6 papers
MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation
Runhan Shi, Quan Zhou, Yuqian Xu +14
Large language models (LLMs) are increasingly deployed in online medical consultation, yet existing benchmarks remain poorly aligned with real clinical practice. Many rely on synth…
Mitigating Hallucination in Financial Retrieval-Augmented Generation via Fine-Grained Knowledge Verification
Taoye Yin, Haoyuan Hu, Yaxin Fan +5
In financial Retrieval-Augmented Generation (RAG) systems, models frequently rely on retrieved documents to generate accurate responses due to the time-sensitive nature of the fina…
Layout-Aware Parsing Meets Efficient LLMs: A Unified, Scalable Framework for Resume Information Extraction and Evaluation
Fanwei Zhu, Jinke Yu, Zulong Chen +6
Automated resume information extraction is critical for scaling talent acquisition, yet its real-world deployment faces three major challenges: the extreme heterogeneity of resume…
Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling
Lipeng Xie, Sen Huang, Zhuo Zhang +9
Conventional reward modeling relies on gradient descent over neural weights, creating opaque, data-hungry "black boxes." We propose a paradigm shift from implicit to explicit rewar…
SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning
Hexian Ni, Tao Lu, Haoyuan Hu +2
Preference-based Reinforcement Learning (PbRL) methods provide a solution to avoid reward engineering by learning reward models based on human preferences. However, poor feedback-…
Intermittent Semi-Working Mask: A New Masking Paradigm for LLMs
HaoYuan Hu, Mingcong Lu, Di Luo +10
Multi-turn dialogues and context-intensive tasks challenge Large Language Models (LLMs) to integrate long histories without sacrificing generation quality. Although prefix LLMs can…