arXiv:2606. 08365v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can behave inconsistently across contexts and perturb unrelated features.
arXiv:2610.16325v1 Announce Type: new Abstract: When a steering intervention changes a language model's behavior, which part of the intervention deserves the credit? We test this question for a targe...
arXiv:2606. 18322v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) decompose residual-stream activations into interpretable features.
arXiv:2607. 10226v1 Announce Type: new Abstract: We evaluate when sparse autoencoder (SAE) features act as localized control handles for safety-relevant behavior.
The paper introduces a controlled benchmark for deciding whether to acquire a third modality or abstain when audio, video, and text scores conflict. A threshold policy that observes two signed scores can request the third at a cost and abstain, achieving higher targeted decision accuracy and utility than always-answer fusion under certain reward settings. Experiments on synthetic and real data show that the policy’s advantage depends on the ambiguity mechanism, budget constraints, and the ranking of observed pairs, highlighting the trade‑off between full-modality accuracy and pre‑request selection value.
arXiv:2608. 09490v1 Announce Type: new Abstract: Task arithmetic treats fine-tuning displacements as composable directions in weight space, yet it remains unclear when parameter addition reflects predictable changes in model function.
arXiv:2607.12176v2 Announce Type: replace Abstract: Ambivalence and hesitancy (A/H) undermine digital behaviour-change interventions, and recognizing them automatically from video is the goal of the...
The study investigates why large language models (LLMs) show different triage performance when answering clinician‑authored vignettes in multiple‑choice versus free‑text formats. Using sparse‑autoencoder features on Gemma 3 and Qwen3 models, the authors find that medical information is encoded similarly in both formats, but at the decision token the multiple‑choice scaffold dominates, with over 91% of attribution coming from scaffold‑peaking features. The effect varies by model, and shuffling option order eliminates simple positional bias, suggesting the format influence is tied to answer selection rather than earlier case processing.
arXiv:2610.22640v1 Announce Type: new Abstract: Model-editing backdoors aim to induce harmful responses under a trigger while preserving ordinary behavior on untriggered input. Recent model-editing a...
arXiv:2609.13709v1 Announce Type: new Abstract: Human corrections identify editable spans, but the examples receiving corrections may come from a selective feedback channel. We analyze this interacti...
arXiv:2610.18462v2 Announce Type: cross Abstract: Readout scaling changes what a sparse autoencoder (SAE) learns, but the benefit of removing it depends on the data. We use readout-canonicalized deci...
arXiv:2607. 19364v2 Announce Type: replace Abstract: Activation steering adds a residual-stream direction at inference time, providing lightweight behavioral control without fine-tuning.