collaborators

10 papers

cs.CL2026

Position: It's Time to Optimize LLMs for Self-Consistency

Itamar Pres, Belinda Z. Li, Laura Ruis +6

Despite ever-increasing sophistication in language model (LM) pre- and post-training pipelines, many important failures persist: models overcondition on user framing ("sycophancy")…

cs.CL2026

Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision

Zifan Carl Guo, Laura Ruis, Jacob Andreas +1

When does training language models (LMs) to generate explanations of their predictions yield faithful introspection, rather than superficial imitation? We study LMs trained to expl…

cs.LG2026

Self-CTRL: Self-Consistency Training with Reinforcement Learning

Itamar Pres, Laura Ruis, Melat Ghebreselassie +2

Language models (LMs) that faithfully describe their own behavior can more easily be audited, understood, and trusted by users. This paper describes Self-Consistency Training with…

cs.LG2026

Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention

Jing Huang, Daniel Wurgaft, Rachit Bansal +6

Larger models learn tasks smaller models do not. What drives this phenomenon? We develop a simple phenomenological argument that power-law scaling already suggests that a larger mo…

cs.LG2026

Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions

J Rosser, Robert Kirk, Edward Grefenstette +2

Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that induces model behavior. Our framework,…

cs.LG2026

The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning

Yi Xu, Philipp Jettkant, Laura Ruis

The viability of chain-of-thought (CoT) monitoring hinges on models being unable to reason effectively in their latent representations. Yet little is known about the limits of such…