activity
20242026
collaborators
Showing cs.CLShow all

9 papers · 1 filter

cs.CL2026

Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers

Xin Gao, Xingming Xu

Transformer architectures form the foundation of modern natural language processing, yet the Key-Value (KV) cache introduces substantial memory and bandwidth overhead during long-c…

cs.CL2025

Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets

Xin Gao, Xiaoyang Wang, Yun Zhu +3

The construction of Supervised Fine-Tuning (SFT) datasets is a critical yet under-theorized stage in the post-training of Large Language Models (LLMs), as prevalent practices often…

cs.CL2025

Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning

Zinan Tang, Xin Gao, Qizhi Pei +5

Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to impr…

cs.CL2025

Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs

Xin Gao, Ruiyi Zhang, Daniel Du +3

Large Language Models (LLMs) are widely used for temporal prediction, but their reliance on pretraining data raises contamination concerns, as accurate predictions on pre-cutoff te…

cs.CL2025

Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning

Honglin Lin, Qizhi Pei, Xin Gao +5

Reasoning capability is pivotal for Large Language Models (LLMs) to solve complex tasks, yet achieving reliable and scalable reasoning remains challenging. While Chain-of-Thought (…

cs.CL2025

MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion

Qizhi Pei, Lijun Wu, Zhuoshi Pan +6

Large Language Models (LLMs) have shown impressive progress in mathematical reasoning. While data augmentation is promising to enhance mathematical problem-solving ability, current…