Amulya Yadav

Hangzhi Guo, Feiran Jia, Jinghui Chen et al.

Counterfactual (CF) explanations for machine learning (ML) models are preferred by end-users, as they explain the predictions of ML models by providing a recourse (or contrastive) case to individuals who are adversely impacted by predicted outcomes. Existing CF explanation methods generate recourses under the assumption that the underlying target ML model remains stationary over time. However, due to commonly occurring distributional shifts in training data, ML models constantly get updated in practice, which might render previously generated recourses invalid and diminish end-users trust in our algorithmic framework. To address this problem, we propose RoCourseNet, a training framework that jointly optimizes predictions and recourses that are robust to future data shifts. This work contains four key contributions: (1) We formulate the robust recourse generation problem as a tri-level optimization problem which consists of two sub-problems: (i) a bi-level problem that finds the worst-case adversarial shift in the training data, and (ii) an outer minimization problem to generate robust recourses against this worst-case shift. (2) We leverage adversarial training to solve this tri-level optimization problem by: (i) proposing a novel virtual data shift (VDS) algorithm to find worst-case shifted ML models via explicitly considering the worst-case data shift in the training dataset, and (ii) a block-wise coordinate descent procedure to optimize for prediction and corresponding robust recourses. (3) We evaluate RoCourseNet's performance on three real-world datasets, and show that RoCourseNet consistently achieves more than 96% robust validity and outperforms state-of-the-art baselines by at least 10% in generating robust CF explanations. (4) Finally, we generalize the RoCourseNet framework to accommodate any parametric post-hoc methods for improving robust validity.

Wenbo Zhang, Hangzhi Guo, Ian D Kivlichan et al.

Toxicity is an increasingly common and severe issue in online spaces. Consequently, a rich line of machine learning research over the past decade has focused on computationally detecting and mitigating online toxicity. These efforts crucially rely on human-annotated datasets that identify toxic content of various kinds in social media texts. However, such annotations historically yield low inter-rater agreement, which was often dealt with by taking the majority vote or other such approaches to arrive at a single ground truth label. Recent research has pointed out the importance of accounting for the subjective nature of this task when building and utilizing these datasets, and this has triggered work on analyzing and better understanding rater disagreements, and how they could be effectively incorporated into the machine learning developmental pipeline. While these efforts are filling an important gap, there is a lack of a broader framework about the root causes of rater disagreement, and therefore, we situate this work within that broader landscape. In this survey paper, we analyze a broad set of literature on the reasons behind rater disagreements focusing on online toxicity, and propose a detailed taxonomy for the same. Further, we summarize and discuss the potential solutions targeting each reason for disagreement. We also discuss several open issues, which could promote the future development of online toxicity research.

Wenbo Zhang, Aditya Majumdar, Amulya Yadav

Large Language Models (LLMs) have demonstrated remarkable capabilities across various NLP tasks but struggle with code-mixed (or code-switched) language understanding. For example, prior work benchmarking the performance of multilingual LLMs on code-mixed translation tasks has demonstrated that current state-of-the-art multilingual LLMs are ineffective in dealing with code-mixed languages. However, the question of how to improve the capability of multilingual LLMs to handle code-mixed language has not received any attention to date. In this paper, we tackle this research gap by proposing CHAI, a novel general-purpose framework for improving the ability of multilingual LLMs to handle code-mixed languages. CHAI relies on three novel contributions made in this paper. First, we explore the ability of LLMs to provide accurate annotations for code-mixed translation tasks. Second, we leverage this ability of LLMs as annotators to generate preference data for code-mixed translation tasks at scale, which are then used within a reinforcement learning from AI feedback (RLAIF) procedure to improve LLMs' capability on code-mixed tasks. Third, we conduct a rigorous experimental evaluation across various real-world datasets and settings. Our analysis shows that CHAI-powered LLMs outperform state-of-the-art open-source LLMs by 25.66% (in terms of win rate adjudicated by human annotators) in code-mixed translation tasks. This work represents a first step towards developing more inclusive code-mixed LLMs.

Arsh Gupta, Ajay Narayanan Sridhar, Bonam Mingole et al.

