Yang Gao

Atomistic simulations of dual phase structure for gold nanostructures with a new EAM model

Qiang Shen, Daoxuan Zhou, Xiaoliang Zhang, Peng Wang et autres

cn (code pays fourni par la source)

Retrieval is NOT always needed: Exploring the timing of retrieval in dynamic retrieval-augmented generation

Yuhang Liu, Heyan Huang, Yizhe Yang, Zhizhuo Zeng et autres

cn (code pays fourni par la source)

Planner Policies Are Bias Learners: A Comprehensive Analysis of Preference Bias in LLM-based Dialogue Planner Policies

Yizhe Yang, Heyan Huang, J F Li, Huashan Sun et autres

Large language models have facilitated the development of sophisticated dialogue planner policies. However, their reliance on LLM-based simulation and feedback for policy optimization may introduce preference bias. This article presents the first comprehensive analysis of preference bias in LLM-based dialogue planners. It …

cn (code pays fourni par la source)

Research on photovoltaic power forecasting driven by data characteristics

Feng Li, Fengfeng Bai, Yang Gao, Qipeng Zheng

Accurate photovoltaic power forecasting is crucial for the grid integration and dispatch of renewable energy sources and for ensuring the stable operation of power systems. Existing models inadequately capture physical laws and struggle to adapt to the strong periodicity, non-stationarity, and multivariate …

cn (code pays fourni par la source)

A hallucination detection and mitigation framework for faithful text summarization using LLMs

Shenling Liu, Yang Gao, Shasha Li, Pancheng Wang et autres

Recent advancements in large language models (LLMs) have significantly propelled the field of automatic text summarization. Nevertheless, the domain continues to face substantial challenges, particularly the issue of hallucination where summaries contain information not present in the source text. Such problems not …

cn (code pays fourni par la source)

Fusing generation task data to enhance generalization of LLMs in zero-shot relational triplet extraction

Xiangzheng Si, Yuhao Ye, Yuming Shang, Mengyuan Cao et autres

cn (code pays fourni par la source)

A multi-layer model for residual stress relaxation aligned with microstructure evolution under thermal exposure and cyclic loading

Dianyin Hu, Tao Wang, Hongyang Huang, Jianxing Mao et autres

cn, gb (code pays fourni par la source)

Enhancing Faithfulness in Text Summarization: A Hallucination Detection and Mitigation Framework Based on LLM

Shenling Liu, Yang Gao, Shasha Li, Pancheng Wang et autres

cn (code pays fourni par la source)

Fundamental Capabilities and Applications of Large Language Models: A Survey

Yang Gao, Yizhe Yang, Yinghao Li, Huashan Sun et autres

Large Language Models (LLMs) have demonstrated remarkable effectiveness across various domain-specific applications. However, which fundamental capabilities most contribute to their success in different domains remains unclear. This uncertainty complicates LLM evaluation, as existing benchmark-based assessments often fail to capture their real-world performance, …

cn (code pays fourni par la source)

DRMSpell: dynamically reweighting multimodality for Chinese spelling correction

Yinghao Li, Heyan Huang, Baojun Wang, Yang Gao

Chinese spelling correction (CSC) is a task that aims to detect and correct the spelling errors that may occur in Chinese texts. However, the Chinese language exhibits a high degree of complexity, characterized by the presence of multiple phonetic representations known as …

cn (code pays fourni par la source)

A Multi-Layer Model for Residual Stress Relaxation Aligned with Microstructure Evolution Under Thermal Exposure and Cyclic Loading

Dianyin Hu, Tao Wang, Hongyang Huang, Jianxing Mao et autres

cn (code pays fourni par la source)

Enhancing consistency with the fusion of paralleled decoders for text generation

Yaolin Li, Heyan Huang, Yu Bai, Yang Gao

cn (code pays fourni par la source)