7 papers
Can LLMs Prove Robotic Path Planning Optimality? A Benchmark for Research-Level Algorithm Verification
Zhengbang Yang, Md. Tasin Tazwar, Minghan Wei +1
Robotic path planning problems are often NP-hard, and practical solutions typically rely on approximation algorithms with provable performance guarantees for general cases. While d…
Distribution Corrected Offline Data Distillation for Large Language Models
Yumeng Zhang, Zhengbang Yang, Yevin Nikhel Goonatilake +1
Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches f…
DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher
Yisheng Zhong, Zhengbang Yang, Zhuangdi Zhu
LLM unlearning is a technique to remove the impacts of undesirable knowledge from the model without retraining from scratch, which is indispensable towards trustworthy AI. Existing…
CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment
Zhengbang Yang, Yisheng Zhong, Junyuan Hong +1
Pretrained knowledge memorized in LLMs raises critical concerns over safety and privacy, which has motivated LLM Unlearning as a technique for selectively removing the influences o…
Hierarchical Federated Unlearning for Large Language Models
Yisheng Zhong, Zhengbang Yang, Zhuangdi Zhu
Large Language Models (LLMs) are increasingly integrated into real-world applications, raising concerns about privacy, security and the need to remove undesirable knowledge. Machin…
ChatWise: A Strategy-Guided Chatbot for Enhancing Cognitive Support in Older Adults
Zhengbang Yang, Junyuan Hong, Yijiang Pang +2
Cognitive health in older adults presents a growing challenge. Although conversational interventions show feasibility in improving cognitive wellness, human caregiver resources rem…