Large language models (LLMs) have demonstrated capabilities across diverse domains, yet their performance on rare disease diagnosis from narrative medical cases remains underexplored. We introduce a novel dataset of 176 symptom-diagnosis pairs extracted from House M.D., a medical television series validated for teaching rare disease recognition in medical education. We evaluate four state-of-the-art LLMs such as GPT 4o mini, GPT 5 mini, Gemini 2.5 Flash, and Gemini 2.5 Pro on narrative-based diagnostic reasoning tasks. Results show significant variation in performance, ranging from 16.48% to 38.64% accuracy, with newer model generations demonstrating a 2.3 times improvement. While all models face substantial challenges with rare disease diagnosis, the observed improvement across architectures suggests promising directions for future development. Our educationally validated benchmark establishes baseline performance metrics for narrative medical reasoning and provides a publicly accessible evaluation framework for advancing AI-assisted diagnosis research.

Hangzhi Guo, Pranav Narayanan Venkit, Eunchae Jang et al.

The widespread adoption of large language models (LLMs) and generative AI (GenAI) tools across diverse applications has amplified the importance of addressing societal biases inherent within these technologies. While the NLP community has extensively studied LLM bias, research investigating how non-expert users perceive and interact with biases from these systems remains limited. As these technologies become increasingly prevalent, understanding this question is crucial to inform model developers in their efforts to mitigate bias. To address this gap, this work presents the findings from a university-level competition, which challenged participants to design prompts for eliciting biased outputs from GenAI tools. We quantitatively and qualitatively analyze the competition submissions and identify a diverse set of biases in GenAI and strategies employed by participants to induce bias in GenAI. Our finding provides unique insights into how non-expert users perceive and interact with biases from GenAI tools.

Xinyu Wang, Wenbo Zhang, Sai Koneru et al.

With the rise of AI-generated content spewed at scale from large language models (LLMs), genuine concerns about the spread of fake news have intensified. The perceived ability of LLMs to produce convincing fake news at scale poses new challenges for both human and automated fake news detection systems. To address this gap, this paper presents the findings from a university-level competition that aimed to explore how LLMs can be used by humans to create fake news, and to assess the ability of human annotators and AI models to detect it. A total of 110 participants used LLMs to create 252 unique fake news stories, and 84 annotators participated in the detection tasks. Our findings indicate that LLMs are ~68% more effective at detecting real news than humans. However, for fake news detection, the performance of LLMs and humans remains comparable (~60% accuracy). Additionally, we examine the impact of visual elements (e.g., pictures) in news on the accuracy of detecting fake news stories. Finally, we also examine various strategies used by fake news creators to enhance the credibility of their AI-generated content. This work highlights the increasing complexity of detecting AI-generated fake news, particularly in collaborative human-AI settings.

Aditya Majumdar, Wenbo Zhang, Kashvi Prawal et al.

In an attempt to tackle the UN SDGs, AI for Social Impact (AI4SI) projects focus on harnessing AI to address societal issues in areas such as healthcare, social justice, etc. Unfortunately, despite growing interest in AI4SI, achieving tangible, on-the-ground impact remains a significant challenge. For example, identifying and engaging motivated collaborators who are willing to co-design and deploy AI based solutions in real-world settings is often difficult. Even when such partnerships are established, many AI4SI projects "fail" to progress beyond the proof-of-concept stage, and hence, are unable to transition to at-scale production-level solutions. Furthermore, the unique challenges faced by AI4SI researchers are not always fully recognized within the broader AI community, where such work is sometimes viewed as primarily applied and not aligning with the traditional criteria for novelty emphasized in core AI venues. This paper attempts to shine a light on the diverse challenges faced in AI4SI research by diagnosing a multitude of factors that prevent AI4SI partnerships from achieving real-world impact on the ground. Drawing on semi-structured interviews with six leading AI4SI researchers - complemented by the authors' own lived experiences in conducting AI4SI research - this paper attempts to understand the day-to-day difficulties faced in developing and deploying socially impactful AI solutions. Through thematic analysis, we identify structural and organizational, communication, collaboration, and operational challenges as key barriers to deployment. While there are no easy fixes, we synthesize best practices and actionable strategies drawn from these interviews and our own work in this space. In doing so, we hope this paper serves as a practical reference guide for AI4SI researchers and partner organizations seeking to engage more effectively in socially impactful AI collaborations.

Firdaus Ahmed Choudhury, Ethan Leicht, Jude Ethan Bislig et al.

