Background: Few-shot learning (FSL) is a class of machine learning methods that require
small numbers of labeled instances for training. With many medical topics having limited …

When answering a question, humans utilize the information available across different
modalities to synthesize a consistent and complete chain of thought (CoT). This process is …

How well can NLP models generalize to a variety of unseen tasks when provided with task
instructions? To address this question, we first introduce Super-NaturalInstructions, a …

Code-generating large language models map natural language to code. However, only a
small portion of the infinite space of naturalistic utterances is effective at guiding code …

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 …

Logical reasoning is fundamental for humans yet presents a substantial challenge in the
domain of Artificial Intelligence. Initially, researchers used Knowledge Representation and …

As large language models (LLMs) continue to advance, accurately and comprehensively
evaluating their performance becomes increasingly challenging. Conventionally, human …

Training and evaluating language models increasingly requires the construction of meta-
datasets--diverse collections of curated data with clear provenance. Natural language …

Molecule property prediction has gained significant attention in recent years. The main
bottleneck is the label insufficiency caused by expensive lab experiments. In order to …

Large Language Models (LLMs) have substantially driven scientific progress in various
domains, and many papers have demonstrated their ability to tackle complex problems with …