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:2607. 03640v1 Announce Type: cross Abstract: Fine-tuning can give a language model a hidden behavior--it may give false answers under a narrow condition, or give harmful advice only when a prompt touches a particular topic.
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.
arXiv:2607. 08173v1 Announce Type: new Abstract: Black box auditing of language models is an essential pre-deployment tool, but it may miss subtle forms of misalignment and hidden information.
arXiv:2606. 06320v1 Announce Type: new Abstract: Machine unlearning aims to remove targeted knowledge from a trained model while preserving its general capabilities.
arXiv:2607. 01033v1 Announce Type: new Abstract: Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques.
arXiv:2607. 15495v1 Announce Type: cross Abstract: Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible reasoning.
arXiv:2607. 04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs).
arXiv:2506. 14003v5 Announce Type: replace Abstract: Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks.
arXiv:2606. 19857v1 Announce Type: cross Abstract: Large language models (LLMs) are commonly prompted and interfaced with human-readable natural language, even when the intended reader is another model.
arXiv:2509. 14704v3 Announce Type: replace Abstract: Benchmark saturation and training-data contamination increasingly obscure whether reported gains in large language models (LLMs) reflect genuine advances in reasoning or familiarity with recurring patterns in benchmark problems.
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
arXiv:2603. 18482v2 Announce Type: replace-cross Abstract: Standard decoding strategies for text generation, including top-$k$, nucleus sampling, and contrastive search, select tokens based on likelihood, restricting outputs to high-probability regions.