相关论文: Know Your Audience: The benefits and pitfalls of g…

The Plain Writing Act in the United States requires government documents to be accessible in clear and simple language that the general public can easily understand, yet existing summarization systems struggle to address diverse linguistic…

Large language models (LLMs) have become the secret ingredient driving numerous industrial applications, showcasing their remarkable versatility across a diverse spectrum of tasks. From natural language processing and sentiment analysis to…

In the field of Artificial (General) Intelligence (AI), the several recent advancements in Natural language processing (NLP) activities relying on Large Language Models (LLMs) have come to encourage the adoption of LLMs as scientific models…

In this paper, we propose Latent Relation Language Models (LRLMs), a class of language models that parameterizes the joint distribution over the words in a document and the entities that occur therein via knowledge graph relations. This…

Cognitive diversity, reflected in variations of language, perspective, and reasoning, is essential to creativity and collective intelligence. This diversity is rich and grounded in culture, history, and individual experience. Yet as large…

To process novel sentences, language models (LMs) must generalize compositionally -- combine familiar elements in new ways. What aspects of a model's structure promote compositional generalization? Focusing on transformers, we test the…

Fine-tuning large language models (LLMs) with limited data poses a practical challenge in low-resource languages, specialized domains, and constrained deployment settings. While pre-trained LLMs provide strong foundations, effective…

Despite the success of large pre-trained language models (LMs) such as Codex, they show below-par performance on the larger and more complicated programming related questions. We show that LMs benefit from the summarized version of…

This study evaluates the ability of Large Language Model (LLM)-based Subpopulation Representative Models (SRMs) to generalize from empirical data, utilizing in-context learning with data from the 2016 and 2020 American National Election…

Numerous powerful large language models (LLMs) are now available for use as writing support tools, idea generators, and beyond. Although these LLMs are marketed as helpful creative assistants, several works have shown that using an LLM as a…

While large language models (LLMs) have shown remarkable capabilities to generate coherent text, they suffer from the issue of hallucinations -- factually inaccurate statements. Among numerous approaches to tackle hallucinations, especially…

Contacting customer service via chat is a common practice. Because employing customer service agents is expensive, many companies are turning to NLP that assists human agents by auto-generating responses that can be used directly or with…

Using Large Language Models (LLMs) to simulate user opinions has received growing attention. Yet LLMs, especially trained with reinforcement learning from human feedback (RLHF), are known to exhibit biases toward dominant viewpoints,…

Clinical notes are an efficient way to record patient information but are notoriously hard to decipher for non-experts. Automatically simplifying medical text can empower patients with valuable information about their health, while saving…

Language models (LMs) are trained on collections of documents, written by individual human agents to achieve specific goals in an outside world. During training, LMs have access only to text of these documents, with no direct evidence of…

Has the style of scientific communication changed due to the growing use of large language models in the writing process? We address this question in the domain of Natural Language Processing by leveraging two data resources we create: a…

Inspired by evidence that pretrained language models (LMs) encode commonsense knowledge, recent work has applied LMs to automatically populate commonsense knowledge graphs (CKGs). However, there is a lack of understanding on their…

Reasoning about code and explaining its purpose are fundamental skills for computer scientists. There has been extensive research in the field of computing education on the relationship between a student's ability to explain code and other…

Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples…

Scientific breakthroughs typically emerge through the surprising violation of established research ideas, yet quantifying surprise has remained elusive because it requires a coherent model of all contemporary scientific worldviews. Deep…