Probes predicting future behaviors from intermediate steps enable Future Probe Controlled Generation for steering large reasoning models with minimal quality degradation.
Future Lens: Anticipating Subsequent Tokens from a Single Hidden State , url=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
PRISM is a new activation-conditioned model that recovers full sets of simultaneous instructions from LLM hidden states via judge-guided GRPO training and outperforms prior activation-to-language methods on security-relevant tasks.
Query Lens extends Logit Lens to interpret sparse features via key-value analysis and indirect effects, yielding coherent token signatures where Logit Lens fails, and proposes the Subspace Channel Hypothesis.
A new framework shows concept subspaces are not unique, estimator choice affects containment and disentanglement, LEACE works well but generalizes poorly, and HuBERT encodes phone info as contained and disentangled from speaker info while speaker info resists compact containment.
A two-stream Transformer variant that separates state storage from next-token prediction improves validation loss and downstream task performance by 2-3 points over standard Transformers.
AERIC uses a 387-parameter head on LLM hidden states for same-pass anticipatory detection of implicit harm, reporting AUROC gains on DiaSafety and Harmful Advice plus low-latency trigger rates on HarmBench and SocialHarmBench.
citing papers explorer
-
A framework for analyzing concept representations in neural models
A new framework shows concept subspaces are not unique, estimator choice affects containment and disentanglement, LEACE works well but generalizes poorly, and HuBERT encodes phone info as contained and disentangled from speaker info while speaker info resists compact containment.
-
The State-Prediction Separation Hypothesis
A two-stream Transformer variant that separates state storage from next-token prediction improves validation loss and downstream task performance by 2-3 points over standard Transformers.
-
AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue
AERIC uses a 387-parameter head on LLM hidden states for same-pass anticipatory detection of implicit harm, reporting AUROC gains on DiaSafety and Harmful Advice plus low-latency trigger rates on HarmBench and SocialHarmBench.