5 papers
What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective
Guangzeng Han, Xiaolei Huang
Instruction-tuning datasets often contain substantial redundancy and low-quality samples, necessitating effective data selection methods. We propose an instruction data selection f…
Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation
Weisi Liu, Guangzeng Han, Xiaolei Huang
Time introduces fundamental challenges in model development and deployment: models are usually trained on historical data while deployed on future data where semantic distributions…
Model-Agnostic Meta Learning for Class Imbalance Adaptation
Hanshu Rao, Guangzeng Han, Xiaolei Huang
Class imbalance is a widespread challenge in NLP tasks, significantly hindering robust performance across diverse domains and applications. We introduce Hardness-Aware Meta-Resampl…
From UAV Imagery to Agronomic Reasoning: A Multimodal LLM Benchmark for Plant Phenotyping
Yu Wu, Guangzeng Han, Ibra Niang Niang +6
To improve crop genetics, high-throughput, effective and comprehensive phenotyping is a critical prerequisite. While such tasks were traditionally performed manually, recent advanc…
Chain-of-Interaction: Enhancing Large Language Models for Psychiatric Behavior Understanding by Dyadic Contexts
Guangzeng Han, Weisi Liu, Xiaolei Huang +1
Automatic coding patient behaviors is essential to support decision making for psychotherapists during the motivational interviewing (MI), a collaborative communication interventio…