UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Modelsby Yijiang River Dong,…
Quantized Embedding Vectors for Controllable Diffusion Language Modelsby Cheng Kang, Xinye Chen, Yong Hu, Daniel…
Large Language Models as Zero-shot Dialogue State Tracker through Function Callingby Zekun Li, Zhiyu Zoey…
Learning Using a Single Forward Passby Aditya Somasundaram, Pushkal Mishra, Ayon BorthakurFirst submitted to arxiv…
Chain-of-Planned-Behaviour Workflow Elicits Few-Shot Mobility Generation in LLMsby Chenyang Shao, Fengli Xu, Bingbing Fan, Jingtao…
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluationby Xiaoying Zhang, Baolin Peng, Ye Tian,…
ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimizationby Feifan Song, Yuxuan…
LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Datasetby…
The Application of ChatGPT in Responding to Questions Related to the Boston Bowel Preparation Scaleby…
Persian Speech Emotion Recognition by Fine-Tuning Transformersby Minoo Shayaninasab, Bagher BabaaliFirst submitted to arxiv on:…