arXiv AI
Jul 8
Transformers converge to invariant algorithmic cores
arXiv:2602. 22600v2 Announce Type: replace-cross Abstract: Training selects for behavior, not circuitry: many weight configurations can implement the same function.
Understanding the Staged Dynamics of Transformers in Learning Latent Structure
Related stories
arXiv Machine Learning
Jul 15
Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale
arXiv:2603. 06592v2 Announce Type: replace-cross Abstract: Contemporary studies in mechanistic interpretability have uncovered many puzzling phenomena in the neural information processing of Transformer-based language models, such as induction heads, function vectors, and the Hydra effect.
Hugging Face Trending Papers
Jul 13
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks
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 AI
Aug 11
Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic
arXiv:2601. 22510v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often achieve strong benchmark accuracy yet remain brittle under small distribution shifts.
arXiv AI
Jul 14
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks
arXiv:2607. 11875v1 Announce Type: cross Abstract: We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models.
arXiv Machine Learning
Jun 16
Next-Latent Prediction Transformers Learn Compact World Models
arXiv:2511. 05963v4 Announce Type: replace Abstract: Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens.
arXiv Machine Learning
Sep 10
LLM Layers Immediately Correct Each Other
arXiv:2609.07876v1 Announce Type: cross Abstract: Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linea...
arXiv AI
Aug 28
Syntax vs. Semantics: How Transformers Learn Deep Dependencies
The paper investigates how transformers acquire deep semantic dependencies, proposing a mechanistic framework that frames learning as a competition between surface statistics and deep semantics. It identifies a "Gradient Starvation" effect that suppresses error signals for sparse semantic dependencies early in training, delaying structural reasoning until a sudden phase transition. The study also explains the success of Chain-of-Thought strategies and introduces a topology‑aligned contrastive objective that improves variable binding performance by more than twice the gain of standard fine‑tuning.
arXiv Machine Learning
Jul 1
Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers
arXiv:2606. 31779v1 Announce Type: new Abstract: Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token.
arXiv AI
Jul 28
Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models
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.
arXiv AI
Sep 10
Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampling
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...
arXiv Machine Learning
Jun 18
Decomposing Prediction Mechanisms for In-Context Recall
arXiv:2507. 01414v2 Announce Type: replace Abstract: We introduce a new family of toy problems that combine features of linear-regression-style continuous in-context learning (ICL) with discrete associative recall.