arXiv:2606. 02609v1 Announce Type: cross Abstract: Activation Oracles (AOs) are promising methods for interpreting residual stream activations.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2607. 23379v1 Announce Type: cross Abstract: Activation Oracles (AOs) are language models trained to answer natural-language questions about another model's internal activations.
arXiv:2606. 10229v1 Announce Type: cross Abstract: We study whether demonstration-curation metrics that detect defective training episodes also improve the downstream behavior-cloning policy that trains on the curated data.
arXiv:2607. 20455v1 Announce Type: cross Abstract: Human-annotated data remains fundamental to training frontier Large Language Models (LLMs).
arXiv:2506. 07406v3 Announce Type: replace-cross Abstract: Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research.
arXiv:2608. 04772v1 Announce Type: cross Abstract: Scaling supervision for multi-turn medical agents is difficult because expert dialogue annotation is costly and clinical conversations are privacy-restricted.
arXiv:2607. 17524v1 Announce Type: cross Abstract: We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task.