arXiv Computation and Language By Alexandru-Iulius Jerpelea

Planting a Latent Variable in Natural-Looking Text: a More Realistic Test of Belief States in LLMs and Their Link to Concept Geometry

Read the original on arXiv Computation and Language →

The paper introduces a method to embed a controllable latent variable into natural-looking text by steering a teacher LLM along eight sparse autoencoder directions that follow a ring-shaped Markov chain. A small transformer trained on this data successfully tracks the Bayesian posterior of the planted variable and arranges the eight states in the same ring order, linking belief states to concept geometry. This demonstrates that LLMs can model latent variables and that concept geometry may arise from the statistical dynamics of these variables.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers
Aug 27

Planting a Latent Variable in Natural-Looking Text: a More Realistic Test of Belief States in LLMs and Their Link to Concept Geometry

The paper investigates whether large language models (LLMs) maintain belief states—probability distributions over latent variables—by embedding a controllable latent variable into natural text. An LLM teacher generates ordinary text while subtly steering it along one of eight sparse autoencoder directions, which follow a ring-shaped Markov chain. A small transformer trained on this data successfully tracks the Bayesian posterior of the planted variable and arranges the eight states on a ring in the same order as the Markov chain, suggesting a link between concept geometry and latent variable dynamics.

arXiv AI
Sep 10

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

A*-Thought-V2 is a framework that models Chain-of-Thought reasoning as a geometric trajectory in a 3D PCA space, using explicit-implicit latent tokens to compress steps that deviate from the main question-to-solution direction. The method measures alignment angles to decide which steps remain text and which become latent, and introduces stepwise embedding forcing and label forcing to train the architecture. Experiments on Qwen models show up to 2.6% accuracy gains, halved response length, and significant reductions in computation and training time.

By Xiaoang Xu, Siyuan Liu, Shuo Wang, Junlan Feng, Fanyu Meng, Zhu Zhang, Jixun Wang, Xiaorong Wang, Zihan Zhou, Xin Li, Chaojun Xiao, Yiming Zhang, Huijia Wu, Liuyu Xiang, Peipei Li, Zhaofeng He