Scholar
Harsh Raj
Google Scholar ID: aMI0UhoAAAAJ
Vijil AI
Machine Learning
Natural Language Processing
Generative Networks
Vision-and-Languge models
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
149
H-index
6
i10-index
5
Publications
10
Co-authors
8
list available
Contact
No contact links provided.
Publications
8 items
Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures
2026
Cited
0
OpenThoughts-Agent: Data Recipes for Agentic Models
2026
Cited
0
Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability
2026
Cited
0
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
2026
Cited
9
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
2025
Cited
0
Improving Consistency in Large Language Models through Chain of Guidance
2025
Cited
0
Evaluating Defences against Unsafe Feedback in RLHF
2024
Cited
3
Semantic Consistency for Assuring Reliability of Large Language Models
arXiv.org · 2023
Cited
13
Resume (English only)
Co-authors
8 total
Domenic Rosati
Dalhousie University; Vector Institute
Subhabrata Majumdar
Head of AI, Vijil | Founder, AI Risk and Vulnerability Alliance
Co-author 3
Sinchani Chakraborty
MS CSE, IIT Kharagpur
Co-author 5
SRISHTI GUREJA
Unknown affiliation
Dr. Rahul Katarya
Department of Computer Science & Engineering, Delhi Technological University (DTU), New Delhi, India
Atif Hassan
PhD at the Center of Excellence in Artificial Intelligence, Indian Institute of Technology Kharagpur
