collaborators

5 papers

cs.CL2026

The State-Prediction Separation Hypothesis

Giovanni Monea, Nathan Godey, Kianté Brantley +1

Transformers use the same forward computation stream to both predict the next token and store useful state for future token predictions. We formulate the \emph{state-prediction sep…

cs.CL2025

Breadcrumbs Reasoning: Memory-Efficient Reasoning with Compression Beacons

Giovanni Monea, Yair Feldman, Shankar Padmanabhan +2

The scalability of large language models for long-context reasoning is severely constrained by the linear growth of their Transformer key-value cache, which incurs significant memo…

cs.CL2025

LLMs Are In-Context Bandit Reinforcement Learners

Giovanni Monea, Antoine Bosselut, Kianté Brantley +1

Large Language Models (LLMs) excel at in-context learning (ICL), a supervised learning technique that relies on adding annotated examples to the model context. We investigate a con…

cs.CL2025

Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers

Clément Dumas, Chris Wendler, Veniamin Veselovsky +2

A central question in multilingual language modeling is whether large language models (LLMs) develop a universal concept representation, disentangled from specific languages. In th…

cs.CL2025

Controllable Context Sensitivity and the Knob Behind It

Julian Minder, Kevin Du, Niklas Stoehr +4

When making predictions, a language model must trade off how much it relies on its context vs. its prior knowledge. Choosing how sensitive the model is to its context is a fundamen…