Shlok Gilda

Peer-Reviewed Publications/Patents

1. AI You Can Trust: Communication-Aware, Ambiguity-Sensitive, and Interpretable NLP for High-Stakes Domains
   B. J. Dorr, C. Jayaweera, S. Youm, S. Gilda.
   Accepted at The 39th International Florida AI Research Society (FLAIRS) Conference 2026
2. Epistemic Accountability for Agentic Financial AI: The Transformer Mandate and Evidence Lifecycle Management
   Sankalp Gilda¹, Shlok Gilda¹ (co-first authors).
   Accepted at ICLR 2026 Workshop on Advances in Financial AI
3. Structured Abductive-Deductive-Inductive Reasoning for LLMs via Algebraic Invariants
   Sankalp Gilda¹, Shlok Gilda¹ (co-first authors).
   Accepted at ICLR 2026 Workshop on Logical Reasoning of Large Language Models
4. An Elicitation-Matrix Approach to Pragmatic Context Modeling in Low-Resource Machine Translation: The Case of Akuapem Twi
   K. Yamoah, G. Agyapong, N. Parekh, D. Brinkley, C. Jayaweera, S. Gilda, B. J. Dorr, E. Dorley, K. Scroggins.
   Accepted at The 39th International Florida AI Research Society (FLAIRS) Conference 2026
5. Navigating the Blue Nowhere: A Framework for Mapping Validated Adversarial Trajectories
   Shlok Gilda, Karsten Martiny, Justin Ho, Laura Tinnel, Grit Denker, Bonnie J. Dorr.
   2025 IEEE International Conference on Data Mining Workshops (ICDMW), 2025, pp. 1055–1062
   📄 Paper
6. Are Fact-Checking Tools Helpful? An Exploration of the Usability of Google Fact Check
   Yang Qiangeng, Tess Christensen, Shlok Gilda, et al.
   Presented at 5th EAI International Conference on Data and Information in Online Systems (2024).
   📄 Paper
7. People Still Care About Facts: Twitter Users Engage More with Factual Discourse than Misinformation--A Comparison Between COVID and General Narratives on Twitter
   Luiz Giovanini¹, Shlok Gilda¹ (co-first authors), Mirela Silva², Fabrício Ceschin², et al.
   Presented at SocialSec 2023.
   Winner of the Best Paper Award!
   📄 Paper
8. None Shall Pass: A blockchain-based federated identity management system
   Shlok Gilda, Tanvi Jain, Aashish Dhalla.
   Presented at 4th International Conference on Inventive Computation and Information Technologies (ICICIT 2022).
   📄 Paper
9. Predicting Different Types of Subtle Toxicity in Unhealthy Online Conversations
   Shlok Gilda, Luiz Giovanini, Mirela Silva, Daniela Oliveira.
   Presented at EUSPN's 2nd International Workshop on Artificial Intelligence for Natural Language Processing (IANLP 2021).
   📄 Paper
10. Epistemic Accountability Engine for AI-Assisted Software Engineering (US Provisional Patent)
    Sankalp Gilda, Shlok Gilda.
    US Provisional Patent Application No. 63/969,626.
11. Identity Attribute Confidence Scoring while Certifying Authorization Claims (US Patent)
    Parag Gokhale, Sakshi Malik, Shlok Gilda, Shams Hasan Rizvi, Rohan Poulose.
    United States Patent and Trademark Office (2020).
    📄 Paper
12. Blockchain for Student Data Privacy and Consent
    Shlok Gilda, Maanav Mehrotra.
    Presented at 2018 International Conference on Computer Communication and Informatics (ICCCI 2018).
    📄 Paper
13. Source Code Classification Using Neural Networks
    Shlok Gilda.
    Presented at 14th International Joint Conference on Computer Science and Software Engineering (JCSSE 2017).
    📄 Paper
14. Smart Music Player Integrating Facial Emotion Recognition and Music Mood Recommendation
    Shlok Gilda, Husain Zafar, Chintan Soni, Kshitija Waghurdekar.
    Presented at 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET 2017).
    📄 Paper

Pre-prints

1. Principled Design for Epistemic Accountability in AI-Assisted Engineering
   Sankalp Gilda¹, Shlok Gilda¹ (co-first authors).
   arXiv Pre-print, 2025.
   📄 Paper

Under Review

1. Position: AI Architectural Decisions Require Epistemic Rigor and Temporal Accountability
   Sankalp Gilda¹, Shlok Gilda¹ (co-first authors).
   Submitted to ICML 2026 Position Paper Track
2. The Admission Control Gap: Longitudinal Evidence of Growing Technical Security Debt in Open Source Dependencies
   Shlok Gilda, Marcus Botacin, Bonnie J. Dorr.
   Submitted to The 42nd IEEE International Conference on Software Maintenance and Evolution (ICSME) 2026
3. Children's English Reading Story Generation via Supervised Fine-Tuning Compact LLMs with Controllable Difficulty and Safety
   Q. Shen, V. Cao, M. Yao, S. Gilda, B. J. Dorr.
   Submitted to 21st Workshop on Innovative Use of NLP for Building Educational Applications 2026
4. Structure-Grounded Medical QA: RDF Retrieval and Claim-Level Verification for Faithful LLM Generation
   A. N. Stocks, J. Salve, I. Hunter, P. A. Kunchepu, S. Youm, S. Gilda, B. J. Dorr.
   Submitted to Structured Understanding, Retrieval, and Generation in the LLM Era 2026

In-Progress Projects

1. Temporal Evolution of Security Concerns in OSS: Investigating the Role of Contributor Characteristics and Behaviors
   Shlok Gilda, Marcus Botacin, Bonnie Dorr.
2. Developing a Communication-Based Health Score for OSS Projects: Insights and Recommendations
   Shlok Gilda, Bonnie Dorr.