arXiv subjects

Ananditha Raghunath

Publications and source records attributed to Ananditha Raghunath.

5 recordsLinked to original sources

arXiv2026

Designing Medical Chatbots where Accuracy and Acceptability are in Conflict: An Exploratory, Vignette-based Study in Urban India

When medical chatbots provide advice that conflicts with users' lived care experiences, users are left to interpret, negotiate, and evaluate the legitimacy of that guidance. In India, the widespread overuse of antibiotics, antidiarrheals, and injections has shifted patient expectations away from the guideline-aligned advice that chatbots are trained to provide. We present a mixed-methods, vignette-based study with 200 urban Indian adults examining preferences for and against guideline-aligned, norm-divergent advice in chatbot transcripts. We find that a majority of users reject such advice, drawing on diverse rationales grounded in their lived expectations. Through the design and introduction of context-aware nudges, we support expectation alignment that shifts preferences towards transcripts containing guideline-aligned advice. In doing so, we surface key tensions in the equitable design of medical chatbots in the Global South.

cs.HC↗

arXiv2024

HEALTH-PARIKSHA: Assessing RAG Models for Health Chatbots in Real-World Multilingual Settings

Assessing the capabilities and limitations of large language models (LLMs) has garnered significant interest, yet the evaluation of multiple models in real-world scenarios remains rare. Multilingual evaluation often relies on translated benchmarks, which typically do not capture linguistic and cultural nuances present in the source language. This study provides an extensive assessment of 24 LLMs on real world data collected from Indian patients interacting with a medical chatbot in Indian English and 4 other Indic languages. We employ a uniform Retrieval Augmented Generation framework to generate responses, which are evaluated using both automated techniques and human evaluators on four specific metrics relevant to our application. We find that models vary significantly in their performance and that instruction tuned Indic models do not always perform well on Indic language queries. Further, we empirically show that factual correctness is generally lower for responses to Indic queries compared to English queries. Finally, our qualitative work shows that code-mixed and culturally relevant queries in our dataset pose challenges to evaluated models.

cs.CL↗

arXiv2024

eKichabi v2: Designing and Scaling a Dual-Platform Agricultural Technology in Rural Tanzania

Although farmers in Sub-Saharan Africa are accessing feature phones and smartphones at historically high rates, they face challenges finding a robust network of agricultural contacts. With collaborators, we conduct a quantitative survey of 1014 agricultural households in Kagera, Tanzania to characterize technology access, use, and comfort levels in the region. Recognizing the paucity of research on dual-platform technologies that cater to both feature phone and smartphone users, we develop and deploy eKichabi v2, a searchable directory of 9833 agriculture-related enterprises accessible via a USSD application and an Android application. To bridge the gap in affordances between the two applications, we conduct a mixed methods pilot leveraging mobile money agents as intermediators for our USSD application's users. Through our investigations, we identify the advantages, obstacles, and critical considerations in the design, implementation, and scalability of agricultural information systems tailored to both feature phone and smartphone users in Sub-Saharan Africa.

cs.HC↗

arXiv2023

Extensible Machine Learning for Encrypted Network Traffic Application Labeling via Uncertainty Quantification

With the increasing prevalence of encrypted network traffic, cyber security analysts have been turning to machine learning (ML) techniques to elucidate the traffic on their networks. However, ML models can become stale as new traffic emerges that is outside of the distribution of the training set. In order to reliably adapt in this dynamic environment, ML models must additionally provide contextualized uncertainty quantification to their predictions, which has received little attention in the cyber security domain. Uncertainty quantification is necessary both to signal when the model is uncertain about which class to choose in its label assignment and when the traffic is not likely to belong to any pre-trained classes. We present a new, public dataset of network traffic that includes labeled, Virtual Private Network (VPN)-encrypted network traffic generated by 10 applications and corresponding to 5 application categories. We also present an ML framework that is designed to rapidly train with modest data requirements and provide both calibrated, predictive probabilities as well as an interpretable "out-of-distribution" (OOD) score to flag novel traffic samples. We describe calibrating OOD scores using p-values of the relative Mahalanobis distance. We demonstrate that our framework achieves an F1 score of 0.98 on our dataset and that it can extend to an enterprise network by testing the model: (1) on data from similar applications, (2) on dissimilar application traffic from an existing category, and (3) on application traffic from a new category. The model correctly flags uncertain traffic and, upon retraining, accurately incorporates the new data.

cs.CR↗

arXiv2022

Testing a Drop of Liquid Using Smartphone LiDAR

We present the first system to determine fluid properties using the LiDAR sensors present on modern smartphones. Traditional methods of measuring properties like viscosity require expensive laboratory equipment or a relatively large amount of fluid. In contrast, our smartphone-based method is accessible, contactless and works with just a single drop of liquid. Our design works by targeting a coherent LiDAR beam from the phone onto the liquid. Using the phone's camera, we capture the characteristic laser speckle pattern that is formed by the interference of light reflecting from light-scattering particles. By correlating the fluctuations in speckle intensity over time, we can characterize the Brownian motion within the liquid which is correlated with its viscosity. The speckle pattern can be captured on a range of phone cameras and does not require external magnifiers. Our results show that we can distinguish between different fat contents as well as identify adulterated milk. Further, algorithms can classify between ten different liquids using the smartphone LiDAR speckle patterns. Finally, we conducted a clinical study with whole blood samples across 30 patients showing that our approach can distinguish between coagulated and uncoagulated blood using a single drop of blood.

cs.CY↗