170 citations · 523 across the 13 of their papers we have counts for
7 papers · 1 filter
Specific versus General Principles for Constitutional AI
Sandipan Kundu, Yuntao Bai, Saurav Kadavath +33
Human feedback can prevent overtly harmful utterances in conversational models, but may not automatically mitigate subtle problematic behaviors such as a stated desire for self-pre…
Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
Ansh Radhakrishnan, Karina Nguyen, Anna Chen +21
As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior. One approach to help with this issue is to p…
The Capacity for Moral Self-Correction in Large Language Models
Deep Ganguli, Amanda Askell, Nicholas Schiefer +46
We test the hypothesis that language models trained with reinforcement learning from human feedback (RLHF) have the capability to "morally self-correct" -- to avoid producing harmf…
Pretraining Language Models with Human Preferences
Tomasz Korbak, Kejian Shi, Angelica Chen +5
Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods, offensive comments, persona…
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
Deep Ganguli, Liane Lovitt, Jackson Kernion +33
We describe our early efforts to red team language models in order to simultaneously discover, measure, and attempt to reduce their potentially harmful outputs. We make three main…
Few-shot Adaptation Works with UnpredicTable Data
Jun Shern Chan, Michael Pieler, Jonathan Jao +2
Prior work on language models (LMs) shows that training on a large number of diverse tasks improves few-shot learning (FSL) performance on new tasks. We take this to the extreme, a…