Work

Can Large Language Models Identify Authorship?

Year: 2024

Type: conference-paper

Abstract: The ability to accurately identify authorship is crucial for verifying content authenticity and mitigating misinformation.Large Language Models (LLMs) have demonstrated an exceptional capacity for reasoning and problemsolving.However, their potential in authorship analysis remains under-explored.Traditional studies have depended on hand-crafted stylistic features, whereas state-of-the-art approaches leverage text embeddings from pre-trained language models.These methods, which typically require fine-tuning on labeled data, often suffer from performance degradation in cross-domain applications and provide limited explainability.This work seeks to address three research questions: (1) Can LLMs perform zero-shot, end-toend authorship verification effectively?(2) Are LLMs capable of accurately attributing authorship among multiple candidates authors (e.g., 10 and 20)? (3) Can LLMs provide explainability in authorship analysis, particularly through the role of linguistic features?Moreover, we investigate the integration of explicit linguistic features to guide LLMs in their reasoning processes.Our assessment demonstrates LLMs' proficiency in both tasks without the need for domain-specific fine-tuning, providing explanations into their decision making via a detailed analysis of linguistic features.This establishes a new benchmark for future research on LLMbased authorship analysis 1 .

Source: Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

DOI: 10.18653/v1/2024.findings-emnlp.26

Authors: Baixiang Huang, Canyu Chen, Kai Shu

Institutions: Illinois Institute of Technology, Emory University

Language: English

Topic: Authorship Attribution and Profiling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, U.S. Department of Homeland Security, Cisco Systems

Awards: NSF POSE: Phase II: OpenAD: An Integrated Open-Source Ecosystem for Anomaly Detection, Collaborative Research: SaTC: CORE: Small: Targeting Challenges in Computational Disinformation Research to Enhance Attribution, Detection, and Explanation, G3997495584, CAREER: Towards Fairness in the Real World under Generalization, Privacy and Robustness Challenges