Machine learning-based decision models are increasingly being used to make decisions that significantly impact people's lives, but their opaque nature leaves end users without a clear understanding of why a decision was made. Counterfactual Explanations (CFEs) have grown in popularity as a means of offering actionable guidance by identifying the minimum changes in feature values required to flip a model's prediction to something more desirable. Unfortunately, most prior research in CFEs relies on artificial evaluation metrics, such as proximity, which may overlook end-user preferences and constraints, e.g., the user's perception of effort needed to make certain feature changes may differ from that of the model designer. To address this research gap, this paper makes three novel contributions. First, we conduct a pilot study with 20 crowd-workers on Amazon MTurk to experimentally validate the alignment of existing CF evaluation metrics with real-world user preferences. Results show that user-preferred CFEs matched those based on proximity in only 63.81% of cases, highlighting the limited applicability of these metrics in real-world settings. Second, inspired by the need to design a user-informed evaluation metric for CFEs, we conduct a more detailed two-day user study with 41 participants facing realistic credit application scenarios to find experimental support for or against three intuitive hypotheses that may explain how end users evaluate CFEs. Third, based on the findings of this second study, we propose the AWP model, a novel user-centric, two-stage model that describes one possible mechanism by which users evaluate and select CFEs. Our results show that AWP predicts user-preferred CFEs with 84.37% accuracy. Our study provides the first human-centered validation for personalized cost models in CFE generation and highlights the need for adaptive, user-centered evaluation metrics.

Bonam Mingole, Aditya Majumdar, Firdaus Ahmed Choudhury et al.

The proliferation of Large Language Models (LLMs) in high-stakes applications such as medical (self-)diagnosis and preliminary triage raises significant ethical and practical concerns about the effectiveness, appropriateness, and possible harmfulness of the use of these technologies for health-related concerns and queries. Some prior work has considered the effectiveness of LLMs in answering expert-written health queries/prompts, questions from medical examination banks, or queries based on pre-existing clinical cases. Unfortunately, these existing studies completely ignore an in-the-wild evaluation of the effectiveness of LLMs in answering everyday health concerns and queries typically asked by general users, which corresponds to the more prevalent use case for LLMs. To address this research gap, this paper presents the findings from a university-level competition that leveraged a novel, crowdsourced approach for evaluating the effectiveness of LLMs in answering everyday health queries. Over the course of a week, a total of 34 participants prompted four publicly accessible LLMs with 212 real (or imagined) health concerns, and the LLM generated responses were evaluated by a team of nine board-certified physicians. At a high level, our findings indicate that on average, 76% of the 212 LLM responses were deemed to be accurate by physicians. Further, with the help of medical professionals, we investigated whether RAG versions of these LLMs (powered with a comprehensive medical knowledge base) can improve the quality of responses generated by LLMs. Finally, we also derive qualitative insights to explain our quantitative findings by conducting interviews with seven medical professionals who were shown all the prompts in our competition. This paper aims to provide a more grounded understanding of how LLMs perform in real-world everyday health communication.

Hangzhi Guo, Thanh Hong Nguyen, Amulya Yadav

This work presents CounterNet, a novel end-to-end learning framework which integrates Machine Learning (ML) model training and the generation of corresponding counterfactual (CF) explanations into a single end-to-end pipeline. Counterfactual explanations offer a contrastive case, i.e., they attempt to find the smallest modification to the feature values of an instance that changes the prediction of the ML model on that instance to a predefined output. Prior techniques for generating CF explanations suffer from two major limitations: (i) all of them are post-hoc methods designed for use with proprietary ML models -- as a result, their procedure for generating CF explanations is uninformed by the training of the ML model, which leads to misalignment between model predictions and explanations; and (ii) most of them rely on solving separate time-intensive optimization problems to find CF explanations for each input data point (which negatively impacts their runtime). This work makes a novel departure from the prevalent post-hoc paradigm (of generating CF explanations) by presenting CounterNet, an end-to-end learning framework which integrates predictive model training and the generation of counterfactual (CF) explanations into a single pipeline. Unlike post-hoc methods, CounterNet enables the optimization of the CF explanation generation only once together with the predictive model. We adopt a block-wise coordinate descent procedure which helps in effectively training CounterNet's network. Our extensive experiments on multiple real-world datasets show that CounterNet generates high-quality predictions, and consistently achieves 100% CF validity and low proximity scores (thereby achieving a well-balanced cost-invalidity trade-off) for any new input instance, and runs 3X faster than existing state-of-the-art baselines.

