paper-with-me

홈 › Papers

ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation

2025-03-27 · Zhicheng Lee, Shulin Cao, Jinxin Liu, Jiajie Zhang, Weichuan Liu, Xiaoyin Che, Lei Hou, Juanzi Li

Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy. While recent works equip reinforcement learning (RL)-based LRMs with retrieval capabilities, they suffer from overthinking and lack robustness in reasoning, reducing their effectiveness in question answering (QA) tasks. To address this, we propose ReaRAG, a factuality-enhanced reasoning model that explores diverse queries without excessive iterations. Our solution includes a novel data construction framework with an upper bound on the reasoning chain length. Specifically, we first leverage an LRM to generate deliberate thinking, then select an action from a predefined action space (Search and Finish). For Search action, a query is executed against the RAG engine, where the result is returned as observation to guide reasoning steps later. This process iterates until a Finish action is chosen. Benefiting from ReaRAG's strong reasoning capabilities, our approach outperforms existing baselines on multi-hop QA. Further analysis highlights its strong reflective ability to recognize errors and refine its reasoning trajectory. Our study enhances LRMs' factuality while effectively integrating robust reasoning for Retrieval-Augmented Generation (RAG).

📄 PDF Abstract BibTeX arXiv:2503.21729

Code (1)

thu-keg/rearag 공식 구현 pytorch

Tasks

Question AnsweringRAGReinforcement Learning (RL)RetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BART BART is a denoising autoencoder for pretraining sequence-to-sequence models. It is trained by (1) corrupting text…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models

2025-10-27 · Xinming Wang, Jian Xu, Bin Yu, Sheng Lian 외 arxiv

Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited. We find this limitation is partially attributable to a reasoning-…

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation

2024-02-14 · Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou 외

Despite showing increasingly human-like abilities, large language models (LLMs) often struggle with factual inaccuracies, i.e. "hallucinations", even when they hold relevant knowledge. To address these hallucinations, cu…

TruthfulQA

Trustworthy Reasoning: Evaluating and Enhancing Factual Accuracy in LLM Intermediate Thought Processes

2025-07-25 · Rui Jiao, Yue Zhang, Jinku Li arxiv

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon …

Reinforcement Learning

Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies

2026-05-28 · Yuxuan Ye, Raul Santos-Rodriguez, Edwin Simpson arxiv

Grounded claim factuality checking is important for large language model (LLM) applications such as retrieval-augmented generation, as it helps users assess the correctness of generated outputs. Existing metrics using en…

Reading Comprehension

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality

2025-06-24 · Baochang Ren, Shuofei Qiao, Wenhao Yu, Huajun Chen 외

Large Language Models (LLMs), particularly slow-thinking models, often exhibit severe hallucination, outputting incorrect content due to an inability to accurately recognize knowledge boundaries during reasoning. While R…

HallucinationHallucination Evaluationreinforcement-learningReinforcement Learning+1