KL
Kamilė Lukošiūtė
cs.CLcs.LGcs.AIastro-ph.HEastro-ph.COastro-ph.IMgr-qcstat.ML
On Valency
published · living versionsW_63ueycek·v1 · currentpublished
Discovering Language Model Behaviors with Model-Written Evaluations
with Ethan Perez, Sam Ringer, Karina Nguyen, Edwin Chen +58
1 version
Preprints & journals
9 papers in the corpus · 2021–2025LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback2510.08604v2 · Raffaele Mura, Giorgio Piras, Kamil\.e Lukosi\=ut\.e et al.2025 · 0 citationsarXiv
Studying Large Language Model Generalization with Influence Functions2308.03296v1 · Roger Grosse, Juhan Bae, Cem Anil et al.2023 · 26 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
Prospects of Gravitational Wave Follow-up Through a Wide-field Ultra-violet Satellite: a Dorado Case Study2206.09696v1 · Bas Dorsman, Geert Raaijmakers, S. Bradley Cenko et al.2022 · 9 citationsarXiv
The Capacity for Moral Self-Correction in Large Language Models2302.07459v2 · Deep Ganguli, Amanda Askell, Nicholas Schiefer et al.2023 · 53 citationsarXiv
Discovering Language Model Behaviors with Model-Written Evaluations2212.09251v1 · Ethan Perez, Sam Ringer, Kamil\.e Lukosi\=ut\.e et al.2022 · 224 citationsarXivon Valency
KilonovaNet: Surrogate Models of Kilonova Spectra with Conditional Variational Autoencoders2204.00285v1 · Kamil\.e Lukosi\=ut\.e, Geert Raaijmakers, Zoheyr Doctor et al.2022 · 16 citationsarXiv
The Challenges Ahead for Multimessenger Analyses of Gravitational Waves and Kilonova: a Case Study on GW1904252102.11569v1 · Geert Raaijmakers, Samaya Nissanke, Francois Foucart et al.2021 · 65 citationsarXiv
Career total: 15 works. 9 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.