SemEval-2024 Task 8: Weighted Layer Averaging RoBERTa for Black-Box Machine-Generated Text Detection

TL;DR

This paper presents a method using weighted layer averaging of RoBERTa to improve detection of machine-generated text across multiple languages and domains, addressing the growing challenge posed by large language models.

Contribution

The authors introduce a novel approach of weighted layer averaging in RoBERTa for black-box machine-generated text detection, enhancing performance across multilingual and multidomain settings.

Findings

Effective in detecting machine-generated text across languages

Improves detection accuracy over baseline models

Applicable to various domains and LLM outputs

Abstract

This document contains the details of the authors' submission to the proceedings of SemEval 2024's Task 8: Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection Subtask A (monolingual) and B. Detection of machine-generated text is becoming an increasingly important task, with the advent of large language models (LLMs). In this paper, we lay out how using weighted averages of RoBERTa layers lets us capture information about text that is relevant to machine-generated text detection.