount of misleading and false information about the virus, especially on social media. During the pandemic social media gained special interest as it went on to become an important medium of communication. This made the information being relayed on these platforms especially critical. In our work, we aim to explore the percentage of fake news being spread on Twitter as well as measure the sentiment of the public at the same time. We further study how the sentiment of fear is present among the public. In addition to that we compare the rate of spread of the virus per day with the rate of spread of fake news on Twitter. Our study is useful in establishing the role of Twitter, and social media, during a crisis, and more specifically during crisis management.

cs.SI↗