Metamorphic Evaluation of ChatGPT as a Recommender System

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Khirbat, Madhurima, Ren, Yongli, Castells, Pablo, Sanderson, Mark
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913580338642944
author Khirbat, Madhurima
Ren, Yongli
Castells, Pablo
Sanderson, Mark
author_facet Khirbat, Madhurima
Ren, Yongli
Castells, Pablo
Sanderson, Mark
contents With the rise of Large Language Models (LLMs) such as ChatGPT, researchers have been working on how to utilize the LLMs for better recommendations. However, although LLMs exhibit black-box and probabilistic characteristics (meaning their internal working is not visible), the evaluation framework used for assessing these LLM-based recommender systems (RS) are the same as those used for traditional recommender systems. To address this gap, we introduce the metamorphic testing for the evaluation of GPT-based RS. This testing technique involves defining of metamorphic relations (MRs) between the inputs and checking if the relationship has been satisfied in the outputs. Specifically, we examined the MRs from both RS and LLMs perspectives, including rating multiplication/shifting in RS and adding spaces/randomness in the LLMs prompt via prompt perturbation. Similarity metrics (e.g. Kendall tau and Ranking Biased Overlap(RBO)) are deployed to measure whether the relationship has been satisfied in the outputs of MRs. The experiment results on MovieLens dataset with GPT3.5 show that lower similarity are obtained in terms of Kendall $τ$ and RBO, which concludes that there is a need of a comprehensive evaluation of the LLM-based RS in addition to the existing evaluation metrics used for traditional recommender systems.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12121
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Metamorphic Evaluation of ChatGPT as a Recommender System
Khirbat, Madhurima
Ren, Yongli
Castells, Pablo
Sanderson, Mark
Information Retrieval
With the rise of Large Language Models (LLMs) such as ChatGPT, researchers have been working on how to utilize the LLMs for better recommendations. However, although LLMs exhibit black-box and probabilistic characteristics (meaning their internal working is not visible), the evaluation framework used for assessing these LLM-based recommender systems (RS) are the same as those used for traditional recommender systems. To address this gap, we introduce the metamorphic testing for the evaluation of GPT-based RS. This testing technique involves defining of metamorphic relations (MRs) between the inputs and checking if the relationship has been satisfied in the outputs. Specifically, we examined the MRs from both RS and LLMs perspectives, including rating multiplication/shifting in RS and adding spaces/randomness in the LLMs prompt via prompt perturbation. Similarity metrics (e.g. Kendall tau and Ranking Biased Overlap(RBO)) are deployed to measure whether the relationship has been satisfied in the outputs of MRs. The experiment results on MovieLens dataset with GPT3.5 show that lower similarity are obtained in terms of Kendall $τ$ and RBO, which concludes that there is a need of a comprehensive evaluation of the LLM-based RS in addition to the existing evaluation metrics used for traditional recommender systems.
title Metamorphic Evaluation of ChatGPT as a Recommender System
topic Information Retrieval
url https://arxiv.org/abs/2411.12121