Krishnaram Kenthapadi

Join us at Oracle Health AI & have a real-world impact through our Clinical AI Agent platform used by thousands of medical professionals worldwide. #ML4H #ML4H2025 #NeurIPS #NeurIPS2025 #HealthAI #ClinicalAI #AgenticAI #MultimodalAI #TrustworthyAI #Guardrails #AIAgent #AISafety

For PhD internship roles, we are looking for students pursuing a PhD degree in Computer Science, Applied Mathematics, Statistics, or a related technical field in US, with experience in #TrustworthyAI, #NLP / #LLM, #ReasoningModels, #SpeechAI, #ComputerVision, or related areas.

#ML4H / #NeurIPS attendees: please connect with Tara Taghavi and Jangwon Kim to learn about Oracle Health AI PhD internship (lnkd.in/gajHjWwp + email krishnaram.kenthapadi@oracle.com & tara.taghavi@oracle.com) & full-time applied scientist roles (lnkd.in/gxQiznAd).

Sharing our #ACL2025 work on a production-grade framework for automatic clinical data de-identification for text/audio, combining LLMs, rules, and retrieval: aclanthology.org/2025.acl-indus… #PrivacyPreservingAI #ClinicalAI #DeIdentification #RedactOR

@kkenthapadi, Chief Scientist, Clinical AI @OracleHealth spoke about Trustworthy Health AI: Challenges & Lessons Learned at #Healthcare #NLPSummit 2025. Watch now: hubs.li/Q03jdjlh0 #ResponsibleAI #ClinicalAI #AIEthics

🚀 New Survey Alert! 🚀 Excited to share our latest survey on Trustworthy Retrieval-Augmented Generation (RAG) for Large Language Models (LLMs)! 🎉 With the increasing adoption of RAG in AI applications—ranging from medical question answering to legal document analysis—ensuring trustworthiness has become a critical challenge. In this survey, we provide: ✅ A comprehensive roadmap for developing trustworthy RAG systems ✅ A structured discussion on six key pillars: Reliability, Privacy, Safety, Fairness, Explainability, and Accountability ✅ A deep dive into existing challenges, methods, and open problems ✅ A review of evaluation metrics and future research directions This work is a collaboration with Zheyuan (Frank) Liu, Leyao Wang, Yongjia LEI, Yuying Zhao, Xueqi Cheng, Qingkai Zeng, Xin Luna Dong, Yinglong Xia, Krishnaram Kenthapadi, Ryan A. Rossi, Franck Dernoncourt, Mehrab Tanjim, Nesreen K. Ahmed, Xiaorui Liu, Wenqi Fan, Erik Blasch, Yu Wang, Meng Jiang, and Tyler Derr. Huge thanks to my co-authors and advisors for their insights! 📄 Preprint: lnkd.in/dEaWGFTa 🔍 GitHub Reading List: lnkd.in/dXavPb2i We hope this survey serves as a valuable resource for the community! Looking forward to feedback and discussions. Let’s push forward towards more trustworthy AI!

Attending #KDD2024? Join our tutorial, "Grounding and Evaluation for LLMs" next Monday (w/ @MSameki @ankurtaly -- 2 PM in Room 133). More info: sites.google.com/view/llm-evalu… & arxiv.org/abs/2407.12858 #TrustworthyAI #GenerativeAI #LLM #HealthAI #LLMEvaluation #AIObservability #AISafety

✒️10 Lessons from Developing an AI Chatbot Using Retrieval-Augmented Generation A great blog from @fiddlerlabs goes through ten lessons learned when building a chatbot using RAG Covers a LOT of content - check it out! fiddler.ai/resources/10-l…

🌐 The Missing Link in GenAI: The Power of #ModelMonitoring. Uncover how model monitoring is key to deploying reliable and safe #GenerativeAI. Our blog delves into its crucial role in #LLMs and the exciting advances in #AI. fiddler.ai/blog/the-missi…

🚀 Join @kkenthapadi @DataScienceDojo on 1/24! Explore the importance of adopting #ResponsibleAI principles when developing and deploying #GenerativeAI. See real-world use cases of evaluating and monitoring #LLMs for robustness, security, bias, and more! hubs.la/Q02gsBkM0

Next week, @baxterkb will be joining us on #AIExplained to discuss #EthicalAI practices organizations can follow to minimize potential harms and maximize the social benefits of #AI. Register now to get your questions answered: fiddler.ai/webinars/ai-ex…

💡Explore our latest research paper "Measuring Distributional Shifts in Text: The Advantage of Language Model-Based Embeddings" for key insights into text data analysis using LLMs: arxiv.org/abs/2312.02337 #LLMs #MachineLearning #DataScience #NLP

Join @baxterkb from @salesforce on our next #AIExplained to discuss #EthicalAI practices organizations can follow to minimize potential harms and maximize the social benefits of #AI. 📅Register now: fiddler.ai/webinars/ai-ex…

Unlock the secrets of #responsibleAI with Krishnaram Kenthapadi @kkenthapadi, Chief AI Officer of @fiddlerlabs! Here are the 9 key takeaways he shared at K1st World Symposium:

Please join our #KDD2023 tutorial: #GenerativeAI meets #ResponsibleAI (w/ @hima_lakkaraju @nazneenrajani 10 AM tomorrow in Room 202B): sites.google.com/view/responsib… #LLM #TrustworthyAI #LLMOps #RobustML #FairML #AIObservability #AIGovernance #AISafety #KDD2023

Sharing link to our @icmlconf tutorial slides: docs.google.com/presentation/d… (more info at sites.google.com/view/responsib…) #GenerativeAI #LLM #ResponsibleAI #RobustML #ExplainableAI #FairML #LLMOps #AIObservability #AIGovernance #AISafety #ICML2023

Attending @icmlconf? Please join our tutorial, "Trustworthy Generative AI" at 4PM Mon, July 24 (w/ @hima_lakkaraju @nazneenrajani): sites.google.com/view/responsib… #GenerativeAI #LLM #TrustworthyAI #RobustML #ExplainableAI #FairML #AIObservability #AIGovernance #AISafety #ICML2023

Please check out the tutorial website for more links: sites.google.com/view/responsib…

Sharing slides from our #ICML2023 tutorial, Trustworthy Generative AI (w/ @hima_lakkaraju @nazneenrajani): docs.google.com/presentation/d… #GenerativeAI #LLM #TrustworthyAI #RobustML #ExplainableAI #FairML #AIObservability #AIGovernance #AISafety

@goodside & @simonw showed that LLMs are vulnerable to #PromptInjection attacks. Check out how Fiddler Auditor can help minimize prompt injection attacks through #LLM testing: fiddler.ai/blog/evaluate-… (by @aiyerix & Karen He) #GenerativeAI #ResponsibleAI #RobustML #TrustworthyAI