Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–4 of 4 results for author: Pepper, K

Searching in archive cs. Search in all archives.
.
  1. arXiv:2607.08077  [pdf, ps, other

    cs.LG

    Modular Pretraining Enables Access Control

    Authors: Ethan Roland, Murat Cubuktepe, Erick Martinez, Stijn Servaes, Keenan Pepper, Mike Vaiana, Diogo Schwerz de Lucena, Judd Rosenblatt, Addie Foote, Cem Anil, Alex Cloud

    Abstract: AI developers face a dual-use dilemma. An AI capability that helps one user cure a disease can help another synthesize one. This dilemma could be resolved with access control, limiting dual-use AI capabilities to trusted deployments with a legitimate need. A gold standard for access control would be to serve separate models with different capabilities to different users. However, training and depl… ▽ More

    Submitted 8 July, 2026; originally announced July 2026.

  2. arXiv:2602.10352  [pdf, ps, other

    cs.CL cs.AI cs.LG

    Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs

    Authors: Keenan Pepper, Alex McKenzie, Florin Pop, Stijn Servaes, Martin Leitgab, Mike Vaiana, Judd Rosenblatt, Michael S. A. Graziano, Diogo de Lucena

    Abstract: Self-interpretation methods prompt language models to describe their own internal states, but remain unreliable due to hyperparameter sensitivity. We show that training lightweight adapters on interpretability artifacts, while keeping the LM entirely frozen, yields reliable self-interpretation across tasks and model families. A scalar affine adapter with just $d_\text{model}+1$ parameters suffices… ▽ More

    Submitted 2 June, 2026; v1 submitted 10 February, 2026; originally announced February 2026.

    Comments: 26 pages, 18 tables, 17 figures. Code and data at https://github.com/agencyenterprise/selfie-adapters

  3. arXiv:2602.06941  [pdf, ps, other

    cs.LG cs.AI cs.CL

    Endogenous Resistance to Activation Steering in Language Models

    Authors: Alex McKenzie, Keenan Pepper, Stijn Servaes, Martin Leitgab, Murat Cubuktepe, Mike Vaiana, Diogo de Lucena, Judd Rosenblatt, Michael S. A. Graziano

    Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.g., ``wait, that's not right'') and continuing on-topic even while the steering perturbation remains active. We term this Endogenous Steering Resistance (ESR). Using sparse autoencoder (SAE) latents to steer model activations, we find that Llama-3.3-70B exhibits explicit… ▽ More

    Submitted 5 July, 2026; v1 submitted 6 February, 2026; originally announced February 2026.

  4. arXiv:2505.00509  [pdf, ps, other

    cs.LG

    Self-Ablating Transformers: More Interpretability, Less Sparsity

    Authors: Jeremias Ferrao, Luhan Mikaelson, Keenan Pepper, Natalia Perez-Campanero Antolin

    Abstract: A growing intuition in machine learning suggests a link between sparsity and interpretability. We introduce a novel self-ablation mechanism to investigate this connection ante-hoc in the context of language transformers. Our approach dynamically enforces a k-winner-takes-all constraint, forcing the model to demonstrate selective activation across neuron and attention units. Unlike post-hoc methods… ▽ More

    Submitted 1 May, 2025; originally announced May 2025.

    Comments: Poster Presentation at Building Trust Workshop at ICLR 2025