paper-with-me

Papers

DeepRAG: Thinking to Retrieval Step by Step for Large Language Models

2025-02-03 · Xinyan Guan, Jiali Zeng, Fandong Meng, Chunlei Xin, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Jie zhou

Large Language Models (LLMs) have shown remarkable potential in reasoning while they still suffer from severe factual hallucinations due to timeliness, accuracy, and coverage of parametric knowledge. Meanwhile, integrating reasoning with retrieval-augmented generation (RAG) remains challenging due to ineffective task decomposition and redundant retrieval, which can introduce noise and degrade response quality. In this paper, we propose DeepRAG, a framework that models retrieval-augmented reasoning as a Markov Decision Process (MDP), enabling strategic and adaptive retrieval. By iteratively decomposing queries, DeepRAG dynamically determines whether to retrieve external knowledge or rely on parametric reasoning at each step. Experiments show that DeepRAG improves retrieval efficiency while improving answer accuracy by 21.99%, demonstrating its effectiveness in optimizing retrieval-augmented reasoning.

📄 PDF Abstract BibTeX arXiv:2502.01142

Code (1)

zhaoolee/garss pytorch

Tasks

RAGRetrievalRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search

2025-02-18 · Yifan Ji, Zhipeng Xu, Zhenghao Liu, Yukun Yan 외

Recent dense retrievers usually thrive on the emergency capabilities of Large Language Models (LLMs), using them to encode queries and documents into an embedding space for retrieval. These LLM-based dense retrievers hav…

Retrieval

Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning

2025-11-12 · Wenda Wei, Yu-An Liu, Ruqing Zhang, Jiafeng Guo 외 arxiv

Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models, yet its effectiveness remains limited in complex, multi-step reasoning scenarios. Recent efforts have…

Reinforcement LearningQuestion Answering

How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMs

2026-01-07 · Su-Hyeon Kim, Hyundong Jin, Yejin Lee, Yo-Sub Han arxiv

Large Reasoning Models (LRMs) achieve remarkable success through explicit thinking steps, yet the thinking steps introduce a novel risk by potentially amplifying unsafe behaviors. Despite this vulnerability, conventional…

Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought

2025-10-28 · Jiachen Zhao, Yiyou Sun, Weiyan Shi, Dawn Song arxiv

Large language models can generate long chain-of-thought (CoT) reasoning, yet prior work suggests that CoT can be post-hoc rationalization rather than a faithful reflection of the computation through explicitly designed …

DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding

2026-05-26 · Peng Zhang, Guanghao Zhang, Wanggui He, Longxiang Zhang 외 arxiv

Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video segments during inference. However, two…

Answer Generation