arXiv Machine Learning
On the Monitorability of Natural Language Autoencoders: Identification vs Discrimination
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 23
Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations
arXiv:2607. 20379v1 Announce Type: new Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it.
Hugging Face Trending Papers
2d ago
Verbalizing Activation Differences with Natural Language Autoencoders
Activation verbalizers translate the internal representations of large language models into human-readable text. The recently proposed natural language autoencoders (NLAs) learn this by reconstructing...
arXiv Computation and Language
1d ago
Verbalizing Activation Differences with Natural Language Autoencoders
The paper investigates natural language autoencoders (NLAs) as tools for verbalizing activation differences in large language models. It examines whether NLAs capture compositional structure, generalize to fine‑tuned models, recover fine‑tuning objectives, and can be specialized for model diffing. Experiments across four models show that NLAs largely succeed in these tasks, though they do not yet match state‑of‑the‑art diffing methods on emergent misalignment detection.
arXiv Machine Learning
Oct 15
Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs
arXiv:2610.20179v1 Announce Type: cross Abstract: Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot...
arXiv Machine Learning
Oct 3
When a Data Artifact Isn't a Shortcut: Causal Auditing of Synthetic RLVR Corpora
The paper audits whether synthetic distractors in RLVR corpora act as shortcuts for learning policies. A classifier using only surface statistics barely outperforms chance, and manual inspection reveals that code distractors are almost identical to correct answers. Experiments with a paraphrase‑matched control show no exploitation advantage for the unmodified data, indicating that the detectable artifact was not used by the policy.
Hugging Face Trending Papers
Oct 14
Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs
Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot control what their activations encode. Humans can l...