控制文本生成的最新工作要么需要基于属性的微调的基础语言模型（LM），或限制了参数化的属性映射，以兼容的基础自回归LM。在这项工作中，我们提出了Mix and Match LM，这是一种基于全局分数的可控文本生成方法，它结合了任意预训练的黑盒模型，用于在生成的文本中实现所需的属性，而不涉及任何关于黑盒模型的微调或结构假设。我们将可控生成的任务解释为从基于能量的模型中抽取样本，该模型的能量值是来自黑盒模型的分数的线性组合，黑盒模型分别负责流畅性、控制属性和对任何条件上下文的忠诚度。我们使用Metropolis-Hastings抽样方案从这个基于能量的模型中使用双向上下文和全局属性特征进行抽样。我们验证了我们的方法在各种控制生成和基于风格的文本修订任务的有效性，优于最近提出的方法，涉及额外的训练，微调，或限制性的假设模型的形式。
英文摘要：
Recent work on controlled text generation has either required attribute-based fine-tuning of the base language model (LM), or has restricted the parameterization of the attribute discriminator to be compatible with the base autoregressive LM. In this work, we propose Mix and Match LM, a global score-based alternative for controllable text generation that combines arbitrary pre-trained black-box models for achieving the desired attributes in the generated text without involving any fine-tuning or structural assumptions about the black-box models. We interpret the task of controllable generation as drawing samples from an energy-based model whose energy values are a linear combination of scores from black-box models that are separately responsible for fluency, the control attribute, and faithfulness to any conditioning context. We use a Metropolis-Hastings sampling scheme to sample from this energy-based model using bidirectional context and global attribute features. We validate the effectiveness of our approach on various controlled generation and style-based text revision tasks by outperforming recently proposed methods that involve extra training, fine-tuning, or restrictive assumptions over the form of models.
Gumbel-Softmax Flow Matching with Straight-Through Guidance for Controllable Biological Sequence Generation
Duke University（杜克大学）；University of Pennsylvania（宾夕法尼亚大学）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）；Mila, Quebec AI Institute（米拉魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）
Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design
Department of Biomedical Engineering, Duke University（杜克大学生物医学工程系）；Department of Computer Science, Fudan University（复旦大学计算机科学系）；Center of Computational Biology, Duke-NUS Medical School（杜克-新加坡国立大学医学学校计算生物学中心）；Management and Technology Program, University of Pennsylvania（宾夕法尼亚大学管理与技术项目）；Department of Computer Science, Duke University（杜克大学计算机科学系）；Department of Biostatistics and Bioinformatics, Duke University（杜克大学生物统计与生物信息学系）
提出 MOG-DFM 框架，通过混合秩方向分数和自适应超锥滤波引导预训练离散流匹配模型，实现多目标帕累托高效的肽与增强子 DNA 序列设计。
CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
The University of Melbourne, Australia（墨尔本大学）；Wuhan University, China（武汉大学）；The Hong Kong University of Science（香港科学与技术大学）；The University of Auckland, New Zealand（奥克兰大学）；Monash University, Australia（莫纳什大学）
MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
Tsinghua University（清华大学）；ESTATES PTE LTD（6ESTATES PTE LTD）；Beijing University of Posts and Telecommunications（北京邮电大学）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Institute for Artificial Intelligence, Tsinghua University（清华大学人工智能研究院）；State Key Lab on Intelligent Technology and Systems, Tsinghua University（智能技术与系统国家重点实验室）
Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Model
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Faculty of Information Technology, Monash University（莫纳什大学信息技术学院）；Baidu Inc.（百度公司）
NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院通用人工智能国家重点实验室）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）
Evolutionary Soups: Evolving Mixture-of-Experts for Multi-Objective LLM Alignment
Fraunhofer Institute for Applied Information Technology FIT（弗劳恩霍夫应用信息技术研究所FIT）；University of Cologne（科隆大学）；University of Stuttgart（斯图加特大学）；University of Southampton（南安普顿大学）；Soochow University（苏州大学）；University Hospital of Cologne（科隆大学医院）
Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data
Signal Analysis and Interpretation Lab, University of Southern California, USA（信号分析与解释实验室，南加州大学）；Thomas Lord Department of Computer Science, University of Southern California, USA（托马斯·劳德计算机科学系，南加州大学）；Department of Linguistics, University of Southern California（语言学系，南加州大学）
