Search Results for author:
Found 8 papers, 4 papers with code
Specific versus General Principles for Constitutional AI
Constitutional AI offers an alternative, replacing human feedback with feedback from AI models conditioned only on a list of written principles.
Towards Understanding Sycophancy in Language Models
Overall, our results indicate that sycophancy is a general behavior of state-of-the-art AI assistants, likely driven in part by human preference judgments favoring sycophantic responses.
Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior.
Measuring Faithfulness in Chain-of-Thought Reasoning
Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasoning is a faithful explanation of the model's actual reasoning (i. e., its process for answering the question).
The Capacity for Moral Self-Correction in Large Language Models
We believe that at this level of scale, language models obtain two capabilities that they can use for moral self-correction: (1) they can follow instructions and (2) they can learn complex normative concepts of harm like stereotyping, bias, and discrimination.
Discovering Language Model Behaviors with Model-Written Evaluations
We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse.
A Data-Centric Optimization Framework for Machine Learning
Rapid progress in deep learning is leading to a diverse set of quickly changing models, with a dramatically growing demand for compute.
Towards Automated Anamnesis Summarization: BERT-based Models for Symptom Extraction
Professionals in modern healthcare systems are increasingly burdened by documentation workloads.
