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.
By Yibei Guo, Rui Liu
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.
By Sovesh Mohapatra, Dani S Bassett
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.
By Han-yu Wang
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...
By Vedant Jumle
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.
By Parsa Mazaheri
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.
By Marcus Armstrong
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
By Deepanshu Mody, Samarth Agarwal, Utkarsh Mittal, Dipesh Mahato
arXiv:2603.13911v2 Announce Type: replace
Abstract: A language model can give the wrong answer even when the correct answer is decodable from its intermediate states. To study this gap between decoda...
By Valeria Ruscio, Keiran Thompson
The paper investigates how visual interventions—training‑free edits applied to multimodal large language models—affect hallucinations and prediction quality. By applying a visual‑residual edit across successive decoder layers and matching its RMS strength, the authors identify an Evidence Anchoring Boundary (EAB) where the intervention’s influence drops sharply; effects before the EAB are 13.78–26.10× larger than after it. They further compare counterfactual subtraction across different question types and introduce calibrated selective routing, which only alters predictions when calibration supports an intervention, improving attribute accuracy by 1.56–1.81 percentage points while avoiding the harms of universal subtraction.
By Qiji Zhou, Junyi Hu, Peiyu Wang, Yue Zhang
arXiv:2610.33025v1 Announce Type: cross
Abstract: Letting a language model take gradient steps on the text it is reading, known as dynamic evaluation, lowers its loss on the rest of the document. Its...
By Surya Saka
arXiv:2610.32309v1 Announce Type: new
Abstract: Why can a task-preserving rewrite turn a correct answer into a failure while a larger internal change leaves the answer intact? We develop a direction-...
By Zhibo Hu, Chen Wang, Yanfeng Shu, Liming Dong, Hye-young Paik, Liming Zhu
The study investigates whether the phenomenon of capitulation—where language models abandon correct answers under user pushback—can be identified as a linear direction in the residual stream and whether this direction emerges with model scale. Analyzing eight instruction‑tuned models from 0.5 B to 14 B parameters, the authors find no usable direction below 7 B, but a clear direction at 7 B, 8 B, and 14 B that, when ablated, reduces the reversal rate of correct answers by about 4.8 percentage points. The research also documents five measurement hazards, including a numerical‑precision effect that alters roughly one in ten episode labels.
By Saad Aamir, Muhammad Awais Bin Adil