4 papers · 1 filter
Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
Peiyang Liu, Qiang Yan, Ziqiang Cui +3
Standard Retrieval-Augmented Generation (RAG) systems predominantly rely on semantic relevance as a proxy for utility. However, this assumption collapses in realistic decision-maki…
R-Capsule: Compressing High-Level Plans for Efficient Large Language Model Reasoning
Hongyu Shan, Mingyang Song, Chang Dai +2
Chain-of-Thought (CoT) prompting helps Large Language Models (LLMs) tackle complex reasoning by eliciting explicit step-by-step rationales. However, CoT's verbosity increases laten…
HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models
Chang Dai, Hongyu Shan, Mingyang Song +1
Positional encoding mechanisms enable Transformers to model sequential structure and long-range dependencies in text. While absolute positional encodings struggle with extrapolatio…
Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning
Muling Wu, Qi Qian, Wenhao Liu +12
Large Language Models (LLMs) have achieved remarkable performance across various reasoning tasks, yet post-training is constrained by inefficient sample utilization and inflexible…