Kamilė Lukošiūtė

Discovering Language Model Behaviors with Model-Written Evaluations

Ethan Perez, Sam Ringer, Kamilė Lukošiūtė et al. · 2023 · 113 citations · Full text

Natural Language Processing, Engineering, Computational Linguistics +13

The Challenges Ahead for Multimessenger Analyses of Gravitational Waves and Kilonova: A Case Study on GW190425

G. Raaijmakers, S. Nissanke, François Foucart et al. · The Astrophysical Journal · 2021 · 59 citations · Full text

The Capacity for Moral Self-Correction in Large Language Models

Deep Ganguli, Amanda Askell, Nicholas Schiefer et al. · arXiv (Cornell University) · 2023 · 48 citations · Full text

Cognitive Science, Behavioral Decision Making, Moral Self-correction +14

Discovering Language Model Behaviors with Model-Written Evaluations

Ethan Perez, Sam Ringer, Kamilė Lukošiūtė et al. · arXiv (Cornell University) · 2022 · 39 citations · Full text

Artificial Intelligence, Llm Fine-tuning, Inverse Scaling +20

Measuring Faithfulness in Chain-of-Thought Reasoning

Tamera Lanham, Anna Chen, Ansh Radhakrishnan et al. · arXiv (Cornell University) · 2023 · 18 citations · Full text

Llm Fine-tuning, Engineering, Verification +21