1 citations · 1 across the 4 of their papers we have counts for
11 papers
Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models
Subramanyam Sahoo, Aman Chadha, Vinija Jain +1
Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported behaviour, the argument goes, it…
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
Mubashara Akhtar, Anka Reuel, Prajna Soni +36
Artificial intelligence benchmarks are an important mechanism to measure model progress and guide deployment decisions. However, benchmarks quickly "saturate", making it difficult…
Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States
Subramanyam Sahoo, Vinija Jain, Aman Chadha +1
Linear probing of large language model (LLM) hidden states is widely used to claim that models learn distinct representations for different reasoning types. We test this by probing…
Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
Anka Reuel, Avijit Ghosh, Jenny Chim +32
Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general c…
The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
Subramanyam Sahoo, Aman Chadha, Vinija Jain +1
Situational awareness, the capacity of an AI system to recognize its own nature, understand its training and deployment context, and reason strategically about its circumstances, i…
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
Subramanyam Sahoo, Aman Chadha, Vinija Jain +1
Recursive self-improvement is moving from theory to practice: modern systems can critique, revise, and evaluate their own outputs, yet iterative self-modification risks subtle alig…