most citedWho Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations

1 citations · 1 across the 4 of their papers we have counts for

collaborators

11 papers

cs.LG2026

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…

cs.AI2026

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…

cs.CL2026

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…

cs.CY20261 cited

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…

cs.AI2026

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…

cs.AI2026

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…