Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2602.04225 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915773133357056 |
|---|---|
| author | Zhang, Yinan Chen, Zhixi Jing, Jiazheng Shen, Zhiqi |
| author_facet | Zhang, Yinan Chen, Zhixi Jing, Jiazheng Shen, Zhiqi |
| contents | Large Language Models (LLMs) have been widely applied across multiple domains for their broad knowledge and strong reasoning capabilities. However, applying them to recommendation systems is challenging since it is hard for LLMs to extract user preferences from large, sparse user-item logs, and real-time per-user ranking over the full catalog is too time-consuming to be practical. Moreover, many existing recommender systems focus solely on ranking items while overlooking explanations, which could help improve predictive accuracy and make recommendations more convincing to users. Inspired by recent works that achieve strong recommendation performance by forecasting near-term item popularity, we propose TRAIL (TRend and explAnation Integrated Learner). TRAIL is a fine-tuned LLM that jointly predicts short-term item popularity and generates faithful natural-language explanations. It employs contrastive learning with positive and negative pairs to align its scores and explanations with structured trend signals, yielding accurate and explainable popularity predictions. Extensive experiments show that TRAIL outperforms strong baselines and produces coherent, well-grounded explanations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04225 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Following the TRAIL: Predicting and Explaining Tomorrow's Hits with a Fine-Tuned LLM Zhang, Yinan Chen, Zhixi Jing, Jiazheng Shen, Zhiqi Information Retrieval Large Language Models (LLMs) have been widely applied across multiple domains for their broad knowledge and strong reasoning capabilities. However, applying them to recommendation systems is challenging since it is hard for LLMs to extract user preferences from large, sparse user-item logs, and real-time per-user ranking over the full catalog is too time-consuming to be practical. Moreover, many existing recommender systems focus solely on ranking items while overlooking explanations, which could help improve predictive accuracy and make recommendations more convincing to users. Inspired by recent works that achieve strong recommendation performance by forecasting near-term item popularity, we propose TRAIL (TRend and explAnation Integrated Learner). TRAIL is a fine-tuned LLM that jointly predicts short-term item popularity and generates faithful natural-language explanations. It employs contrastive learning with positive and negative pairs to align its scores and explanations with structured trend signals, yielding accurate and explainable popularity predictions. Extensive experiments show that TRAIL outperforms strong baselines and produces coherent, well-grounded explanations. |
| title | Following the TRAIL: Predicting and Explaining Tomorrow's Hits with a Fine-Tuned LLM |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2602.04225 |