作者位次 #2/7ACL 2026Findings· Findings of ACL
Let Retrievers Think Before Action: Thought-Augmented Embedding for Dense Retrieval
Ruiran Yan · Wen Xiong · Ze Liu · Chaozhuo Li · Hao Liao · Defu Lian · Zheng Liu
摘要
Large language models (LLMs) have demonstrated that explicitly performing step-by-step thinking before producing final outputs can substantially improve performance on complex tasks, as exemplified by recent reasoning-oriented models such as OpenAI O1 and DeepSeek R1. Inspired by these advancemen...