arXiv subjects

Shomik Jain

Publications and source records attributed to Shomik Jain.

14 recordsLinked to original sources

arXiv2025

Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework

Large language models often generate homogeneous outputs, but whether this is problematic depends on the specific task. For objective math tasks, responses may vary in terms of problem-solving strategy but should maintain the same verifiable answer. Whereas, for creative writing tasks, we often expect variation in key narrative components (e.g. plot, setting, etc.) beyond mere vocabulary diversity. Prior work on homogenization rarely conceptualizes diversity in a task-dependent way. We address this gap with four contributions: (1) a task taxonomy with distinct notions of functional diversity -- whether a user would perceive two responses as meaningfully different for a given task; (2) a small user study validating that the taxonomy aligns with human perception of functional diversity; (3) a task-dependent sampling technique that increases diversity only where homogenization is undesired; (4) evidence challenging the perceived diversity-quality trade-off, showing it may stem from mis-conceptualizing both diversity and quality in a task-agnostic way.

cs.CL↗

arXiv2025

Interaction Context Often Increases Sycophancy in LLMs

We investigate how the presence and type of interaction context shapes sycophancy in LLMs. While real-world interactions allow models to mirror a user's values, preferences, and self-image, prior work often studies sycophancy in zero-shot settings devoid of context. Using two weeks of interaction context from 38 users, we evaluate two forms of sycophancy: (1) agreement sycophancy -- the tendency of models to produce overly affirmative responses, and (2) perspective sycophancy -- the extent to which models reflect a user's viewpoint. Agreement sycophancy tends to increase with the presence of user context, though model behavior varies based on the context type. User memory profiles are associated with the largest increases in agreement sycophancy (e.g. $+$45\% for Gemini 2.5 Pro), and some models become more sycophantic even with non-user synthetic contexts (e.g. $+$15\% for Llama 4 Scout). Perspective sycophancy increases only when models can accurately infer user viewpoints from interaction context. Overall, context shapes sycophancy in heterogeneous ways, underscoring the need for evaluations grounded in real-world interactions and raising questions for system design around alignment, memory, and personalization.

cs.HC↗

arXiv2025

Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects

Conventional AI evaluation approaches concentrated within the AI stack exhibit systemic limitations for exploring, navigating and resolving the human and societal factors that play out in real world deployment such as in education, finance, healthcare, and employment sectors. AI capability evaluations can capture detail about first-order effects, such as whether immediate system outputs are accurate, or contain toxic, biased or stereotypical content, but AI's second-order effects, i.e. any long-term outcomes and consequences that may result from AI use in the real world, have become a significant area of interest as the technology becomes embedded in our daily lives. These secondary effects can include shifts in user behavior, societal, cultural and economic ramifications, workforce transformations, and long-term downstream impacts that may result from a broad and growing set of risks. This position paper argues that measuring the indirect and secondary effects of AI will require expansion beyond static, single-turn approaches conducted in silico to include testing paradigms that can capture what actually materializes when people use AI technology in context. Specifically, we describe the need for data and methods that can facilitate contextual awareness and enable downstream interpretation and decision making about AI's secondary effects, and recommend requirements for a new ecosystem.

cs.CY↗

arXiv2025

Allocation Multiplicity: Evaluating the Promises of the Rashomon Set

The Rashomon set of equally-good models promises less discriminatory algorithms, reduced outcome homogenization, and fairer decisions through model ensembles or reconciliation. However, we argue from the perspective of allocation multiplicity that these promises may remain unfulfilled. When there are more qualified candidates than resources available, many different allocations of scarce resources can achieve the same utility. This space of equal-utility allocations may not be faithfully reflected by the Rashomon set, as we show in a case study of healthcare allocations. We attribute these unfulfilled promises to several factors: limitations in empirical methods for sampling from the Rashomon set, the standard practice of deterministically selecting individuals with the lowest risk, and structural biases that cause all equally-good models to view some qualified individuals as inherently risky.

cs.CY↗

arXiv2024

Automating Transparency Mechanisms in the Judicial System Using LLMs: Opportunities and Challenges

Bringing more transparency to the judicial system for the purposes of increasing accountability often demands extensive effort from auditors who must meticulously sift through numerous disorganized legal case files to detect patterns of bias and errors. For example, the high-profile investigation into the Curtis Flowers case took seven reporters a full year to assemble evidence about the prosecutor's history of selecting racially biased juries. LLMs have the potential to automate and scale these transparency pipelines, especially given their demonstrated capabilities to extract information from unstructured documents. We discuss the opportunities and challenges of using LLMs to provide transparency in two important court processes: jury selection in criminal trials and housing eviction cases.