Amulya Yadav

This thesis proposal makes the following technical contributions: (i) we provide a definition of the Dynamic Influence Maximization Under Uncertainty (or DIME) problem, which models the problem faced by homeless shelters accurately; (ii) we propose a novel Partially Observable Markov Decision Process (POMDP) model for solving the DIME problem; (iii) we design two scalable POMDP algorithms (PSINET and HEALER) for solving the DIME problem, since conventional POMDP solvers fail to scale up to sizes of interest; and (iv) we test our algorithms effectiveness in the real world by conducting a pilot study with actual homeless youth in Los Angeles. The success of this pilot (as explained later) shows the promise of using influence maximization for social good on a larger scale.

Amulya Yadav

The potential of Artificial Intelligence (AI) to tackle challenging problems that afflict society is enormous, particularly in the areas of healthcare, conservation and public safety and security. Many problems in these domains involve harnessing social networks of under-served communities to enable positive change, e.g., using social networks of homeless youth to raise awareness about Human Immunodeficiency Virus (HIV) and other STDs. Unfortunately, most of these real-world problems are characterized by uncertainties about social network structure and influence models, and previous research in AI fails to sufficiently address these uncertainties. This thesis addresses these shortcomings by advancing the state-of-the-art to a new generation of algorithms for interventions in social networks. In particular, this thesis describes the design and development of new influence maximization algorithms which can handle various uncertainties that commonly exist in real-world social networks. These algorithms utilize techniques from sequential planning problems and social network theory to develop new kinds of AI algorithms. Further, this thesis also demonstrates the real-world impact of these algorithms by describing their deployment in three pilot studies to spread awareness about HIV among actual homeless youth in Los Angeles. This represents one of the first-ever deployments of computer science based influence maximization algorithms in this domain. Our results show that our AI algorithms improved upon the state-of-the-art by 160% in the real-world. We discuss research and implementation challenges faced in deploying these algorithms, and lessons that can be gleaned for future deployment of such algorithms. The positive results from these deployments illustrate the enormous potential of AI in addressing societally relevant problems.

Eric Rice, Robin Petering, Jaih Craddock et al.

Objective. To pilot test an artificial intelligence (AI) algorithm that selects peer change agents (PCA) to disseminate HIV testing messaging in a population of homeless youth. Methods. We recruited and assessed 62 youth at baseline, 1 month (n = 48), and 3 months (n = 38). A Facebook app collected preliminary social network data. Eleven PCAs selected by AI attended a 1-day training and 7 weekly booster sessions. Mixed-effects models with random effects were used to assess change over time. Results. Significant change over time was observed in past 6-month HIV testing (57.9%, 82.4%, 76.3%; p < .05) but not condom use (63.9%, 65.7%, 65.8%). Most youth reported speaking to a PCA about HIV prevention (72.0% at 1 month, 61.5% at 3 months). Conclusions. AI is a promising avenue for implementing PCA models for homeless youth. Increasing rates of regular HIV testing is critical to HIV prevention and linking homeless youth to treatment.

Amulya Yadav, Hau Chan, Albert Jiang et al.

This paper presents HEALER, a software agent that recommends sequential intervention plans for use by homeless shelters, who organize these interventions to raise awareness about HIV among homeless youth. HEALER's sequential plans (built using knowledge of social networks of homeless youth) choose intervention participants strategically to maximize influence spread, while reasoning about uncertainties in the network. While previous work presents influence maximizing techniques to choose intervention participants, they do not address three real-world issues: (i) they completely fail to scale up to real-world sizes; (ii) they do not handle deviations in execution of intervention plans; (iii) constructing real-world social networks is an expensive process. HEALER handles these issues via four major contributions: (i) HEALER casts this influence maximization problem as a POMDP and solves it using a novel planner which scales up to previously unsolvable real-world sizes; (ii) HEALER allows shelter officials to modify its recommendations, and updates its future plans in a deviation-tolerant manner; (iii) HEALER constructs social networks of homeless youth at low cost, using a Facebook application. Finally, (iv) we show hardness results for the problem that HEALER solves. HEALER will be deployed in the real world in early Spring 2016 and is currently undergoing testing at a homeless shelter.