Language models (LMs) with less than 100B parameters are known to perform poorly on
chain-of-thought (CoT) reasoning in contrast to large LMs when solving unseen tasks. In this …

This paper reviews the state-of-the-art of language models architectures and strategies for"
complex" question-answering (QA, CQA, CPS) with a focus on hybridization. Large …

Task semantics can be expressed by a set of input-output examples or a piece of textual
instruction. Conventional machine learning approaches for natural language processing …

In the realm of large language models (LLMs), enhancing instruction-following capability
often involves curating expansive training data. This is achieved through two primary …

Language models like BERT or GPT are becoming increasingly popular measurement tools,
but are the measurements they produce valid? Literature suggests that there is still a …

Generative Large Language Models (LLMs) have become the mainstream choice for
fewshot and zeroshot learning thanks to the universality of text generation. Many users …

In recent years, few-shot and zero-shot learning, which learn to predict labels with limited
annotated instances, have garnered significant attention. Traditional approaches often treat …

While Large Language Models (LLMs) exhibit remarkable capabilities in zero-shot and few-
shot scenarios, they often require computationally prohibitive sizes. Conversely, smaller …

Task semantics can be expressed by a set of input-output examples or a piece of textual
instruction. Conventional machine learning approaches for natural language processing …

Contradiction retrieval refers to identifying and extracting documents that explicitly disagree
with or refute the content of a query, which is important to many downstream applications …