Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs
Qian Zhu, Xinnan Guo, Jingjing Huo +5
Adapting Large Language Models (LLMs) to high-stakes vertical domains like insurance presents a significant challenge: scenarios demand strict adherence to complex regulations and…
cs.CL2026
Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction
Yuchun Zou, Junhong Tong, Jun Li
Traditional lossless text compression preserves every byte, but its gains on natural language are often modest in realistic operating regimes. We study \emph{lossy semantic text co…
cs.CL2025
LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model
Wei Shao, Lingchao Zheng, Pengyu Wang +3
Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimi…