collaborators

7 papers

cs.AI2026

Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes

Alec Harris, Kasey Corra, Archie Chaudhury +1

Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives. H…

cs.CL2026

ResonatorLM: Causal Resonant Field Mixing for Efficient Long-Context Language Modeling

Archie Chaudhury

Contemporary language models are dominated by the transformer architecture, which leverages self-attention mechanisms to enable more efficient, parallelized training across a wide…

cs.LG2026

Forgetting is Not Erasure: Recovering Latent Knowledge via Transport Keys

Archie Chaudhury

Catastrophic forgetting is often framed as a representational problem: after sequential training, a model appears to lose the features that supported performance on earlier tasks.…

cs.LG2026

But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors

Leon Eshuijs, Archie Chaudhury, Alan McBeth +1

LLM-as-a-judge is widely used as a scalable substitute for human evaluation, yet current approaches rely on black-box access and struggle to detect subtle dishonesty, such as sycop…

cs.CL2026

The Hypocrisy Gap: Quantifying Divergence Between Internal Belief and Chain-of-Thought Explanation via Sparse Autoencoders

Shikhar Shiromani, Archie Chaudhury, Sri Pranav Kunda

Large Language Models (LLMs) frequently exhibit unfaithful behavior, producing a final answer that differs significantly from their internal chain of thought (CoT) reasoning in ord…

cs.LG2025

Alignment is Localized: A Causal Probe into Preference Layers

Archie Chaudhury

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a lan…