6 papers · 1 filter
MOSAIC: Composable Safety Alignment with Modular Control Tokens
Jingyu Peng, Hongyu Chen, Jiancheng Dong +5
Safety alignment in large language models (LLMs) is commonly implemented as a single static policy embedded in model parameters. However, real-world deployments often require conte…
NEZHA: A Zero-sacrifice and Hyperspeed Decoding Architecture for Generative Recommendations
Yejing Wang, Shengyu Zhou, Jinyu Lu +9
Generative Recommendation (GR), powered by Large Language Models (LLMs), represents a promising new paradigm for industrial recommender systems. However, their practical applicatio…
FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use
Zengzhuang Xu, Bingguang Hao, Zechuan Wang +14
Function calling (FC) empowers large language models (LLMs) and autonomous agents to interface with external tools, a critical capability for solving complex, real-world problems.…
Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning
Xiao Han, Zimo Zhao, Wanyu Wang +4
Recent advancements in Large Language Models (LLMs) have emphasized the critical role of fine-tuning (FT) techniques in adapting LLMs to specific tasks, especially when retraining…
Stepwise Reasoning Error Disruption Attack of LLMs
Jingyu Peng, Maolin Wang, Xiangyu Zhao +6
Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored. Existing attacks…
SIGMA: Selective Gated Mamba for Sequential Recommendation
Ziwei Liu, Qidong Liu, Yejing Wang +6
In various domains, Sequential Recommender Systems (SRS) have become essential due to their superior capability to discern intricate user preferences. Typically, SRS utilize transf…