From the 10 of 385 papers with an AI index.
53 citations
- University of Science and Technology of ChinaCN114 papers
- Peking UniversityCN112 papers
- Tsinghua UniversityCN110 papers
- Carnegie Mellon UniversityUS101 papers
- South China Normal UniversityCN98 papers
- Institute of Modern PhysicsCN97 papers
- University of TarapacáCL97 papers
- University of TurinIT97 papers
- Beihang UniversityCN96 papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di FrascatiIT96 papers
- Nanjing Normal UniversityCN96 papers
- National Centre for Nuclear ResearchPL96 papers
5 papers · 1 filter
IMFuse: Instance-Aware Multi-Layer Fusion for LLM-Enhanced Sequential Recommendation
Yuheng Zheng, Yu Cui, Bin Wu +4
The paper introduces IMFuse, a method that adaptively combines representations from multiple layers of large language models to improve sequential recommendation, using instance-aw…
Sharpness-aware Model Merging with Salience Recovery for LLM-based Cross-Domain Sequential Recommendation
Huwei Ji, Jiajie Su, Yuyuan Li +2
The paper introduces SharpRec, a method that merges large language models for cross-domain sequential recommendation by using sharpness-aware geometric alignment and preference sal…
The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders
Weiqin Yang, Yue Pan, Chongming Gao +4
We identify a critical pitfall in scaling transformer-based sequential recommenders: while increasing model size improves recommendation accuracy, it simultaneously amplifies popul…
DeGRe: Dense-supervised Generative Reranking for Recommendation
Chaotian Song, Jingyao Zhang, Chenghao Chen +6
In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequenc…
BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models
Weiqin Yang, Bohao Wang, Zhenxiang Xu +5
Recent years have seen a rapid surge in research leveraging Large Language Models (LLMs) for recommendation. These methods typically employ supervised fine-tuning (SFT) to adapt LL…