2 papers
cs.LG2025
Embedded Safety-Aligned Intelligence via Differentiable Internal Alignment Embeddings
Harsh Rathva, Ojas Srivastava, Pruthwik Mishra
We introduce Embedded Safety-Aligned Intelligence (ESAI), a theoretical framework for multi-agent reinforcement learning that embeds alignment constraints directly into agents inte…
cs.CL2025
"AGI" team at SHROOM-CAP: Data-Centric Approach to Multilingual Hallucination Detection using XLM-RoBERTa
Harsh Rathva, Pruthwik Mishra, Shrikant Malviya
The detection of hallucinations in multilingual scientific text generated by Large Language Models (LLMs) presents significant challenges for reliable AI systems. This paper descri…