Papers by Guangzeng Han

7 papers
Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts (2025.naacl-long)

Copied to clipboard

Challenge: Existing classification models only consider the temporal variations of existing data . current models focus on English corpora, leaving time as domains unexplored .
Approach: They propose a framework to generalize classifiers over time on four languages, English, Danish, French, and German.
Outcome: The proposed framework can generalize classifiers over time on four languages, English, Danish, French, and German.
Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation (2026.acl-long)

Copied to clipboard

Challenge: Existing studies either overlook temporal shifts or hardly capture rich shifting patterns of both semantic and knowledge.
Approach: They develop a temporal adaptive learning framework that captures temporal shifts . they use medical ontology and other knowledge sources to integrate temporal adaptation .
Outcome: The proposed framework improves classification tasks across multiple domains and domains with knowledge integration.
Model-Agnostic Meta Learning for Class Imbalance Adaptation (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to address class imbalance and data difficulty have been used to train models.
Approach: They propose a framework that prioritizes challenging samples and minority classes over hard examples and their semantically similar neighbors to address class imbalance.
Outcome: The proposed framework outperforms baselines on six imbalanced datasets and achieves substantial improvements for minority classes.
Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Copied to clipboard

Challenge: MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach: They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome: The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.
Length-Aware Multi-Kernel Transformer for Long Document Classification (2024.starsem-1)

Copied to clipboard

Challenge: Existing SOTA models segment long texts into equal-length snippets, but they have new challenges of context fragmentation and generalizability due to sentence boundaries and varying text lengths.
Approach: They propose a Length-Aware Multi-Kernel Transformer to encode long documents by transformers and vectorize text length by the kernels to promote model robustness over varying document lengths.
Outcome: The proposed model outperforms existing models on five benchmarks from health and law domains up to an absolute 10.9% improvement.
Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Genetic Prompt combines genetic algorithms with Large Language Models to augment synthetic data generation.
Approach: They propose a framework that combines genetic algorithms with LLMs to augment synthetic data generation.
Outcome: The proposed framework outperforms state-of-the-art models and shows robust performance across generator models.
What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for instruction-tuning data contain redundancy and low-quality samples.
Approach: They propose an instruction data selection framework based on weighted in-context influence . they show that sample difficulty negatively correlates with in-constext influence.
Outcome: The proposed method outperforms baselines under constrained data budgets while demonstrating that sample difficulty negatively correlates with in-context influence.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations