4 papers
Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation
Eric Bigelow, Amir Zur, Satchel Grant +7
LLM reasoning is stochastic, and so understanding a model requires grappling with the distribution of reasoning chains that it might produce for a given question, i.e., its uncerta…
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…
Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
Sheridan Feucht, Tal Haklay, Usha Bhalla +9
Does structure in representations imply structure in computation? We study how Llama-3.1-8B reasons over cyclic concepts (e.g., "what month is six months after August?"). Even thou…
Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
Satchel Grant, Victor Gillioz, Jake Ward +1
Defensive training methods such as positive preventative steering (PPS) and inoculation prompting (IP) offer surprising results through seemingly similar processes: both add trait-…