-
Core Dative PRIME-LM Corpus
The dataset used in the paper to study the inverse frequency effect (IFE) in structural priming. -
Context versus Prior Knowledge in Language Models
The dataset used in the paper to test the persuasion and susceptibility scores of language models. -
Anthropic Helpfulness Base eval
The dataset used in the paper is the Anthropic Helpfulness Base eval dataset. -
Anthropic Helpfulness Base
The dataset used in the paper is the Anthropic Helpfulness Base train dataset and the Anthropic Helpfulness eval dataset. -
OpenAssistant dataset
The dataset used for the experiments in the paper, consisting of 1000 benign instruction examples. -
AdvBench dataset
The dataset used for the experiments in the paper, consisting of 60 harmful instructions from the AdvBench dataset. -
CALaMo: a Constructionist Assessment of Language Models
The authors used the CHILDES corpus to train a character-based LSTM model and evaluated its performance on a set of tasks. -
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 -
Edit Distance Robust Watermarks for Language Models
The dataset used in the paper is a language model output, which is a sequence of tokens generated by a language model. -
SafeDecoding dataset
The dataset used in the SafeDecoding paper, which contains 32 harmful queries spanning 16 harmful categories. -
Enhancing chat language models by scaling high-quality instructional conversa...
Enhancing chat language models by scaling high-quality instructional conversations. -
Llama: Open and efficient foundation language models
The LLaMA dataset is a large language model dataset used in the paper. -
Fine-tuning Language Models with Advantage-Induced Policy Alignment
The dataset used in the paper is the Anthropic Helpfulness and Harmlessness dataset and the StackExchange dataset. -
Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture
Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture