paper-with-me

Papers

KunLunBaizeRAG: Reinforcement Learning Driven Inference Performance Leap for Large Language Models

2025-06-24 · Cheng Li, Jiexiong Liu, Yixuan Chen, Qihang Zhou, KunLun Meta

This paper introduces KunLunBaizeRAG, a reinforcement learning-driven reasoning framework designed to enhance the reasoning capabilities of large language models (LLMs) in complex multi-hop question-answering tasks. The framework addresses key limitations of traditional RAG, such as retrieval drift, information redundancy, and strategy rigidity. Key innovations include the RAG-driven Reasoning Alignment (RDRA) mechanism, the Search-Think Iterative Enhancement (STIE) mechanism, the Network-Local Intelligent Routing (NLR) mechanism, and a progressive hybrid training strategy. Experimental results demonstrate significant improvements in exact match (EM) and LLM-judged score (LJ) across four benchmarks, highlighting the framework's robustness and effectiveness in complex reasoning scenarios.

📄 PDF Abstract BibTeX arXiv:2506.19466

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-hop Question AnsweringQuestion AnsweringRAGRetrieval

Methods 이 논문이 사용한 방법론

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.
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 Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

RELEAP: Reinforcement-Enhanced Label-Efficient Active Phenotyping for Electronic Health Records

2025-11-08 · Yang Yang, Kathryn I. Pollak, Bibhas Chakraborty, Molei Liu 외 arxiv

Objective: Electronic health record (EHR) phenotyping often relies on noisy proxy labels, which undermine the reliability of downstream risk prediction. Active learning can reduce annotation costs, but most rely on fixed…

Reinforcement LearningActive Learning

matLeap: A fast adaptive Matlab-ready tau-leaping implementation suitable for Bayesian inference

2016-08-25

Background: Species abundance distributions in chemical reaction network models cannot usually be computed analytically. Instead, stochas- tic simulation algorithms allow sample from the the system configuration. Althoug…

Bayesian Inference

L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models

2025-05-23 · Xiaohao Liu, Xiaobo Xia, Weixiang Zhao, Manyi Zhang 외

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inferenc…

Prediction

LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking

2025-01-14 · Yukai Ma, Tiantian Wei, Naiting Zhong, Jianbiao Mei 외

While autonomous driving technology has made remarkable strides, data-driven approaches still struggle with complex scenarios due to their limited reasoning capabilities. Meanwhile, knowledge-driven autonomous driving sy…

Autonomous DrivingDecision MakingDomain AdaptationFew-Shot Learning+1

LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling

2026-05-11 · Sheng Pan, Ming Jin, Bo Du, Shirui Pan arxiv

Time series forecasting serves as an essential tool for many real-world applications, supporting tasks such as resource optimization and decision-making. Despite significant architectural advancements, most modern models…

Time Series Forecasting