The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The study investigates whether adaptive layer-skipping and repetition programs truly improve language‑model inference or merely exploit input‑blind controls. Using 32 such programs on Qwen3‑4B‑Base and Llama‑3.1‑8B across 4,413 multiple‑choice items, the authors compare real program gains to those from input‑blind perturbations and fixed letter offsets. Results show that input‑blind controls can produce comparable or even larger headroom, and that real programs only outperform controls in specific menu configurations, indicating that the apparent benefits may not be due to the actual layer computation choices.
The study investigates how task context reshapes the roles of shared attention heads in large language models. By applying identical graph facts and measuring interventions on attention heads and downstream activations, the authors show that task changes redistribute influence across five open‑weight models, causing the same heads to respond to different facts and affect later components differently. Linear response maps before and after activation edits reveal significant reductions in prediction error, indicating that task context alters both the facts processed and the downstream impact of shared components.
arXiv:2608. 04021v1 Announce Type: cross Abstract: Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the same way regardless of where the readout slot sits.
arXiv:2610.14958v1 Announce Type: new Abstract: Activation steering has recently been used as a memory for skills: past experiences of an agent are stored as steering vectors and retrieved later. Fac...
arXiv:2608. 15022v1 Announce Type: new Abstract: Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it flexibly.
The paper investigates how a language model’s first answer to a yes/no question influences its subsequent answer to a different question about the same entity, a phenomenon termed self‑commitment. By fixing the initial answer and measuring changes in the second across 3,600 question pairs for 22 open‑weight models (0.5B–72B parameters), the authors find that each answer writes a commitment direction into the residual stream, and the similarity of these directions predicts answer coupling. They show that ablating a shared direction reduces coupling significantly, while the reading circuit for this direction varies with model size, instruction tuning, and prompts, and that sparing the attention sink during ablation preserves low perplexity cost in most models.