Adaptive scheduling of interventions in discrete diffusion language models, timed to attribute-specific commitment schedules discovered with sparse autoencoders, delivers precise multi-attribute steering up to 93% strength while preserving generation quality.
hub
Probing Classifiers: Promises, Shortcomings, and Advances
20 Pith papers cite this work, alongside 130 external citations. Polarity classification is still indexing.
20
Pith papers citing it
130
external citations · Crossref
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
verdicts
UNVERDICTED 20representative citing papers
KamonBench is a grammar-generated synthetic dataset of compositional kamon crests with explicit factor annotations to evaluate factor recovery in vision-language models.
Symmetry under affine reparameterizations of hidden coordinates selects a unique hierarchy of shallow coordinate-stable probes and a probe-visible quotient for cross-model transfer.
EEG foundation models encode many traditional hand-crafted features like frequency power, recovering on average 79% of their advantage over random baselines on clinical tasks while leaving residuals on harder ones.
Behavioral directions from one LLM family transfer to others via projection into a shared anchor coordinate space, yielding 0.83 ten-way detection accuracy and steering effects up to 0.46% on held-out models.
Tabular foundation models show substantial depthwise redundancy, so a looped single-layer version achieves comparable results with 20% of the original parameters.
Finite-answer projections of continuation probabilities stabilize before the answer is parseable, showing 17-31 token mean lead in delayed-verdict tasks with Qwen3-4B-Instruct.
Latent space probing on CogVideoX achieves 97.29% F1 for adult content detection on a new 11k-clip dataset with 4-6ms overhead.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
A tabular foundation model with LLM-as-Observer features predicts AI agent decisions in controlled games, outperforming baselines by 4 AUC points and 14% lower error at K=16 interactions.
Instructions trigger a production-centered mechanism in language models, with task-specific information stable in input tokens but varying strongly in output tokens and correlating with behavior.
Chemically meaningful steering for properties like cLogP and TPSA emerges in entangled Transformer-VAE latent spaces only after controlling for SELFIES representation confounds through residualization and decoded traversals.
Conceptors as soft projection matrices from bipolar activations offer a multidimensional, compositional, and geometrically principled method for semantic steering in LLMs that outperforms single-vector baselines in multi-dimensional subspaces.
An encoding probe reconstructs transformer representations from acoustic, phonetic, syntactic, lexical and speaker features, showing independent syntactic/lexical contributions and training-dependent speaker effects.
LLMs encode accurate but brittle internal beliefs about latent game states and convert them poorly into actions, creating systematic gaps that explain strategic failures.
Architecture and training determine whether transformers retain a readable internal signal that lets activation monitors catch errors missed by output confidence.
At sufficient scale, LLMs linearly represent the truth value of factual statements, as shown by visualizations, cross-dataset generalization, and causal interventions that flip truth judgments.
BLOOM is a 176B-parameter open-access multilingual language model trained on the ROOTS corpus that achieves competitive performance on benchmarks, with improved results after multitask prompted finetuning.
Overthinking in medical QA is linearly decodable at 71.6% accuracy yet fixed residual-stream steering yields no correction across 29 configurations, while enabling selective abstention with AUROC 0.610.
The note proposes applying emotion probes to SAE-analyzed strategic concealment episodes to test if emotion vectors capture causal emotions or situational projections in AI models.
citing papers explorer
-
Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models
Adaptive scheduling of interventions in discrete diffusion language models, timed to attribute-specific commitment schedules discovered with sparse autoencoders, delivers precise multi-attribute steering up to 93% strength while preserving generation quality.
-
Deep Minds and Shallow Probes
Symmetry under affine reparameterizations of hidden coordinates selects a unique hierarchy of shallow coordinate-stable probes and a probe-visible quotient for cross-model transfer.
-
Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
Tabular foundation models show substantial depthwise redundancy, so a looped single-layer version achieves comparable results with 20% of the original parameters.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling
A tabular foundation model with LLM-as-Observer features predicts AI agent decisions in controlled games, outperforming baselines by 4 AUC points and 14% lower error at K=16 interactions.
-
Molecules Meet Language: Confound-Aware Representation Learning and Chemical Property Steering in Transformer-VAE Latent Spaces
Chemically meaningful steering for properties like cLogP and TPSA emerges in entangled Transformer-VAE latent spaces only after controlling for SELFIES representation confounds through residualization and decoded traversals.
-
Conceptors for Semantic Steering
Conceptors as soft projection matrices from bipolar activations offer a multidimensional, compositional, and geometrically principled method for semantic steering in LLMs that outperforms single-vector baselines in multi-dimensional subspaces.
-
Architecture Determines Observability of Transformers
Architecture and training determine whether transformers retain a readable internal signal that lets activation monitors catch errors missed by output confidence.