Whose LLM is It Anyway? Linguistic Comparison and LLM Attribution for GPT-3.5, GPT-4 and Bard

arXiv (Cornell University)（2024）

Bar Ilan University Department of Information Science | University College London Department of Cancer Biology

Cited 0|Views18

Abstract

Large Language Models (LLMs) are capable of generating text that is similarto or surpasses human quality. However, it is unclear whether LLMs tend toexhibit distinctive linguistic styles akin to how human authors do. Through acomprehensive linguistic analysis, we compare the vocabulary, Part-Of-Speech(POS) distribution, dependency distribution, and sentiment of texts generatedby three of the most popular LLMS today (GPT-3.5, GPT-4, and Bard) to diverseinputs. The results point to significant linguistic variations which, in turn,enable us to attribute a given text to its LLM origin with a favorable 88%accuracy using a simple off-the-shelf classification model. Theoretical andpractical implications of this intriguing finding are discussed.

Translated text

Key words

Language Modeling,Semantic Similarity,Topic Modeling,Part-of-Speech Tagging,Machine Translation

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Try using models to generate summary,it takes about 60s

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper