pith. sign in

arXiv preprint arXiv:2504.12459 , year=

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 2

years

2026 1 2025 1

representative citing papers

How Do Language Models Compose Functions?

cs.CL · 2025-10-02 · conditional · novelty 6.0

LLMs solve compositional factual recall either by computing intermediates or directly, with mechanism choice correlated to translation geometry in embedding spaces.

citing papers explorer

Showing 2 of 2 citing papers.

  • Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space cs.CL · 2026-05-12 · unverdicted · none · ref 150

    LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.

  • How Do Language Models Compose Functions? cs.CL · 2025-10-02 · conditional · none · ref 29

    LLMs solve compositional factual recall either by computing intermediates or directly, with mechanism choice correlated to translation geometry in embedding spaces.