Language models (LMs) often struggle to pay enough attention to the input context, and
generate texts that are unfaithful or contain hallucinations. To mitigate this issue, we present …

In spite of the potential for ground-breaking achievements offered by large language models
(LLMs)(eg, GPT-3), they still lag significantly behind fully-supervised baselines (eg, fine …

The strong few-shot in-context learning capability of large pre-trained language models
(PLMs) such as GPT-3 is highly appealing for application domains such as biomedicine …

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on
learned prompt vectors, has emerged as a promising approach for efficiently adapting large …

Why do large language models sometimes output factual inaccuracies and exhibit
erroneous reasoning? The brittleness of these models, particularly when executing long …

Highly effective, task-specific prompts are often heavily engineered by experts to integrate
detailed instructions and domain insights based on a deep understanding of both instincts of …

Autoregressive large language models (LLMs) compress knowledge from their training data
through next-token conditional distributions. This limits tractable querying of this knowledge …

Machine-Generated Text (MGT) detection, a task that discriminates MGT from Human-
Written Text (HWT), plays a crucial role in preventing misuse of text generative models …

Classifier-Free Guidance (CFG) has recently emerged in text-to-image generation as a
lightweight technique to encourage prompt-adherence in generations. In this work, we …

Abstract Machine-Generated Text (MGT) detection, a task that discriminates MGT from
Human-Written Text (HWT), plays a crucial role in preventing misuse of text generative …