Papers by Zhengyang Shan
Gender Inclusivity Fairness Index (GIFI): A Multilevel Framework for Evaluating Gender Diversity in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | GIFI measures the diversity of LLMs' outputs, including gender identifiers, and identifies gender biases associated with varying gender identifiers. |
| Approach: | They propose a Gender Inclusivity Fairness Index (GIFI) that quantifies the diverse gender inclusivity of large language models. |
| Outcome: | The proposed metric quantifies the diversity of LLMs across multiple dimensions, including non-binary identities. |
Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics? (2026.eacl-long)
Copied to clipboard
| Challenge: | Using multi-task evaluation, we examine how independent demographic bias mechanisms are from general demographic recognition in language models. |
| Approach: | They compare attribution-based and correlation-based methods for locating bias features in language models to find out which features are independent from general demographic recognition. |
| Outcome: | The proposed method reduces bias without degrading recognition performance. |
HisDoc-OCR: Restoring Visual Grounding in MLLMs for Chinese Historical Document OCR (2026.findings-acl)
Copied to clipboard
| Challenge: | Despite multimodal large language models' strong performance on modern document OCR, their application to historical Chinese texts suffers from severe hallucinations, character fabrication, uncontrolled repetition, and semantic drift. |
| Approach: | They propose a multimodal large language model which restores visual grounding through three synergistic strategies: Layout Injection, First-Occurrence Boost, Self-Distilled Attention Focusing and HisDoc-OCR. |
| Outcome: | The proposed model outperforms general-purpose and OCR-specific models on Chinese historical documents. |
SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for process supervision fail to distinguish meaningful progress from mere verbosity . existing methods lack a coherent approach to process supervision . |
| Approach: | They propose a framework that formalizes reasoning as a trajectory through a state space of empirical solvability. |
| Outcome: | The proposed framework achieves an average accuracy gain of 3% with 30% reduced token consumption. |