11 papers · 1 filter
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…
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…
Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
Yoav Gur-Arieh, Mor Geva, Atticus Geiger
A key component of in-context reasoning is the ability of language models (LMs) to bind entities for later retrieval. For example, an LM might represent "Ann loves pie" by binding…
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…
The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors
Raphaël Sarfati, Eric Bigelow, Daniel Wurgaft +6
Large language models (LLMs) form implicit beliefs (posteriors over latent variables) from prompts, but we lack a mechanistic account of how these beliefs are encoded in representa…
Constructing Interpretable Features from Compositional Neuron Groups
Or Shafran, Atticus Geiger, Mor Geva
A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early wo…