Zhongwei Wan

UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation

2024 · arXiv (Cornell University)

We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) that utilizes Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks. This span uncertainty enhances model calibration, improving robustness and mitigating semantic …

Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning

2025 · arXiv (Cornell University)

Large language models (LLMs) demonstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local decisions and lacks global planning, often leading to redundant or inaccurate reasoning. Existing methods, such as tree-based search …

Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS

2025 · arXiv (Cornell University)

Test-time scaling has emerged as a promising paradigm in language modeling, leveraging additional computational resources at inference time to enhance model performance. In this work, we introduce R2-LLMs, a novel and versatile hierarchical retrieval-augmented reasoning …