arXiv:2606. 24026v1 Announce Type: new Abstract: Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains labor-intensive and difficult to standardize.
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. 00089v1 Announce Type: new Abstract: Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact.
arXiv:2601. 09624v2 Announce Type: replace-cross Abstract: Machine unlearning is becoming essential for building trustworthy and compliant language models.
arXiv:2608. 10430v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions to force a resolution rather than expressing uncertainty.
arXiv:2606. 29604v1 Announce Type: cross Abstract: We aim to discover diverse, generalizable perturbations of LLM internals that can surface hidden behavioral modes.
arXiv:2608. 05732v1 Announce Type: new Abstract: Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment.
arXiv:2606. 16939v1 Announce Type: cross Abstract: A prominent research direction in mechanistic interpretability is learning sparse circuits over LLM components to reveal how they jointly produce model behavior.
arXiv:2608. 02585v1 Announce Type: new Abstract: Optimization-based latent reasoning improves large language model outputs by optimizing instance-specific continuous states at test time while keeping model parameters frozen.
arXiv:2603. 14465v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions.
arXiv:2509. 24808v2 Announce Type: replace Abstract: Explaining why a language model produces a particular output requires local, input-level explanations.
arXiv:2602. 06841v4 Announce Type: replace Abstract: Over the last decade, Explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs to outputs under a fixed decision structure.
arXiv:2601. 22594v2 Announce Type: replace-cross Abstract: The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986).