arXiv AI
Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
2d ago
Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
arXiv:2601.08058v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting often improves the reasoning performance of large language models (LLMs), but the internal signal that trigg...
arXiv AI
2d ago
Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer
arXiv:2608.30462v1 Announce Type: cross Abstract: Large language models exhibit substantial performance variation across languages, even when solving semantically equivalent tasks. Existing analyses...
arXiv Machine Learning
Jun 2
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
arXiv:2603. 03031v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning.
arXiv AI
Jul 29
Penelope: Localized Latent Recurrence for Efficient Structured Reasoning
arXiv:2607. 25915v1 Announce Type: new Abstract: Complex structured reasoning tasks often require additional computation, yet current language models obtain it mainly by increasing parameter scale or by serializing intermediate steps as chain-of-thought (CoT) tokens.
arXiv Computer Vision
2d ago
LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck
arXiv:2606.13061v3 Announce Type: replace Abstract: Reasoning-driven universal multimodal embedding has advanced rapidly by introducing Chain-of-Thought (CoT) reasoning into the embedding pipeline. D...
arXiv AI
Jul 29
Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
arXiv:2601. 03595v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (\eg backtracking, cross-verification) during the reasoning process, which improves their performance on complex tasks.