Publications
Foundation model research
At Ola Krutrim I worked on the fine-tuning and alignment of Krutrim, a multilingual large language model built for Indian languages. The technical report documents the model, its training data and its evaluation.
arXiv · February 2025
Krutrim LLM: Multilingual Foundational Model for over a Billion People
Technical report from the Krutrim AI team describing a foundational language model trained for India’s languages and cultural context. I am a co-author, credited in the fine-tuning and alignment work.
arXiv:2502.09642Large language modelsMultilingual · Indic languagesFine-tuning and alignment
Published models
Evaluating language beyond the surface
These models focus on specific questions in natural language processing: how well a query is formed, and how much meaningful variety a paraphrase adds. The linked model cards contain the technical details, usage examples and available files.
Text classification · RoBERTa
Query well-formedness scoring
This model scores grammatical correctness and sentence completeness. It is sensitive to capitalization, helping distinguish a complete, well-formed query from fragments or grammatically inconsistent text.
The model card describes applications in chatbot query validation, educational tools and content review. It includes an example using Hugging Face Transformers to score several sentences together.
At its peak the model was downloaded 8.5 million times in a single month on Hugging Face, and it has passed 73 million downloads in total. It was used as the well-formed query classifier in GaRAGe, a benchmark for evaluating retrieval-augmented generation published in Findings of ACL 2025.
The score describes the form of the language. Factual correctness and task relevance require separate evaluation.
73M+ downloads8.5M in one month at peakApache 2.0Text classificationGoogle Wellformed Query dataset
Text ranking · Paraphrase evaluation
Paraphrase diversity ranking
This model distinguishes semantic variation from surface-level wording changes in paraphrases. It supports workflows that generate several candidate paraphrases and then rank them for diversity.
The model card recommends first filtering for semantic similarity using a model trained on natural language inference or semantic textual similarity, then applying the diversity ranker. That separates preserving the source meaning from assessing useful variation.
The public examples reference the Salesken model namespace. The model card provides the original training context and usage guidance.
Apache 2.0Text rankingParaphrase evaluation
More published experiments in language generation, context resolution and text processing are available on my Hugging Face profile.
Technical writing
Questions from building AI products
My articles explore language understanding, training data, language generation and the relationship between AI research and practical products. Each title below links to its original publication.
Blog · Enterprise AI · October 2026
System One models, from Meta’s System 2 distillation to TypeSafe’s Jev, and four rules for using them inside enterprise agents.
Active.Ai · 2018
AI hype, benchmark results and the practical work of building products from research.
Natural language understanding · 2019
A look at understanding in conversational systems and the challenges involved in building a chatbot.
Conversational AI · 2020
Training datasets and their role in the development and adoption of conversational AI.
Natural language generation · 2020
Exploring whether an open-domain dialogue model can be fine-tuned for more specific language generation tasks.
Haptik · Conversations on AI
Brain–computer interfaces, bionics and nonverbal signals as possible directions for virtual assistants.
Analytics India Magazine · Council Post · 2022
An AIM Leaders Council article on forecasting under volatile conditions, written while leading data science at Salesken.
Forbes Technology Council · 2022
Expert panel contribution on matching learning styles with AI assistants and generated practice material.
Forbes Technology Council · 2022
Expert panel contribution on building a resilience roadmap from a risk assessment.
Forbes Technology Council · 2022
Expert panel contribution on using analytics and competitor research to guide a redesign.
Industry perspectives
Research and enterprise context
My career spans conversational banking at Active.Ai, language understanding at Reliance Jio Haptik, sales intelligence at Salesken, applied AI at Ola Krutrim and AI and data platforms at Tata Group. That background connects the technical work on this page with enterprise products and AI leadership.
As a member of Forbes Technology Council and the AIM Leaders Council I contributed expert-panel pieces and a council article on forecasting, listed above. The historical Forbes contributor profile lists my Salesken role at the time.