Papers by Zengyi Yu
KidsArtBench: Multi-Dimensional Children’s Art Evaluation with Attribute-Aware MLLMs (2026.eacl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) show impressive capabilities across visual–language tasks, but their capacity to evaluate artistic expression remains limited. |
| Approach: | They propose an attribute-specific multi-LoRA approach where each attribute corresponds to a distinct evaluation dimension in the scoring rubric. |
| Outcome: | The proposed approach increases correlation from 0.468 to 0.653 on Qwen2.5-VL-7B, with the largest gains on perceptual dimensions and narrowed gaps on higher-order attributes. |
EMNLP: Educator-role Moral and Normative Large Language Models Profiling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing frameworks for evaluating the ethical and moral alignment of large language models (LLMs) in educational AI are lacking. |
| Approach: | They propose a framework for a teacher-role moral and normative LLMs profiling . they extend existing scales and construct 88 teacher-specific moral dilemmas . |
| Outcome: | The proposed framework evaluates compliance and vulnerability of teacher-role LLMs under soft prompt injection. |
Decoding LLM Personality Measurement: Forced-Choice vs. Likert (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent research has focused on investigating the psychological characteristics of Large Language Models (LLMs), emphasizing the importance of comprehending their behavioral traits. |
| Approach: | They evaluated six Large Language Models: Llama-3.1-8B, GLM-4-9B, Claude-3.5-sonnet, and Deepseek-V3 and used the forced-choice test to assess their personality traits. |
| Outcome: | The forced-choice test is more reliable and more accurate than the likert scale and forced-CHOICE test results for LLMs' Big Five personality scores. |