2 papers
cs.CV2025
Are MLMs Trapped in the Visual Room?
Yazhou Zhang, Chunwang Zou, Qimeng Liu +6
Can multi-modal large models (MLMs) that can ``see'' an image be said to ``understand'' it? Drawing inspiration from Searle's Chinese Room, we propose the \textbf{Visual Room} argu…
cs.CL2025
Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories
Yazhou Zhang, Qimeng Liu, Qiuchi Li +2
Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive…