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:2511. 21594v3 Announce Type: replace Abstract: Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret.
By Alex Ning, Vainateya Rangaraju, Yen-Ling Kuo
The paper investigates how transformer models learn latent structure by training a small decoder-only transformer on three variants of the Alchemy benchmark. It finds that the model acquires different components of latent structure in discrete stages, with a notable asymmetry: it robustly composes fundamental transitions but struggles to decompose complex examples into atomic transitions. Layer‑specific causal interventions reveal plasticity windows where freezing layers delays or prevents stage completion, offering a detailed view of capability evolution during training.
By Rohan Saha, Farzane Aminmansour, Alona Fyshe
Large language models (LLMs) trained on next-token prediction exhibit remarkable in-context learning (ICL) abilities, yet the representations that support ICL remain poorly understood. We consider suc...
arXiv:2609.17376v1 Announce Type: new
Abstract: Large language models (LLMs) trained on next-token prediction exhibit remarkable in-context learning (ICL) abilities, yet the representations that supp...
By Daniel Balcells, Andrew Jun Lee, Chirag Rastogi, Paul M. Riechers, Adam Shai, Xavier Poncini
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
arXiv:2606. 27681v1 Announce Type: new Abstract: World models in partially observed environments rely on latent representations that summarize interaction history, but in many modern LLM-based architectures predictive performance fails to reflect representation quality due to history bypass, rendering the latent state unidentifiable.
By Xiang Gao, Kaiwen Dong, Yuguang Yao, Padmaja Jonnalagedda, Kamalika Das
arXiv:2604. 02029v2 Announce Type: replace Abstract: Latent space is rapidly emerging as a native substrate for language-based models.
By Xinlei Yu, Zhangquan Chen, Yongbo He, Tianyu Fu, Guanting Dong, Cheng Yang, Chengming Xu, Yue Ma, Xiaobin Hu, Zhe Cao, Jie Xu, Guibin Zhang, Jiale Tao, Jiayi Zhang, Siyuan Ma, Kaituo Feng, Haojie Huang, Youxing Li, Ronghao Chen, Huacan Wang, Chenglin Wu, Zikun Su, Xiaogang Xu, Kelu Yao, Kun Wang, Chen Gao, Yue Liao, Ruqi Huang, Tao Jin, Zhucun Xue, Cheng Tan, Jiangning Zhang, Wenqi Ren, Yanwei Fu, Yong Liu, Yu Wang, Xiangyu Yue, Yu-Gang Jiang, Shuicheng Yan
The paper compares latent representations in Selective State Space Models (SSMs) like Mamba and Transformers such as Pythia using Sparse Autoencoders. Across a 10‑million token corpus, 99.98% of Mamba features align closely with Pythia’s, supporting the Universality Hypothesis that core semantic representations are similar across architectures. A tiny 0.02% of features diverge, with Mamba’s recurrent bottleneck causing it to compress syntactic anomalies into polysemantic neurons, whereas Pythia’s attention can isolate distinct formatting edge‑cases.
By Rithin Nagaraj, Rupa Laalasa Oruganti, Prerna Subhashchandra Kunder, Ashwini M Joshi
arXiv:2607. 22646v1 Announce Type: new Abstract: Large language models (LLMs) display a striking ability to predict next observations from Hidden Markov Models (HMMs) via in-context learning (ICL), but the algorithm underlying this capability remains undetermined: prior work has proposed several candidates without consensus, and none has been grounded in the model's internal activations.
By Yijia Dai, Zhaolin Gao, Yahya Sattar, Jennifer J. Sun, Sarah Dean
We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous works on Transformer learning dynamics have so far been mostly tied to specific tasks, we study a generalized class of inductive tasks that unifies several synthetic tasks known in the literature, including in-context n-grams and multi-hop reasoning.
arXiv:2609.08981v1 Announce Type: cross
Abstract: A growing body of work establishes that large language models are not mere statistical memorizers, but are capable of in-context learning: performing...
By Arman Adibi, Alireza Jafari, Mohammad Ghavamzadeh, Hadi Daneshmand