-
Grammaticality Judgment Task
The dataset used in the paper is a grammaticality judgment task featuring four linguistic phenomena: anaphora, center embedding, comparatives, and negative polarity constructions. -
Finetuned language models are zero-shot learners
Finetuned language models are zero-shot learners -
Llama: Open and efficient foundation language models
The LLaMA dataset is a large language model dataset used in the paper. -
Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture
Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture -
Self-Supervised Alignment with Mutual Information
The dataset is used for training a language model to follow behavioral principles without the use of preference labels, demonstrations, or human oversight. -
GPT-2 small
The dataset used in this paper is a large language model, GPT-2 small, and its residual stream activations. -
BERT: Pre-training of deep bidirectional transformers for language understanding
This paper proposes BERT, a pre-trained deep bidirectional transformer for language understanding. -
Demonstration ITerated Task Optimization (DITTO)
The dataset used in the paper is a collection of email and blog posts from 20 distinct authors, with a focus on few-shot alignment of large language models. -
Interpreting Learned Feedback Patterns in Large Language Models
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used a condensed representation of LLM activations obtained from sparse...
