一作ACL 2026Findings· Findings of ACL
L ive L ong B ench: Tackling Long-Context Understanding for Spoken Texts from Live Streams
Yongxuan Wu · Runyu Chen · Peiyu Liu · Hongjin Qian
摘要
Long-context understanding poses significant challenges in natural language processing, particularly for real-world dialogues characterized by high redundancy and uneven information density. Although large language models (LLMs) achieve impressive results on existing benchmarks, these datasets fa...