8 papers
TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization
Peiji Li, Linyang Li, Handa Sun +15
Large language models have demonstrated strong reasoning capabilities in complex tasks through tool integration, which is typically framed as a Markov Decision Process and optimize…
Lowest Span Confidence: A Zero-Shot Metric for Efficient and Black-Box Hallucination Detection in LLMs
Yitong Qiao, Licheng Pan, Yu Mi +4
Hallucinations in Large Language Models (LLMs), i.e., the tendency to generate plausible but non-factual content, pose a significant challenge for their reliable deployment in high…
Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training
Lei Liu, Hao Zhu, Yue Shen +4
Continual Pre-training (CPT) serves as a fundamental approach for adapting foundation models to domain-specific applications. Scaling laws for pre-training define a power-law relat…
HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
Duolin Sun, Dan Yang, Yue Shen +7
The Retrieval-Augmented Generation (RAG) approach enhances question-answering systems and dialogue generation tasks by integrating information retrieval (IR) technologies with larg…
PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation
Zhehao Tan, Yihan Jiao, Dan Yang +7
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge, where the LLM's ability to generate responses based on the combination…
HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation
YiHan Jiao, ZheHao Tan, Dan Yang +5
Retrieval-augmented generation (RAG) has become a fundamental paradigm for addressing the challenges faced by large language models in handling real-time information and domain-spe…