cs.CY↗

arXiv2024

As an AI Language Model, "Yes I Would Recommend Calling the Police": Norm Inconsistency in LLM Decision-Making

We investigate the phenomenon of norm inconsistency: where LLMs apply different norms in similar situations. Specifically, we focus on the high-risk application of deciding whether to call the police in Amazon Ring home surveillance videos. We evaluate the decisions of three state-of-the-art LLMs -- GPT-4, Gemini 1.0, and Claude 3 Sonnet -- in relation to the activities portrayed in the videos, the subjects' skin-tone and gender, and the characteristics of the neighborhoods where the videos were recorded. Our analysis reveals significant norm inconsistencies: (1) a discordance between the recommendation to call the police and the actual presence of criminal activity, and (2) biases influenced by the racial demographics of the neighborhoods. These results highlight the arbitrariness of model decisions in the surveillance context and the limitations of current bias detection and mitigation strategies in normative decision-making.

cs.CY↗

arXiv2024

Algorithmic Pluralism: A Structural Approach To Equal Opportunity

We present a structural approach toward achieving equal opportunity in systems of algorithmic decision-making called algorithmic pluralism. Algorithmic pluralism describes a state of affairs in which no set of algorithms severely limits access to opportunity, allowing individuals the freedom to pursue a diverse range of life paths. To argue for algorithmic pluralism, we adopt Joseph Fishkin's theory of bottlenecks, which focuses on the structure of decision-points that determine how opportunities are allocated. The theory contends that each decision-point or bottleneck limits access to opportunities with some degree of severity and legitimacy. We extend Fishkin's structural viewpoint and use it to reframe existing systemic concerns about equal opportunity in algorithmic decision-making, such as patterned inequality and algorithmic monoculture. In proposing algorithmic pluralism, we argue for the urgent priority of alleviating severe bottlenecks in algorithmic decision-making. We contend that there must be a pluralism of opportunity available to many different individuals in order to promote equal opportunity in a systemic way. We further show how this framework has several implications for system design and regulation through current debates about equal opportunity in algorithmic hiring.

cs.CY↗

arXiv2024

Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized

Contrary to traditional deterministic notions of algorithmic fairness, this paper argues that fairly allocating scarce resources using machine learning often requires randomness. We address why, when, and how to randomize by proposing stochastic procedures that more adequately account for all of the claims that individuals have to allocations of social goods or opportunities.

cs.CY↗

arXiv2024

Facebook Political Ads And Accountability: Outside Groups Are Most Negative, Especially When Hiding Donors

The emergence of online political advertising has come with little regulation, allowing political advertisers on social media to avoid accountability. We analyze how transparency and accountability deficits caused by dark money and disappearing groups relate to the sentiment of political ads on Facebook. We obtained 430,044 ads with FEC-registered advertisers from Facebook's ad library that ran between August-November 2018. We compare ads run by candidates, parties, and outside groups, which we classify by (1) their donor transparency (dark money or disclosed) and (2) the group's permanence (only FEC-registered in 2018 or persistent across cycles). The most negative advertising came from dark money and disappearing outside groups, which were mostly corporations or 501(c) organizations. However, only dark money was associated with a significant decrease in ad sentiment. These results suggest that accountability for political speech matters for advertising tone, especially in the context of affective polarization on social media.

cs.CY↗

arXiv2021

Toward Personalized Affect-Aware Socially Assistive Robot Tutors in Long-Term Interventions for Children with Autism

Affect-aware socially assistive robotics (SAR) has shown great potential for augmenting interventions for children with autism spectrum disorders (ASD). However, current SAR cannot yet perceive the unique and diverse set of atypical cognitive-affective behaviors from children with ASD in an automatic and personalized fashion in long-term (multi-session) real-world interactions. To bridge this gap, this work designed and validated personalized models of arousal and valence for children with ASD using a multi-session in-home dataset of SAR interventions. By training machine learning (ML) algorithms with supervised domain adaptation (s-DA), the personalized models were able to trade off between the limited individual data and the more abundant less personal data pooled from other study participants. We evaluated the effects of personalization on a long-term multimodal dataset consisting of 4 children with ASD with a total of 19 sessions, and derived inter-rater reliability (IR) scores for binary arousal (IR = 83%) and valence (IR = 81%) labels between human annotators. Our results show that personalized Gradient Boosted Decision Trees (XGBoost) models with s-DA outperformed two non-personalized individualized and generic model baselines not only on the weighted average of all sessions, but also statistically (p < .05) across individual sessions. This work paves the way for the development of personalized autonomous SAR systems tailored toward individuals with atypical cognitive-affective and socio-emotional needs.

