9 papers
Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration
Ruochen Jin, Zhanliang Wang, Zongyu Dai +2
Preference alignment often makes large language models (LLMs) overconfident and poorly calibrated. Traditional post-hoc temperature scaling is inherently domain-dependent: a temper…
Beyond Logit Adjustment: A Residual Decomposition Framework for Long-Tailed Reranking
Zhanliang Wang, Hongzhuo Chen, Quan Minh Nguyen +2
Long-tailed classification, where a small number of frequent classes dominate many rare ones, remains challenging because models systematically favor frequent classes at inference…
A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
Zhanliang Wang, Jiancong Xiao, Ruochen Jin +3
Calibration measures whether a model's predicted confidence aligns with its empirical accuracy, and is central to the reliable deployment of large language models (LLMs) in high-st…
Autonomous Agent-Orchestrated Digital Twins (AADT): Leveraging the OpenClaw Framework for State Synchronization in Rare Genetic Disorders
Hongzhuo Chen, Zhanliang Wang, Quan M. Nguyen +3
Background: Medical Digital Twins (MDTs) are computational representations of individual patients that integrate clinical, genomic, and physiological data to support diagnosis, tre…
Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes
Zhanliang Wang, Da Wu, Quan Nguyen +1
Background: Several studies show that large language models (LLMs) struggle with phenotype-driven gene prioritization for rare diseases. These studies typically use Human Phenotype…
MultiSHAP: A Shapley-Based Framework for Explaining Cross-Modal Interactions in Multimodal AI Models
Zhanliang Wang, Kai Wang
Multimodal AI models have achieved impressive performance in tasks that require integrating information from multiple modalities, such as vision and language. However, their "black…