arXiv AI
Jun 30
A Gravitational Interpretation of Fine-Tuning Reversion
arXiv:2606. 28525v1 Announce Type: cross Abstract: Fine-tuning on harmless data can partially undo behaviors acquired earlier in training.
Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal
The paper investigates whether fine‑tuning a language model erases previously embedded activation steering interventions that suppress refusals and encourage brevity. Across five instruction‑tuned models (3B–14B) subjected to non‑adversarial supervised fine‑tuning (SFT) and reinforcement learning from human feedback (RLHF), the authors find that the steering’s behavioural effect degrades when the fine‑tuning objective conflicts with the targeted behaviour, yet the underlying weight edits remain largely unchanged. Mechanistically, the steering vectors survive with minimal alteration, but functionally the steering is vulnerable and must be re‑validated after downstream training.
Related stories
arXiv Machine Learning
Jul 15
Inference-Time Machine Unlearning via Gated Activation Redirection
arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.
arXiv Machine Learning
Jun 19
Leverage Is Not Reach: A Control-Window Law for Single-Neuron Steering in Language Models
arXiv:2606. 19831v1 Announce Type: cross Abstract: Aligned language models gate behaviors such as refusal and language routing through sparse feed forward neurons, yet no theory predicts when a single neuron intervention controls a behavior coherently rather than collapsing the output.
arXiv AI
Aug 10
Divergent Response Modes in Frontier Language Models Under Steering Pressure
arXiv:2608. 06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines.
arXiv Machine Learning
Aug 11
Early Data Exposure Improves Robustness to Subsequent Fine-Tuning
arXiv:2605. 12705v2 Announce Type: replace Abstract: How can we train models whose post-trained capabilities survive subsequent fine-tuning?
arXiv AI
3d ago
Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities
arXiv:2608.29458v1 Announce Type: cross Abstract: Sandbagging, in which a model deliberately underperforms on an evaluation despite retaining the underlying capability, threatens the safety evaluatio...
arXiv AI
Jun 9
Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects
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 AI
Jul 29
Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
arXiv AI
Jun 8
Endogenous Resistance to Activation Steering in Language Models
arXiv:2602. 06941v2 Announce Type: replace-cross Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.
arXiv Machine Learning
Jun 11
When is Your LLM Steerable?
arXiv:2606. 11599v1 Announce Type: cross Abstract: Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration.
arXiv AI
Jun 9
Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation
arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).
arXiv AI
Jul 29
Where Steering Signals Come From: Activation Source Selection in Activation Steering
arXiv:2607. 25270v1 Announce Type: cross Abstract: Activation steering controls language models by adding vectors or features to hidden states at inference time, but the upstream source of these steering signals is often treated as a secondary detail.