collaborators

5 papers

cs.AI2026

Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition

Prasoon Goyal, Sattvik Sahai, Michael Johnston +14

Post-training Large Language Models requires diverse, high-quality data which is rare and costly to obtain, especially in low resource domains and for multi-turn conversations. Com…

cs.CL2026

Addressing LLM Diversity by Infusing Random Concepts

Pulin Agrawal, Prasoon Goyal

Large language models (LLMs) are known to produce outputs with limited diversity. In this work, we study whether infusing random concepts in the prompts can improve the diversity o…

cs.LG2025

From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs

Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna +5

Recent work has shown that fine-tuning on insecure code data can trigger an emergent misalignment (EMA) phenomenon, where models generate malicious responses even to prompts unrela…

cs.AI2025

Amazon Nova AI Challenge -- Trusted AI: Advancing secure, AI-assisted software development

Sattvik Sahai, Prasoon Goyal, Michael Johnston +13

AI systems for software development are rapidly gaining prominence, yet significant challenges remain in ensuring their safety. To address this, Amazon launched the Trusted AI trac…

cs.RO2025

Is the House Ready For Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering

Vishnu Sashank Dorbala, Prasoon Goyal, Robinson Piramuthu +3

We present and tackle the problem of Embodied Question Answering (EQA) with Situational Queries (S-EQA) in a household environment. Unlike prior EQA work tackling simple queries th…