collaborators

5 papers

cs.LG2026

Assign and Add: A Mechanistic Study of Compositional Arithmetic

Brady Exoo, Alberto Bietti, John Sous

Large language models are able to compose skills in order to perform complex tasks, many of which might not have been seen during training. The details of how exactly this composit…

cs.LG2026

Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs

Andy Zeyi Liu, Michael Zhang, Ilana Greenberg +3

Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong control, but caches guidance tokens at ev…

stat.ML2026

Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization

Andy Zeyi Liu, Elliot Paquette, John Sous

Training loss and throughput can hide distinct internal representation in language-model training. To examine these hidden mechanics, we use spectral measurements as practical and…

cs.LG2025

(Im)possibility of Automated Hallucination Detection in Large Language Models

Amin Karbasi, Omar Montasser, John Sous +1

Is automated hallucination detection possible? In this work, we introduce a theoretical framework to analyze the feasibility of automatically detecting hallucinations produced by l…

cs.AI2025

PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving

Kaiyue Feng, Yilun Zhao, Yixin Liu +4

We introduce PHYSICS, a comprehensive benchmark for university-level physics problem solving. It contains 1297 expert-annotated problems covering six core areas: classical mechanic…