cs.RO↗

arXiv2021

Nowcasting Gentrification Using Airbnb Data

There is a rumbling debate over the impact of gentrification: presumed gentrifiers have been the target of protests and attacks in some cities, while they have been welcome as generators of new jobs and taxes in others. Census data fails to measure neighborhood change in real-time since it is usually updated every ten years. This work shows that Airbnb data can be used to quantify and track neighborhood changes. Specifically, we consider both structured data (e.g. number of listings, number of reviews, listing information) and unstructured data (e.g. user-generated reviews processed with natural language processing and machine learning algorithms) for three major cities, New York City (US), Los Angeles (US), and Greater London (UK). We find that Airbnb data (especially its unstructured part) appears to nowcast neighborhood gentrification, measured as changes in housing affordability and demographics. Overall, our results suggest that user-generated data from online platforms can be used to create socioeconomic indices to complement traditional measures that are less granular, not in real-time, and more costly to obtain.

cs.CY↗

arXiv2020

Adversarial Perturbations Fool Deepfake Detectors

This work uses adversarial perturbations to enhance deepfake images and fool common deepfake detectors. We created adversarial perturbations using the Fast Gradient Sign Method and the Carlini and Wagner L2 norm attack in both blackbox and whitebox settings. Detectors achieved over 95% accuracy on unperturbed deepfakes, but less than 27% accuracy on perturbed deepfakes. We also explore two improvements to deepfake detectors: (i) Lipschitz regularization, and (ii) Deep Image Prior (DIP). Lipschitz regularization constrains the gradient of the detector with respect to the input in order to increase robustness to input perturbations. The DIP defense removes perturbations using generative convolutional neural networks in an unsupervised manner. Regularization improved the detection of perturbed deepfakes on average, including a 10% accuracy boost in the blackbox case. The DIP defense achieved 95% accuracy on perturbed deepfakes that fooled the original detector, while retaining 98% accuracy in other cases on a 100 image subsample.

cs.CV↗

arXiv2020

Modeling Engagement in Long-Term, In-Home Socially Assistive Robot Interventions for Children with Autism Spectrum Disorders

Socially assistive robotics (SAR) has great potential to provide accessible, affordable, and personalized therapeutic interventions for children with autism spectrum disorders (ASD). However, human-robot interaction (HRI) methods are still limited in their ability to autonomously recognize and respond to behavioral cues, especially in atypical users and everyday settings. This work applies supervised machine learning algorithms to model user engagement in the context of long-term, in-home SAR interventions for children with ASD. Specifically, we present two types of engagement models for each user: (i) generalized models trained on data from different users; and (ii) individualized models trained on an early subset of the user's data. The models achieved approximately 90% accuracy (AUROC) for post hoc binary classification of engagement, despite the high variance in data observed across users, sessions, and engagement states. Moreover, temporal patterns in model predictions could be used to reliably initiate re-engagement actions at appropriate times. These results validate the feasibility and challenges of recognition and response to user disengagement in long-term, real-world HRI settings. The contributions of this work also inform the design of engaging and personalized HRI, especially for the ASD community.

cs.HC↗

arXiv2019

Long-Term Personalization of an In-Home Socially Assistive Robot for Children With Autism Spectrum Disorders

Socially assistive robots (SAR) have shown great potential to augment the social and educational development of children with autism spectrum disorders (ASD). As SAR continues to substantiate itself as an effective enhancement to human intervention, researchers have sought to study its longitudinal impacts in real-world environments, including the home. Computational personalization stands out as a central computational challenge as it is necessary to enable SAR systems to adapt to each child's unique and changing needs. Toward that end, we formalized personalization as a hierarchical human robot learning framework (hHRL) consisting of five controllers (disclosure, promise, instruction, feedback, and inquiry) mediated by a meta-controller that utilized reinforcement learning to personalize instruction challenge levels and robot feedback based on each user's unique learning patterns. We instantiated and evaluated the approach in a study with 17 children with ASD, aged 3 to 7 years old, over month-long interventions in their homes. Our findings demonstrate that the fully autonomous SAR system was able to personalize its instruction and feedback over time to each child's proficiency. As a result, every child participant showed improvements in targeted skills and long-term retention of intervention content. Moreover, all child users were engaged for a majority of the intervention, and their families reported the SAR system to be useful and adaptable. In summary, our results show that autonomous, personalized SAR interventions are both feasible and effective in providing long-term in-home developmental support for children with diverse learning needs.

cs.RO↗