InstructAV: Instruction Fine-tuning Large Language Models for Authorship Verification
This addresses authorship verification for NLP applications, offering improved accuracy and explainability, though it appears incremental as it builds on existing fine-tuning techniques.
The paper tackles the problem of authorship verification by introducing InstructAV, a method that fine-tunes large language models to improve accuracy and provide transparent explanations, achieving state-of-the-art performance with high classification accuracy across multiple datasets.
Large Language Models (LLMs) have demonstrated remarkable proficiency in a wide range of NLP tasks. However, when it comes to authorship verification (AV) tasks, which involve determining whether two given texts share the same authorship, even advanced models like ChatGPT exhibit notable limitations. This paper introduces a novel approach, termed InstructAV, for authorship verification. This approach utilizes LLMs in conjunction with a parameter-efficient fine-tuning (PEFT) method to simultaneously improve accuracy and explainability. The distinctiveness of InstructAV lies in its ability to align classification decisions with transparent and understandable explanations, representing a significant progression in the field of authorship verification. Through comprehensive experiments conducted across various datasets, InstructAV demonstrates its state-of-the-art performance on the AV task, offering high classification accuracy coupled with enhanced explanation reliability.