arXiv:2603.27518v4 Announce Type: replace Abstract: Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemb...
The paper challenges the notion that refusal in large language models is governed by a single direction in activation space. It demonstrates that different refusal and non‑compliance categories map to distinct geometric directions, yet steering along any of these directions yields similar refusal–over‑refusal trade‑offs, acting as a shared one‑dimensional control knob. Using sparse autoencoders, the authors reveal a structured internal representation of refusal, comprising a reusable core of shared latents and style‑ or domain‑specific latents, and show that linear interventions collapse this structure into uniform behavioral control.
arXiv:2603. 06591v2 Announce Type: replace Abstract: Transformers frequently allocate disproportionate attention to specific tokens, a phenomenon known as attention sinks.
The paper introduces the Communication Map, a method that charts every potential communication channel in a transformer model using only its weights. It generalizes previous coupling metrics into a single coefficient covering all 18 connection classes, revealing that 70‑89% of head pairs are non‑randomly oriented and identifying strong or avoiding couplings. The authors demonstrate the map’s utility by recovering known induction circuits and uncovering a two‑dimensional stream subspace whose removal eliminates induction capabilities across several models.
arXiv:2606.04160v2 Announce Type: replace-cross Abstract: Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse harmful or disallowed requ...
arXiv:2608. 12334v1 Announce Type: cross Abstract: Despite the impressive multilingual capabilities of Large Language Models, the latent dynamics dictating language selection remain poorly understood.
arXiv:2603.13359v2 Announce Type: replace Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusa...
arXiv:2608.22034v1 Announce Type: new Abstract: Mechanistic interpretability has identified transformer circuits, but lacks a shared vocabulary for describing how their functions compose across tasks...
arXiv:2605. 27458v2 Announce Type: replace-cross Abstract: Transformer has significantly propelled the development of artificial intelligence, and certainly the development of agents as well.
The paper investigates how transformer models learn latent structure by training a small decoder-only transformer on three variants of the Alchemy benchmark. It finds that the model acquires different components of latent structure in discrete stages, with a notable asymmetry: it robustly composes fundamental transitions but struggles to decompose complex examples into atomic transitions. Layer‑specific causal interventions reveal plasticity windows where freezing layers delays or prevents stage completion, offering a detailed view of capability evolution during training.
The paper introduces a Mixture‑Gated Theory of Anisotropic Representation Dynamics that decomposes Transformer self‑attention into value transport, query gating, and key gating. It shows that the geometry of attended representations can cause a representation difference to contract or expand, a phenomenon termed gating‑induced regime switching. The authors derive a spectral criterion to predict switching, quantify its strength, and identify subspaces where switching occurs, validating these predictions experimentally across four Transformer architectures.
arXiv:2606. 25010v1 Announce Type: new Abstract: Neural scaling laws for transformer language models predict smooth improvements in pretraining loss with increasing parameters, but downstream capabilities such as in-context learning are known to emerge abruptly past a certain model scale.