Conversational agents based on Large Language Models (LLMs) have recently emerged as powerful tools for human-computer interaction. Nevertheless, their black-box nature implies challenges in predictability and a lack of personalization, both of which can be addressed by controlled generation. This work proposes an end-to-end method to obtain modular and explainable control over LLM outputs through ontological definitions of aspects related to the conversation. Key aspects are modeled and used as constraints; we then further fine-tune the LLM to generate content accordingly. To validate our approach, we explore two tasks that tackle two key conversational aspects: the English proficiency level and the polarity profile of the content. Using a hybrid fine-tuning procedure on seven state-of-the-art, open-weight conversational LLMs, we show that our method consistently outperforms pre-trained baselines, even on smaller models. Beyond quantitative gains, the framework remains model-agnostic, lightweight, and interpretable, enabling reusable control strategies that can be extended to new domains and interaction goals. This approach enhances alignment with strategy instructions and demonstrates the effectiveness of ontology-driven control in conversational systems.
AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation
School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University(计算机科学与工程学院、计算机网络与信息集成重点实验室、教育部、东南大学)
MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
University of Central Florida(佛罗里达大学中央分校);University of Rochester(罗切斯特大学);University of Illinois at Chicago(伊利诺伊大学香槟分校);Case Western Reserve University(凯斯西储大学)
Center for Healthcare Organization and Implementation Research, VA Bedford Health Care(VA贝德福德医疗中心健康组织与实施研究中心);Miner School of Computer and Information Sciences, University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校计算机与信息科学学院);Manning College of Information and Computer Sciences, University of Massachusetts Amherst(马萨诸塞大学阿姆赫斯特分校信息与计算机科学学院)
MindGap: A Conversational AI Framework for Upstream Neuroplastic Intervention in Post-Traumatic Stress Disorder
Old Dominion University(旧 Dominion 大学);AI Motion Labs(AI Motion 实验室);Nanyang Technological University(南洋理工大学);University of Colombo(科伦坡大学);Accenture Technology Labs(Accenture 技术实验室);Department of Psychiatry and Neurobehavioral Sciences(精神病学与神经行为科学系);University of Virginia School of Medicine(弗吉尼亚大学医学院);Blanchfield Army Community Hospital(Blanchfield 军队社区医院);McDonald Army Health Center(McDonald 军队健康中心)
Lightweight LLM Agent Memory with Small Language Models
University of Electronic Science and Technology of China(电子科学与技术大学);Kyung Hee University(庆熙大学);City University of Hong Kong(香港城市大学);University of Oxford(牛津大学)
Cost-effective Instruction Learning for Pathology Vision and Language Analysis
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Computer Science, Fudan University(复旦大学计算机学院);National Biomedical Imaging Center, College of Future Technology, Peking University(北京大学未来技术学院生物医学成像中心);Ruijin Hospital, Shanghai Jiaotong University School of Medicine(上海交通大学医学院瑞金医院);Department of Pathology, State Key Laboratory of Cancer Biology, Xijing Hospital(西京医院病理科,癌症生物学国家重点实验室);Department of Computer Science, Rutgers University(罗格斯大学计算机科学系)
CityLLM: A framework for natural-language querying of semantic 3D city models
GRID Lab, School of Built Environment, UNSW Sydney(新南威尔士大学悉尼分校建筑环境学院GRID实验室);School of Civil and Environmental Engineering, UNSW Sydney(新南威尔士大学悉尼分校土木与环境工程学院)
研究针对语义 3D 城市模型访问查询难的问题,提出 CityLLM 框架,结合空间与图形数据库,在基于语言模型工作流中支持迭代查询等。通过多种模型在鹿特丹数据集上评估,多个场景 54 个查询显示其性能强大,为语义 3D 城市数据对话访问提供轻量级可扩展方法。
ReVision: A Dataset and Baseline VLM for Privacy-Preserving Task-Oriented Visual Instruction Rewriting
School of Information(信息学院);The University of Texas at Austin(德克萨斯大学奥斯汀分校);Department of Statistics and Data Science(统计与数据科学系);Yale University(耶鲁大学);School of Computing and Augmented Intelligence(计算与增强智能学院)
DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing
School of Computer Science, Peking University(北京大学计算机学院);Center on Frontiers of Computing Studies, Peking University(北京大学计算前沿研究中心);National Research and Engineering Center of Software Engineering, Peking University(北京大学国家软件工程研究与工程中心)
The Art of Socratic Inquiry: A Framework for Proactive Template-Guided Therapeutic Conversation Generation
School of Information Science and Engineering, Lanzhou University(信息科学与工程学院,兰州大学);School of Medical Technology, Beijing Institute of Technology(医学技术学院,北京理工大学)
Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips
Louisiana State University(路易斯安那州立大学);Northeastern University(东北大学);Zhejiang University(浙江大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);Southeast University(东南大学)
Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings
University of Lübeck(吕贝克大学);Technical University of Munich(慕尼黑工业大学);AUMOVIO SE;Osnabrück University(奥斯纳布吕克大学);Leibniz Institute for Agricultural Engineering and Bioeconomy(莱布尼茨农业工程与生物经济研究所);University of Hamburg(汉堡大学)