6 papers
Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture
Anand Gupta, Akshat Surolia, Shubham Mishra +2
Digital mental health interventions (DMHIs) offer scalable support, but ensuring they accurately detect users' intent during volatile situations can be challenging. Pure parametric…
Continual Learning for Food Category Classification Dataset: Enhancing Model Adaptability and Performance
Piyush Kaushik Bhattacharyya, Devansh Tomar, Shubham Mishra +6
Conventional machine learning pipelines often struggle to recognize categories absent from the original trainingset. This gap typically reduces accuracy, as fixed datasets rarely c…
Proteus: Append-Only Ledgers for (Mostly) Trusted Execution Environments
Shubham Mishra, João Gonçalves, Chawinphat Tankuranand +4
Distributed ledgers are increasingly relied upon by industry to provide trustworthy accountability, strong integrity protection, and high availability for critical data without cen…
From Facts to Conclusions : Integrating Deductive Reasoning in Retrieval-Augmented LLMs
Shubham Mishra, Samyek Jain, Gorang Mehrishi +4
Retrieval-Augmented Generation (RAG) grounds large language models (LLMs) in external evidence, but fails when retrieved sources conflict or contain outdated or subjective informat…
Predicting Antimicrobial Resistance (AMR) in Campylobacter, a Foodborne Pathogen, and Cost Burden Analysis Using Machine Learning
Shubham Mishra, The Anh Han, Bruno Silvester Lopes +2
Antimicrobial resistance (AMR) poses a significant public health and economic challenge, increasing treatment costs and reducing antibiotic effectiveness. This study employs machin…
Lightweight, Secure and Stateful Serverless Computing with PSL
Alexander Thomas, Shubham Mishra, Kaiyuan Chen +1
We present PSL, a lightweight, secure and stateful Function-as-a-Serivce (FaaS) framework for Trusted Execution Environments (TEEs). The framework provides rich programming languag…