6 papers
From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models
Jiaxu Zuo, Mu You, Kaixin Lan +5
Recent advances in Large Language Models (LLMs) have substantially transformed Automated Essay Scoring (AES), yet the internal mechanisms underlying LLM-based scoring remain poorly…
MC-PDD: Masked Corpus-Level Pretraining Data Detection for Black-Box Large Language Models
Kaixin Lan, Mu You, Tao Fang +3
Pretraining is fundamental to the development of Large Language Models (LLMs), yet the opacity of pretraining data complicates model analysis and raises ethical, legal, and fairnes…
Worlds Within Words: Translating Culture in Ancient Chinese Texts with Multi-Agent Coordination
Xiaoqi He, Kaixin Lan, Mu You +3
Large language model (LLM)-based machine translation has advanced cross-cultural communication, yet it still struggles with culture-loaded words (CLWs) in ancient Chinese texts. Th…
CLIF: Concept-Level Influence Functions for Transparent Bottleneck Models
Yike Sun, Mingkun Xu, Mu You +5
In recent years, the black-box nature of deep learning models has limited their application in high-stakes domains such as medical diagnosis and finance, where interpretability is…
Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judge
Wentao Zhang, Qi Zhang, Mingkun Xu +6
Crop disease diagnosis from field photographs faces two recurring problems: models that score well on benchmarks frequently hallucinate species names, and when predictions are corr…
RF-Agent: Automated Reward Function Design via Language Agent Tree Search
Ning Gao, Xiuhui Zhang, Xingyu Jiang +3
Designing efficient reward functions for low-level control tasks is a challenging problem. Recent research aims to reduce reliance on expert experience by using Large Language Mode…