5 papers
TAAL: Mitigating Early Beam Pruning in Generative Recommendation via Temporal Autoregressive Alignment
Lianjie Li, Zhiying Tu, Dianhui Chu +1
Generative recommendation encodes items as hierarchical semantic identifiers (SIDs) and retrieves the next item through autoregressive decoding. Standard next-token prediction, how…
GARDRec: Decision-Level Graph Grounding for Large Language Model Recommendation
Yong Wang, Hongliang Sun, Jinlan Liu +4
Large language models (LLMs) offer new opportunities for recommendation by interpreting item descriptions, user instructions, and external knowledge through natural-language prompt…
Dual-Path LLM Reasoning for Multimodal Few-Shot Knowledge Graph Completion
Jinlan Liu, Zhiying Tu, Yongchao Xing +5
Knowledge graph completion (KGC) aims to infer missing facts in knowledge graphs (KGs), thereby improving their completeness and supporting downstream intelligent applications. How…
SkillWiki: A Living Knowledge Infrastructure for Agent Skills
Dingcheng Huang, Yuda Ding, Bingshuo Liu +8
While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an infrastructure for large-scale production, governance, and evolution. SkillWiki…
Plug-and-Play Performance Estimation for LLM Services without Relying on Labeled Data
Can Wang, Dianbo Sui, Hongliang Sun +3
Large Language Model (LLM) services exhibit impressive capability on unlearned tasks leveraging only a few examples by in-context learning (ICL). However, the success of ICL varies…