3 papers
cs.CL2026
EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL
Huawei Zheng, Sen Yang, Zhaorui Yang +12
Schema linking is a difficult and important step in large-scale Text-to-SQL, where systems must identify a compact yet sufficient schema context from large and ambiguous databases.…
cs.LG2025
SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification
Zhendong Tan, Xingjun Zhang, Chaoyi Hu +2
Growing demands from tasks like code generation, deep reasoning, and long-document understanding have made long-context generation a crucial capability for large language models (L…
cs.CL2025
Adaptive Rectification Sampling for Test-Time Compute Scaling
Zhendong Tan, Xingjun Zhang, Chaoyi Hu +2
The newly released OpenAI-o1 and DeepSeek-R1 have demonstrated that test-time scaling can significantly improve model performance, especially in complex tasks such as logical reaso…