ACL Anthology · ACL 2026:acl:2026.acl-short.51 · 记录 #1
CaBSALLM: Efficient Context-Aware Batch Annotation of Conversational Streams with Large Language Models
Mohammadsadegh AbolhasaniReza Mousavi University of Virginia, CharlottesvillePaul Jen-Hwa Hu University of Utah
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 21:44
摘要
Analyses of parasocial cues in live-stream chats require accurate, efficient, and scalable annotation. However, manual annotation is tedious, and large language models (LLMs) often make mistakes when applying subjective, discourse-dependent labels. This study proposes Context-aware Batching for Stream Annotation with LLMs (CaBSALLM), an efficient pipeline that incorporates lightweight conversational context and a novel dynamic batching method to improve throughput and scalability. Compared with state-of-the-art pipelines, this generalizable approach is significantly more time- and cost-efficient while achieving comparable or better predictive performance and agreement.