Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models
Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University(上海数据科学 key laboratory,计算机科学与人工智能学院,复旦大学);School of Data Science, Fudan University(数据科学学院,复旦大学);Ant Group(蚂蚁集团)
It is crucial for large language models (LLMs) to follow instructions that involve multiple constraints. However, it is an unexplored area to enhance LLMs' ability to follow soft constraints. To bridge the gap, we initially design a pipeline to construct datasets with high-quality outputs automatically. Additionally, to fully utilize the positive and negative samples generated during the data construction process, we choose Direct Preference Optimization (DPO) as the training method. Furthermore, taking into account the difficulty of soft constraints indicated by the number of constraints, we design a curriculum learning training paradigm based on the constraint quantity. We experimentally evaluate the effectiveness of our methods in improving LLMs' soft constraint following ability and analyze the factors driving the improvements.The datasets and code are publicly available at https://github.com/Rainier-rq/FollowSoftConstraint.
From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Baidu Inc.(百度公司);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
PaniniQA: Enhancing Patient Education Through Interactive Question Answering
University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Emory University(埃默里大学);Northeastern University(东北大学);UMass Chan Medical School(马萨诸塞大学陈医学院);University of Minnesota(明尼苏达大学);University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校)
Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Models
Department of Systems Engineering and Engineering Management(系统工程与工程管理系);The Chinese University of Hong Kong(香港中文大学);Centre for Perceptual and Interactive Intelligence (CPII) Limited(感知与交互智能中心(CPII)有限公司)
本文提出将 LoRA 集成到已有自监督模型并结合数据组合与重新聚类保留策略,使 mHuBERT 高效扩展至普通话,在语音重合成任务中显著提升 MOS 并降低 WER,同时保持原有语言能力不退化。
ARREST: Adversarial Resilient Regulation Enhancing Safety and Truth in Large Language Models
Electronics and Communication Sciences Unit (ECSU), Indian Statistical Institute Kolkata, University of Surrey, and Indian Institute Of Technology Delhi(电子与通信科学单元(ECSU)、印度统计研究所科钦分校、萨里大学和印度理工学院德里)