NC
Newton Cheng
cs.CLcs.AIcs.LGhep-thquant-phcs.CRcs.SEmath.MPmath-phmath.PR
On Valency
published · living versionsW_3sjke4et·v1 · currentpublished
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
with Evan Hubinger, Carson Denison, Jesse Mu, Mike Lambert +34
1 version
Preprints & journals
10 papers in the corpus · 2019–2024Random tensor networks with nontrivial links2206.10482v2 · Newton Cheng, C'ecilia Lancien, Geoff Penington et al.2022 · 27 citationsAnnales Henri Poincare, Vol. 25, No. 4 (2024) pp. 2107-2212
Towards Understanding Sycophancy in Language Models2310.13548v4 · Mrinank Sharma, Meg Tong, Tomasz Korbak et al.2023 · 132 citationsarXiv
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training2401.05566v3 · Evan Hubinger, Carson Denison, Jesse Mu et al.2024 · 39 citationsarXivon Valency
Specific versus General Principles for Constitutional AI2310.13798v1 · Sandipan Kundu, Yuntao Bai, Saurav Kadavath et al.2023 · 7 citationsarXiv
Measuring Faithfulness in Chain-of-Thought Reasoning2307.13702v1 · Tamera Lanham, Anna Chen, Ansh Radhakrishnan et al.2023 · 32 citationsarXiv
Question Decomposition Improves the Faithfulness of Model-Generated Reasoning2307.11768v2 · Ansh Radhakrishnan, Karina Nguyen, Anna Chen et al.2023 · 8 citationsarXiv
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model2211.05100v4 · BigScience Workshop: Teven Le Scao, Angela Fan, Christopher Akiki et al.2022 · 834 citationsarXiv
Topological Link Models of Multipartite Entanglement2109.01150v2 · Ning Bao, Newton Cheng, Sergio Hern'andez-Cuenca et al.2021 · 15 citationsQuantum 6, 741 (2022)
A Gap Between the Hypergraph and Stabilizer Entropy Cones2006.16292v2 · Ning Bao, Newton Cheng, Sergio Hern'andez-Cuenca et al.2020 · 12 citationsarXiv
Optimized Correlation Measures in Holography1909.09334v3 · Newton Cheng2019 · 7 citationsPhys. Rev. D 101, 066009 (2020)
Career total: 14 works. 10 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.