Papers by Zeyang Zhou

3 papers
Flames: Benchmarking Value Alignment of LLMs in Chinese (2024.naacl-long)

Copied to clipboard

Challenge: Existing benchmarks for large language models (LLMs) do not accurately uncover safety vulnerabilities in LLMs.
Approach: They propose a value alignment benchmark called Flames that encompasses both harmlessness principles and a unique morality dimension that integrates specific Chinese values such as harmony.
Outcome: The proposed model performs poorly on Flames, particularly in safety and fairness dimensions.
Investigating Capsule Networks with Dynamic Routing for Text Classification (D18-1)

Copied to clipboard

Challenge: Earlier efforts in text modeling have achieved limited success on word meanings . convolutional neural networks (CNNs) are used to model higher level concepts and facts in texts .
Approach: They propose three strategies to stabilize dynamic routing process to alleviate disturbance of noise capsules.
Outcome: The proposed methods achieve state-of-the-art on 4 out of 6 datasets . they show that capsule networks exhibit significant improvement over baseline methods .
StrucText-Eval: Evaluating Large Language Model’s Reasoning Ability in Structure-Rich Text (2025.acl-long)

Copied to clipboard

Challenge: Structured data has been central to corporate data strategies for decades . however, with the advancement of large language models (LLMs), there has been a significant shift towards the effective utilization of unstructured data.
Approach: They propose an automatic evaluation data generation method to assess LLMs’ reasoning capabilities on structure-rich text.
Outcome: The proposed method supports 8 structured languages and 29 tasks, generating data with adjustable complexity through controllable nesting and structural width.

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