4 citations · 9 across the 46 of their papers we have counts for
14 papers · 1 filter
Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
Aryan Kasat, Smriti Singh, Aman Chadha +1
Do large language models reason morally, or do they merely sound like they do? We investigate whether LLM responses to moral dilemmas exhibit genuine developmental progression thro…
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…
Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition
Tanmay Joshi, Shourya Aggarwal, Anusa Saha +7
Deterministic inference is a comforting ideal in classical software: the same program on the same input should always produce the same output. As large language models move into re…
AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints
Aniruddha Roy, Jyoti Patel, Aman Chadha +2
Merging large language models (LLMs) is a practical way to compose capabilities from multiple fine-tuned checkpoints without retraining. Yet standard schemes (linear weight soups,…
Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria
Kartik Garg, Shourya Mishra, Kartikeya Sinha +8
Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving diff…