14 papers
Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
Jiahui Zhou, Dan Li, Boxin Li +6
Time series is a pervasive data type across various application domains, rendering the reasonable solving of diverse time series tasks a long-standing goal. Recent advances in larg…
When More Retrieval Hurts: Retrieval-Augmented Code Review Generation
Qianru Meng, Xiao Zhang, Zhaochen Ren +1
Code review generation can reduce developer effort by producing concise, reviewer-style feedback for a given code snippet or code change. However, generation-only models often prod…
Federated Reasoning Distillation Framework with Model Learnability-Aware Data Allocation
Wei Guo, Siyuan Lu, Xiangdong Ran +8
Data allocation plays a critical role in federated large language model (LLM) and small language models (SLMs) reasoning collaboration. Nevertheless, existing data allocation metho…
Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data
Jiapeng Wang, Yiwen Hu, Yanzipeng Gao +7
As access to high-quality, domain-specific data grows increasingly scarce, multi-epoch training has become a practical strategy for adapting large language models (LLMs). However,…
VALUE: Value-Aware Large Language Model for Query Rewriting via Weighted Trie in Sponsored Search
Xiao Zhang, Guanyu Chen, Boyang Zuo +4
Query-to-bidword(i.e., bidding keyword) rewriting is fundamental to sponsored search, transforming noisy user queries into semantically relevant and commercially valuable keywords.…
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
Advik Raj Basani, Xiao Zhang
LLMs have shown impressive capabilities across various natural language processing tasks, yet remain vulnerable to input prompts, known as jailbreak attacks, carefully designed to…