6 papers
DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces
Boyan Li, Zhuowen Liang, Yupeng Xie +11
Data agents enable natural-language analytics over organizational workspaces, where relevant evidence may be scattered across databases, structured files, long documents, and multi…
TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins
Yuxiang Luo, Haonan Long, Chen Wang +6
Fine-tuning large language models (LLMs) is compute-intensive and error-prone: model performance depends sensitively on data quality and hyperparameter choices, and naïve runs can…
Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
Zhuowen Liang, Xiaotian Lin, Zhengxuan Zhang +3
Large language models (LLMs) are widely applied to data analytics over documents, yet direct reasoning over long, noisy documents remains brittle and error-prone. Hence, we study d…
A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
Yizhang Zhu, Liangwei Wang, Chenyu Yang +22
The rapid advancement of large language models (LLMs) has spurred the emergence of data agents, autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex…
Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting
Yifan Wu, Jingze Shi, Bingheng Wu +4
Existing chain-of-thought (CoT) distillation methods can effectively transfer reasoning abilities to base models but suffer from two major limitations: excessive verbosity of reaso…
LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning
Xiaotian Lin, Yanlin Qi, Yizhang Zhu +4
Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data sel…