AP
Adam Pearce
cs.CLcs.LGcs.AIstat.MLartificial intelligencecs.CRcs.DCcs.HCcs.ROdeep learning
On Valency
published · living versionsW_5uruupn8·v1 · currentpublished
Auditing language models for hidden objectives
with Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey +30
1 version
Preprints & journals
13 papers in the corpus · 2019–2026Effect of [68Ga]Ga-PSMA-11 PET-CT in the diagnosis of prostate cancer in men with equivocal or clinically high-risk non-suspicious findings on multiparametric MRI (PRIMARY2): a multicentre, non-inferiority, phase 3, randomised controlled trial.42269655 · Buteau, James P, Moon, Daniel, Fahey, Michael T et al.2026 · 9 citationsThe Lancet. Oncology. 2026;27(7):839-848
Auditing language models for hidden objectives2503.10965v2 · Samuel Marks, Johannes Treutlein, Trenton Bricken et al.2025 · 4 citationsarXivon Valency
M-SET: Multi-Drone Swarm Intelligence Experimentation with Collision Avoidance Realism2406.10916v2 · Chuhao Qin, Alexander Robins, Callum Lillywhite-Roake et al.2024 · 7 citationsarXiv
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models2401.06102v4 · Asma Ghandeharioun, Avi Caciularu, Adam Pearce et al.2024 · 2 citationsarXiv
Large Scale Qualitative Evaluation of Generative Image Model Outputs2301.04518v1 · Yannick Assogba, Adam Pearce, Madison Elliott2023 · 4 citationsarXiv
Acquisition of Chess Knowledge in AlphaZero2111.09259v3 · Thomas McGrath, Andrei Kapishnikov, Nenad Tomasev et al.2021 · 103 citationsarXiv
Early social distancing policies in Europe, changes in mobility & COVID-19 case trajectories: Insights from Spring 2020.34191818 · Woskie, Liana R, Hennessy, Jonathan, Espinosa, Valeria et al.2021 · 60 citationsPloS one. 2021;16(6):e0253071
Impacts of Social Distancing Policies on Mobility and COVID-19 Case Growth in the US2004.10172v4 · Gregory A. Wellenius (1, Swapnil Vispute Valeria Espinosa, Alex Fabrikant et al.2020 · 198 citationsNat Commun 12, 3118 (2021)
An Interpretability Illusion for BERT2104.07143v1 · Tolga Bolukbasi, Adam Pearce, Ann Yuan et al.2021 · 11 citationsarXiv
Evaluation of the Use of Combined Artificial Intelligence and Pathologist Assessment to Review and Grade Prostate Biopsies.33180129 · Steiner, David F, Nagpal, Kunal, Sayres, Rory et al.2021 · 126 citationsJAMA network open. 2020;3(11):e2023267
Google COVID-19 Search Trends Symptoms Dataset: Anonymization Process Description (version 1.0)2009.01265v1 · Shailesh Bavadekar, Andrew Dai, John Davis et al.2020 · 16 citationsarXiv
Visualizing and Measuring the Geometry of BERT1906.02715v2 · Andy Coenen, Emily Reif, Ann Yuan et al.2019 · 281 citationsarXiv
Career total: 18 works. 13 are in this corpus.Showing the 12 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.