6 papers
Trust Regions Sell, But Who's Buying? Overlap Geometry as an Alternative Trust Region for Policy Optimization
Gaurish Trivedi, Alakh Sharma, Kartikey Singh Bhandari +4
Standard trust-region methods constrain policy updates via Kullback-Leibler (KL) divergence. However, KL controls only an average divergence and does not directly prevent rare, lar…
The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation
Devanshu Sahoo, Manish Prasad, Vasudev Majhi +5
The rapid integration of Large Language Models (LLMs) into educational assessment rests on the unverified assumption that instruction following capability translates directly to ob…
When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection
Devanshu Sahoo, Manish Prasad, Vasudev Majhi +5
Driven by surging submission volumes, scientific peer review has catalyzed two parallel trends: individual over-reliance on LLMs and institutional AI-powered assessment systems. Th…
How to Trick Your AI TA: A Systematic Study of Academic Jailbreaking in LLM Code Evaluation
Devanshu Sahoo, Vasudev Majhi, Arjun Neekhra +3
The use of Large Language Models (LLMs) as automatic judges for code evaluation is becoming increasingly prevalent in academic environments. But their reliability can be compromise…
OrgAccess: A Benchmark for Role Based Access Control in Organization Scale LLMs
Debdeep Sanyal, Umakanta Maharana, Yash Sinha +4
Role-based access control (RBAC) and hierarchical structures are foundational to how information flows and decisions are made within virtually all organizations. As the potential o…
Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models
Yash Sinha, Manit Baser, Murari Mandal +2
Knowledge erasure in large language models (LLMs) is important for ensuring compliance with data and AI regulations, safeguarding user privacy, mitigating bias, and misinformation.…