Lune

ACL Findings2026

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 reasoningoriented models such as OpenAI O1 and DeepSeek R1. Inspired by these advancements, we propose the O1 Embedder, a novel approach aiming to endow retrieval models with similar capabilities to address challenges like multi-task retrieval, zero-shot retrieval, and tasks requiring intensive reasoning of complex relationships. The O1 Embedder generates preliminary thoughts for input queries before document retrieval. To realize this objective, we address two fundamental challenges in integrating thinking mechanisms into dense retrieval. First, retrieval tasks lack explicit supervision for intermediate thinking processes, making it difficult to define thoughts that are truly useful for retrieval. We address this challenge with a data synthesis framework following an Exploration-Refinement process, ensuring alignment with retrieval utility. Second, effectively integrating thought generation with representation learning requires a unified modeling framework that can jointly support generation and embedding within a single model. O1 Embedder addresses this challenge by jointly optimizing thought generation and dense retrieval in an end-to-end manner, enhancing retrieval accuracy while reducing complexity through a single deployable model. Extensive evaluations across diverse datasets demonstrate significant performance improvements, highlighting the effectiveness and generalization capability of O1 Embedder.

问 Lune

几分钟读透这篇 Paper,不用再花一下午。

Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。

可以从这些问题问起

Lune 可以查阅

全文 · 相关的 Paper

获取答案

免费开始,无需绑卡

脉络

  • Precise Zero-Shot Dense Retrieval without Relevance Labels 引用了 Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
  • Precise Zero-Shot Dense Retrieval without Relevance Labels 引用了 Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling
  • Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling 引用了 Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
它引用的引用它的从左到右按年份排列,引用越多,位置越高。

它引用的 Paper29

  1. Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran 等NeurIPS 2023 · 5,068 次引用
  2. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalLee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang 等ICLR 2021 · 1,547 次引用
  3. Towards Revealing the Mystery behind Chain of Thought: A Theoretical PerspectiveGuhao Feng, Bohang Zhang, Yuntian Gu, Haotian Ye 等NeurIPS 2023 · 470 次引用
  4. Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware SamplingSebastian Hofstätter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin 等SIGIR 2021 · 297 次引用
  5. Precise Zero-Shot Dense Retrieval without Relevance LabelsLuyu Gao, Xueguang Ma, Jimmy Lin, Jamie CallanACL 2023 · 211 次引用

相关 Paper

  1. LeTS: Learning to Think-and-Search via Process-and-Outcome Reward HybridizationQi Zhang, Shouqing Yang, Lirong Gao, Hao Chen 等EMNLP 2025
  2. ReSearch: Learning to Reason with Search for LLMs via Reinforcement LearningMingyang Chen, Linzhuang Sun, Tianpeng Li, Haoze Sun 等NeurIPS 2025 · 125 次引用
  3. Search-o1: Agentic Search-Enhanced Large Reasoning ModelsXiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang 等EMNLP 2025 · 12 次引用
  4. Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and BeyondYinghao Hu, Yaoyao Yu, Leilei Gan, Bin Wei 等EMNLP Findings 2025 · 1 次引用
  5. WebThinker: Empowering Large Reasoning Models with Deep Research CapabilityXiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian 等NeurIPS 2025 · 354 次引用
黄昏的海面,两侧是细线勾勒的悬崖