工程、医疗保健和教育领域的领域专家在生成技术手册、用药说明和儿童阅读材料等高质量内容时会遵循严格的标准。然而,当前可控文本生成领域的研究尚未探索将这些标准用作控制参考。为此,我们提出了Standardize,这是一种基于检索式上下文学习的框架,用于引导大语言模型与专家定义的标准对齐。我们以教育领域的英语语言标准为用例,针对开放式内容生成任务,采用了欧洲语言共同参考框架(Common European Framework of Reference for Languages, CEFR)和共同核心标准(Common Core Standards, CCS)。研究结果表明,在接受评估的开源和商业大语言模型中,模型的精确准确率可提升45%至100%,这证明使用从标准中提取的知识构件并将其整合到生成过程中,能够有效引导模型生成更符合标准的内容。
英文摘要:
Domain experts across engineering, healthcare, and education follow strict standards for producing quality content such as technical manuals, medication instructions, and children's reading materials. However, current works in controllable text generation have yet to explore using these standards as references for control. Towards this end, we introduce Standardize, a retrieval-style in-context learning-based framework to guide large language models to align with expert-defined standards. Focusing on English language standards in the education domain as a use case, we consider the Common European Framework of Reference for Languages (CEFR) and Common Core Standards (CCS) for the task of open-ended content generation. Our findings show that models can gain a 45% to 100% increase in precise accuracy across open and commercial LLMs evaluated, demonstrating that the use of knowledge artifacts extracted from standards and integrating them in the generation process can effectively guide models to produce better standard-aligned content.
Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(多媒体信息处理国家重点实验室,计算机学院,北京大学);LLM-Core Xiaomi(小米LLM-Core)
Aligning ESG Controversy Data with International Guidelines through Semi-Automatic Ontology Construction
University of Zürich (UZH)(苏黎世大学);RepRisk AG(RepRisk公司);Graduate School of Information Science and Technology, The University of Tokyo(东京大学信息科学与技术研究生院);The Canon Institute for Global Studies(佳能全球研究学院)
TCM-Eval: An Expert-Level Dynamic and Extensible Benchmark for Traditional Chinese Medicine
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);Beijing Zhimingtang Technology Co., Ltd.(北京智明堂科技有限公司);Beijing Zhiyan AI Technology Co., Ltd.(北京智言AI科技有限公司);Guangzhou University of Chinese Medicine(广州中医药大学)
TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
Department of Computer Science, Stanford University, Stanford, CA, USA(计算机科学系,斯坦福大学,斯坦福,加州,美国);Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA, USA(精神病学与行为科学系,斯坦福大学,斯坦福,加州,美国);Department of Biomedical Data Science, Stanford University, Stanford, CA, USA(生物医学数据科学系,斯坦福大学,斯坦福,加州,美国);University of California, Berkeley, Berkeley, CA, USA(加州大学伯克利分校,伯克利,加州,美国);The University of Hong Kong, Hong Kong(香港大学,香港)
Multi-objective Large Language Model Alignment with Hierarchical Experts
Harbin Institute of Technology, Shenzhen, China(哈尔滨工业大学(深圳));Nanyang Technological University(南洋理工大学);Peng Cheng Laboratory(鹏城实验室);Beijing Academy of Artificial Intelligence(北京人工智能研究院);Tencent(腾讯)
Self-Instruct: Aligning Language Models with Self-Generated Instructions
University of Washington(华盛顿大学);Tehran Polytechnic(德黑兰理工大学);Arizona State University(亚利桑那州立大学);Johns Hopkins University(约翰斯·霍普金斯大学);Allen Institute for AI(艾伦人工智能研究所)
VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
The Hong Kong University of Science and Technology(香港科学与技术大学);Nanyang Technological University(南洋理工大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting
Hong Kong University of Science and Technology(香港科技大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));University of Cologne(科隆大学)
CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
Southeast University(东南大学);ByteDance Inc.(字节跳动公司);Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China(新一代人工智能技术及其交叉应用重点实验室(东南大学),中华人民共和国教育部,中国)