Metamorphic testing of GPT-3.5 on MovieLens shows rating-scale and prompt perturbations sharply reduce ranking similarity, suggesting LLM recommender evaluation needs new methods.
Chat-rec: Towards interactive and explainable llms-augmented recommender system,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Metamorphic Evaluation of ChatGPT as a Recommender System
Metamorphic testing of GPT-3.5 on MovieLens shows rating-scale and prompt perturbations sharply reduce ranking similarity, suggesting LLM recommender evaluation needs new methods.