Publication

Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models

2024

Abstract

Humor is a fundamental facet of human cognition and interaction. Yet, despite recent advances in natural language processing, humor detection remains a challenging task that is complicated by the scarcity of datasets that pair humorous texts with similar non-humorous counterparts. We investigate whether large language models (LLMs) can generate synthetic data for humor detection via editing texts. We benchmark LLMs on an existing human dataset and show that current LLMs display an impressive ability to “unfun” jokes, as judged by humans and as measured on the downstream task of humor detection. We extend our approach to a code-mixed English-Hindi humor dataset where we find that GPT-4’s synthetic data is highly rated by bilingual annotators and provides challenging adversarial examples for humor classifiers.

Official source

https://infoscience.epfl.ch/entities/publication/94e4958d-c53c-4687-99ba-95666242fe75

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

2024

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/94e4958d-c53c-4687-99ba-95666242fe75

About this result

Related concepts (26)

Large language model

A large language model (LLM) is a language model characterized by its large size. Their size is enabled by AI accelerators, which are able to process vast amounts of text data, mostly scraped from the Internet. The artificial neural networks which are built can contain from tens of millions and up to billions of weights and are (pre-)trained using self-supervised learning and semi-supervised learning. Transformer architecture contributed to faster training.

Theories of humor

There are many theories of humor which attempt to explain what humor is, what social functions it serves, and what would be considered humorous. Among the prevailing types of theories that attempt to account for the existence of humor, there are psychological theories, the vast majority of which consider humor to be very healthy behavior; there are spiritual theories, which consider humor to be an inexplicable mystery, very much like a mystical experience.

Language model

A language model is a probabilistic model of a natural language that can generate probabilities of a series of words, based on text corpora in one or multiple languages it was trained on. Large language models, as their most advanced form, are a combination of feedforward neural networks and transformers. They have superseded recurrent neural network-based models, which had previously superseded the pure statistical models, such as word n-gram language model.

Related publications (17)

Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models

Chat with Graph Search

When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger

ProteomeLM: A proteome-scale language model enables accurate and rapid prediction of protein–protein interactions and gene essentiality across taxa

Sequence Modeling Architectures: Foundations [Special Issue on the Mathematics of Deep Learning]