AI access makes people almost entirely unwilling to say "I don't know," study finds
4 min
Minimally Invasive Steering of Language Models
Contrastive Language Models
Parts-of-Speech as Emergent Categories in SAE Latent Space
Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning
Memory Attention
Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models
MemoryAthena: Adaptive Routing over Latent and Generated Memories
Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention
A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal
Objective vs. Search: Decomposing What Makes a Good Tokeniser
MAxBench: A Multinomial Concept Recovery Benchmark
Competence-Gated Pooling of Language Models and Priors for Event Forecasting
1
Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction
LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders
1
Kalman Delta Networks: Uncertainty-aware Associative Memory
One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation
