14 papers
A Graph Signal Processing Perspective on Numerical Sequence Representations in LLM In-Context Learning
Jiajun Bao, Zihao Qi, Toni J. B. Liu +6
Pretrained large language models (LLMs) have demonstrated in-context learning (ICL) capabilities for numerical inference over sequences serialized as text. Prior work has identifie…
What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness
Raphaël Sarfati, Pratyush Ranjan Tiwari, Siddharth Boppana +3
Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a…
Jacobian Scopes: token-level causal attributions in LLMs
Toni J. B. Liu, Baran ZadeoÄlu, Nicolas Boullé +3
Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prio…
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
Leon Bergen, Usha Bhalla, Sidharth Baskaran +14
Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. Th…
Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
Siddharth Boppana, Annabel Ma, Max Loeffler +5
We provide evidence of performative chain-of-thought (CoT) in reasoning models, where a model becomes strongly confident in its final answer, but continues generating tokens withou…
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
Eric Bigelow, Raphaël Sarfati, Daniel Wurgaft +5
Large Language Models (LLMs) update their behavior in context, which can be viewed as a form of Bayesian inference. However, the structure of the latent hypothesis space over which…