一作ACL 2026Findings· Findings of ACL
Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM -Based Attribute Value Extraction
Theodore Glavas · Nikhita Vedula · Dushyanta Dhyani · Yilun Zhu · Shervin Malmasi
摘要
Some text generation tasks, such as Attribute Value Extraction (AVE), require decoding multiple independent sequences from the same document context. While standard autoregressive decoding is slow due to its sequential nature, the independence between output sequences offers an opportunity for pa...