Uncertainty-Aware Semantic Decoding for LLM-Based Sequential Recommendation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918132420968448 |
|---|---|
| author | Yin, Chenke Fan, Li Wang, Jia Hu, Dongxiao Zhang, Haichao Zhang, Chong Xiang, Yang |
| author_facet | Yin, Chenke Fan, Li Wang, Jia Hu, Dongxiao Zhang, Haichao Zhang, Chong Xiang, Yang |
| contents | Large language models have been widely applied to sequential recommendation tasks, yet during inference, they continue to rely on decoding strategies developed for natural language processing. This creates a mismatch between text-generation objectives and recommendation next item selection objectives. This paper addresses this limitation by proposing an Uncertainty-aware Semantic Decoding (USD) framework that combines logit-based clustering with adaptive scoring to improve next-item predictions. Our approach clusters items with similar logit vectors into semantic equivalence groups, then redistributes probability mass within these clusters and computes entropy across them to control item scoring and sampling temperature during recommendation inference. Experiments on Amazon Product datasets (six domains) gains of 18.5\% in HR@3, 11.9\% in NDCG@3, and 10.8\% in MRR@3 compared to state-of-the-art baselines. Hyperparameter analysis confirms the optimal parameters among various settings, and experiments on H\&M, and Netflix datasets indicate that the framework can adapt to differing recommendation domains. The experimental results confirm that integrating semantic clustering and uncertainty assessment yields more reliable and accurate recommendations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07210 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncertainty-Aware Semantic Decoding for LLM-Based Sequential Recommendation Yin, Chenke Fan, Li Wang, Jia Hu, Dongxiao Zhang, Haichao Zhang, Chong Xiang, Yang Information Retrieval Large language models have been widely applied to sequential recommendation tasks, yet during inference, they continue to rely on decoding strategies developed for natural language processing. This creates a mismatch between text-generation objectives and recommendation next item selection objectives. This paper addresses this limitation by proposing an Uncertainty-aware Semantic Decoding (USD) framework that combines logit-based clustering with adaptive scoring to improve next-item predictions. Our approach clusters items with similar logit vectors into semantic equivalence groups, then redistributes probability mass within these clusters and computes entropy across them to control item scoring and sampling temperature during recommendation inference. Experiments on Amazon Product datasets (six domains) gains of 18.5\% in HR@3, 11.9\% in NDCG@3, and 10.8\% in MRR@3 compared to state-of-the-art baselines. Hyperparameter analysis confirms the optimal parameters among various settings, and experiments on H\&M, and Netflix datasets indicate that the framework can adapt to differing recommendation domains. The experimental results confirm that integrating semantic clustering and uncertainty assessment yields more reliable and accurate recommendations. |
| title | Uncertainty-Aware Semantic Decoding for LLM-Based Sequential Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2508.07210 |