Skip to main content

Indiana University

2 related articles

Subscribe to updates

arXiv Nov 1, 2026
Where to inject activation steering: TopoSteer ranks layers by the connectivity length of displacement clouds, skipping held-out trials
Activation steering adds a vector to a large language model's internal representations at inference time, but where to add it has mostly been settled by trial: existing selectors score how separable the two activation classes are or how well individual displacements align with their mean, without ever steering the model to check. TopoSteer instead scores each layer by the total length of the Euclidean minimum spanning tree of its per-example displacement cloud, measuring whether the mean-difference vector can stand in for those displacements. Across five instruction-tuned models and six binary persona-steering tasks it beats LayerNavigator in most model-budget comparisons, but the margin depends on model and layer budget and is smaller and more mixed on Qwen-7B and Qwen-32B.
Activation steering adds a vector to a large language model's internal representations at inference time, but where to add it has mostly been settled by trial: existing selectors score how separable the two activation classes are or how well individual displacements align with their mean, without ever steering the model to check. TopoSteer instead scores each layer by the total length of the Euclidean minimum spanning tree of its per-example displacement cloud, measuring whether the mean-difference vector can stand in for those displacements. Across five instruction-tuned models and six binary persona-steering tasks it beats LayerNavigator in most model-budget comparisons, but the margin depends on model and layer budget and is smaller and more mixed on Qwen-7B and Qwen-32B.
Indiana University Universidad de Sevilla Massachusetts Institute of Technology Northeastern University The University of Tokyo
Tuc Nguyen（First author）
TopoSteer Activation Steering Persistent Homology Layer Selection for Activation Steering
arXiv Oct 5, 2026
SWR self-supervises training environments from 500 scientific software workflows, lifting Qwen3.8-27B on Terminal-Bench 2 from 47.94% to 53.56%
The authors introduce software-in-the-loop reconstruction (SWR), a self-supervised framework that draws reference outputs and verification targets from existing software workflows, instantiated with 500 workflows across 46 software families and six domains, where Qwen3.8-Max solves 838 tasks over three attempts and yields 1,422 verified trajectories oversampled into 3,000 reconstruction-only training examples, and supervised fine-tuning raises Qwen3.8-27B mean Terminal-Bench 2 performance from 47.94% to 53.56% while achieving the highest mean among four matched-token corpus controls on all four reported evaluations.
The authors introduce software-in-the-loop reconstruction (SWR), a self-supervised framework that draws reference outputs and verification targets from existing software workflows, instantiated with 500 workflows across 46 software families and six domains, where Qwen3.8-Max solves 838 tasks over three attempts and yields 1,422 verified trajectories oversampled into 3,000 reconstruction-only training examples, and supervised fine-tuning raises Qwen3.8-27B mean Terminal-Bench 2 performance from 47.94% to 53.56% while achieving the highest mean among four matched-token corpus controls on all four reported evaluations.
Hong Kong Polytechnic University University of Georgia Indiana University National University of Singapore University of Illinois Chicago University of Maryland, College Park
Zhongzhi Li（First author）
Software-in-the-loop reconstruction Terminal agents Terminal-Bench 2 Supervised Fine-tuning

You’re all caught up