arXiv:2507. 06445v2 Announce Type: replace-cross Abstract: Interpretability research often predicts model responses to targeted mechanistic interventions.
arXiv:2601. 21996v2 Announce Type: replace-cross Abstract: While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive.
arXiv:2606. 32008v1 Announce Type: new Abstract: Mechanistic interpretability (MI) requires full access to model internals, yet the APIs for most widely deployed language models at best expose log-probabilities over output tokens.
arXiv:2608. 12036v1 Announce Type: new Abstract: AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood.
arXiv:2604. 10098v2 Announce Type: replace Abstract: As the foundational architecture of modern machine learning, Transformers have driven remarkable progress across diverse AI domains.
arXiv:2608. 16747v1 Announce Type: cross Abstract: Many areas of AI research, such as language model interpretability and chain of thought faithfulness, seek to explain model behaviors.
arXiv:2606. 29171v1 Announce Type: cross Abstract: While existing data attribution methods can identify which training examples build specific mechanistic circuits, they cannot explain how training data shapes the high-level behavioral decisions a model learns to make.
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:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
arXiv:2607. 07316v1 Announce Type: new Abstract: This article offers a comprehensive overview of mechanistic interpretability, an emerging field that seeks to reverse-engineer the internal algorithms of modern neural networks.
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. 08046v1 Announce Type: cross Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast.
arXiv:2601. 14590v3 Announce Type: replace Abstract: Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine learning model's prediction.