Cold-Starts in Generative Recommendation: A Reproducibility Study

TL;DR

This paper systematically evaluates generative recommendation models' ability to handle cold-start scenarios using a unified protocol, highlighting the importance of reproducibility and consistent evaluation.

Contribution

It provides a reproducibility study that standardizes cold-start evaluation for generative recommenders built on pre-trained language models.

Findings

Cold-start remains a significant challenge in recommendation systems.

Existing studies often lack primary evaluation focus on cold-start.

Reproducibility and standardized protocols are crucial for fair assessment.

Abstract

Cold-start recommendation remains a central challenge in dynamic, open-world platforms, requiring models to recommend for newly registered users (user cold-start) and to recommend newly introduced items to existing users (item cold-start) under sparse or missing interaction signals. Recent generative recommenders built on pre-trained language models (PLMs) are often expected to mitigate cold-start by using item semantic information (e.g., titles and descriptions) and test-time conditioning on limited user context. However, cold-start is rarely treated as a primary evaluation setting in existing studies, and reported gains are difficult to interpret because key design choices, such as model scale, identifier design, and training strategy, are frequently changed together. In this work, we present a systematic reproducibility study of generative recommendation under a unified suite of cold-start protocols.