7 papers
General Preference Reinforcement Learning
Muhammad Umer, Muhammad Ahmed Mohsin, Ahsan Bilal +5
Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards drives emergent reason…
Improving Latent Generalization Using Test-time Compute
Arslan Chaudhry, Sridhar Thiagarajan, Andrew Lampinen
Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (…
The Illusion of Latent Generalization: Bi-directionality and the Reversal Curse
Julian Coda-Forno, Jane X. Wang, Arslan Chaudhry
The reversal curse describes a failure of autoregressive language models to retrieve a fact in reverse order (e.g., training on ``'' but failing on ``''). Recent work…
Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
Andrew Kyle Lampinen, Martin Engelcke, Yuxuan Li +2
When do machine learning systems fail to generalize, and what mechanisms could improve their generalization? Here, we draw inspiration from cognitive science to argue that one weak…
Towards Responsible Development of Generative AI for Education: An Evaluation-Driven Approach
Irina Jurenka, Markus Kunesch, Kevin R. McKee +71
A major challenge facing the world is the provision of equitable and universal access to quality education. Recent advances in generative AI (gen AI) have created excitement about…
On the generalization of language models from in-context learning and finetuning: a controlled study
Andrew K. Lampinen, Arslan Chaudhry, Stephanie C. Y. Chan +7
Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relati…