JM
Jesse Mu
cs.CLcs.LGcs.AICognitive Psychologycs.CRcs.CVDevelopmental Psychologycluster analysiscs.MAcs.SE
On Valency
published · living versionsW_3sjke4et·v1 · currentpublished
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
with Evan Hubinger, Carson Denison, Mike Lambert, Meg Tong +34
1 version
Preprints & journals
20 papers in the corpus · 2017–2025Forecasting Rare Language Model Behaviors2502.16797v1 · Erik Jones, Meg Tong, Jesse Mu et al.2025 · 0 citationsarXiv
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming2501.18837v1 · Mrinank Sharma, Meg Tong, Jesse Mu et al.2025 · 7 citationsarXiv
Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach2412.02159v1 · Tony T. Wang, John Hughes, Henry Sleight et al.2024 · 0 citationsarXiv
Learning to Compress Prompts with Gist Tokens2304.08467v3 · Jesse Mu, Xiang Lisa Li, Noah Goodman2023 · 30 citationsarXiv
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training2401.05566v3 · Evan Hubinger, Carson Denison, Jesse Mu et al.2024 · 39 citationsarXivon Valency
Characterizing tradeoffs between teaching via language and demonstrations in multi-agent systems2305.11374v1 · Dhara Yu, Noah D. Goodman, Jesse Mu2023 · 0 citationsarXiv
Improving Intrinsic Exploration with Language Abstractions2202.08938v2 · Jesse Mu, Victor Zhong, Roberta Raileanu et al.2022 · 19 citationsarXiv
Improving Policy Learning via Language Dynamics Distillation2210.00066v1 · Victor Zhong, Jesse Mu, Luke Zettlemoyer et al.2022 · 5 citationsarXiv
Active Learning Helps Pretrained Models Learn the Intended Task2204.08491v1 · Alex Tamkin, Dat Nguyen, Salil Deshpande et al.2022 · 14 citationsarXiv
Parkinson's Disease Subtypes Identified from Cluster Analysis of Motor and Non-motor Symptoms.28979203 · Mu, Jesse, Chaudhuri, Kallol R, Bielza, Concha et al.2022 · 135 citationsFrontiers in aging neuroscience. 2017;9:301
Emergent Communication of Generalizations2106.02668v2 · Jesse Mu, Noah Goodman2021 · 8 citationsarXiv
Calibrate your listeners! Robust communication-based training for pragmatic speakers2110.05422v1 · Rose E. Wang, Julia White, Jesse Mu et al.2021 · 2 citationsarXiv
Multi-party referential communication in complex strategic gamestfb3d_v1 · Jess Mankewitz, Veronica Boyce, Brandon Waldon et al.2021 · 3 citationsPsyArXiv
Compositional Explanations of Neurons2006.14032v2 · Jesse Mu, Jacob Andreas2020 · 65 citationsarXiv
Shaping Visual Representations with Language for Few-shot Classification1911.02683v2 · Jesse Mu, Percy Liang, Noah Goodman2019 · 34 citationsarXiv
Learning to refer informatively by amortizing pragmatic reasoning2006.00418v1 · Julia White, Jesse Mu, Noah D. Goodman2020 · 2 citationsarXiv
Learning Outside the Box: Discourse-level Features Improve Metaphor Identification1904.02246v2 · Jesse Mu, Helen Yannakoudakis, Ekaterina Shutova2019 · 14 citationsarXiv
Robustness of the adult statistical word segmentation literature: Part 1vu8je_v1 · Joshua Hartshorne, Lauren Skorb, Sven L. Dietz et al.2017 · 5 citationsPsyArXiv
Replication of Frank, Goldwater, Griffiths, & Tenenbaum (2010): Modeling human performance in statistical word segmentation, Experiment 179bnu_v1 · Jesse Mu, James Ledoux, Joshua Hartshorne2017 · 1 citationPsyArXiv
Replication of Saffran, Newport, & Aslin (1996) Word segmentation: The role of distributional cues, Exp. 1qsyd2_v1 · Caitlin Garcia, Gina Iozzo, Katie Lamirato et al.2017 · 1 citationPsyArXiv
Career total: 33 works. 20 are in this corpus.
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.