5 papers · 1 filter
Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs
Yihang Du, Juhao Liang, Zhengzhao Lai +2
Multimodal large language models (MLLMs) exhibit substantial performance degradation in non-English visual reasoning, despite the strong multilingual competence of their text-only…
Do LLMs Triage Like Clinicians? A Dynamic Study of Outpatient Referral
Xiaoxiao Liu, Qingying Xiao, Bingquan Zhang +8
Outpatient referral (OR) is a core clinical workflow that assigns patients to hospital departments under incomplete and evolving information, yet it is commonly simplified as a sta…
PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment
Chang Hong, Minghao Wu, Qingying Xiao +5
As medical LLMs transition to clinical deployment, assessing their ethical reasoning capability becomes critical. While achieving high accuracy on knowledge benchmarks, LLMs lack v…
Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
Xu Wang, Yan Hu, Wenyu Du +3
Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth i…
Model Unlearning via Sparse Autoencoder Subspace Guided Projections
Xu Wang, Zihao Li, Benyou Wang +2
Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing…