5 papers · 1 filter
EHR-Bench: A Chinese Multi-Task Benchmark for Recruitment AI
Ruijia Yang, Bing Xu, Zulong Chen +5
Recruitment applications span diverse operations, from drafting job descriptions and interpreting queries to organizing profiles, assessing fit, and recommending candidates and job…
TRACE: Single-Pass Decoding-Trace Risk Localization for Generation Calibration
Yuebin Xu, Xuemei Peng, Junlan Chen +2
Reliable confidence estimation is essential for large language model deployment. However, answer-level calibration remains challenging because generation errors are often localized…
EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge
Chengxi Liao, Tao Xu, Zulong Chen +7
Text-to-SQL enables natural language access to databases, and recent LLMs have substantially advanced its capabilities. Existing benchmarks such as Spider, BIRD, and Spider~2.0 eva…
DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models
You-Liang Huang, Xinhao Huang, Chengxi Liao +1
Existing works on large language model (LLM) decomposition mainly focus on improving performance on downstream tasks, but they ignore the poor parallel inference performance when t…
SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression
Xinhao Huang, You-Liang Huang, Zeyi Wen
Large language models (LLMs) have demonstrated impressive capabilities across various tasks, but the billion-scale parameters pose deployment challenges. Although existing methods…