MOPO: Multi-Objective Prompt Optimization for Affective Text Generation
Institut für Maschinelle Sprachverarbeitung, University of Stuttgart(斯图加特大学机器语言研究所);Fundamentals of Natural Language Processing, University of Bamberg(班贝格大学自然语言处理基础研究所)
How emotions are expressed depends on the context and domain. On X (formerly Twitter), for instance, an author might simply use the hashtag #anger, while in a news headline, emotions are typically written in a more polite, indirect manner. To enable conditional text generation models to create emotionally connotated texts that fit a domain, users need to have access to a parameter that allows them to choose the appropriate way to express an emotion. To achieve this, we introduce MOPO, a Multi-Objective Prompt Optimization methodology. MOPO optimizes prompts according to multiple objectives (which correspond here to the output probabilities assigned by emotion classifiers trained for different domains). In contrast to single objective optimization, MOPO outputs a set of prompts, each with a different weighting of the multiple objectives. Users can then choose the most appropriate prompt for their context. We evaluate MOPO using three objectives, determined by various domain-specific emotion classifiers. MOPO improves performance by up to 15 pp across all objectives with a minimal loss (1-2 pp) for any single objective compared to single-objective optimization. These minor performance losses are offset by a broader generalization across multiple objectives - which is not possible with single-objective optimization. Additionally, MOPO reduces computational requirements by simultaneously optimizing for multiple objectives, eliminating separate optimization procedures for each objective.
EmoMind: Decoding Affective Captions from Human Brain fMRI
Department of Biomedical Engineering(生物医学工程系);Vanderbilt University(范德比大学);Research Institute of Electrical Communication(电气通信研究所);Tohoku University(东北大学);University of Florida(佛罗里达大学)
UKP_Psycontrol at SemEval-2026 Task 2: Modeling Valence and Arousal Dynamics from Text
Ubiquitous Knowledge Processing Lab (UKP Lab)(无所不在的知识处理实验室);Technical University of Darmstadt(达姆斯塔特技术大学);National Research Center for Applied Cybersecurity ATHENE(应用网络安全国家研究中心ATHENE);Psychiatric Control Systems Lab(精神病控制系统实验室);Marburg University(马尔堡大学)
A Formative Study of Brief Affective Text as a Complement to Wearable Sensing for Longitudinal Student Health Monitoring
University of Vermont(佛罗里达大学);University of Vermont Department of Computer Science(佛罗里达大学计算机科学系);University of Vermont Department of Psychological Science(佛罗里达大学心理学科学系);University of Vermont Vermont Complex Systems Center(佛罗里达大学复杂系统中心);University of Vermont Department of Rehabilitation(佛罗里达大学康复与运动科学系);University of Vermont MassMutual Center of Excellence in Complex Systems(佛罗里达大学复杂系统与数据科学卓越中心);Adelaide University School of Mathematical Sciences(阿德莱德大学数学科学学院);University of Vermont Department of Mathematics(佛罗里达大学数学系);Adelaide University(阿德莱德大学)
Investigating Disability Representations in Text-to-Image Models
Department of Computational Linguistics University of Zurich(计算语言学系 苏黎世大学);Center for Law & Economics ETH Zurich(法律与经济学中心 伯尔尼联邦理工学院);Department of Information Systems University of Lausanne(信息系统系 瑞士洛桑大学)
From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models
State Key Laboratory on Technologies for Chinese Medicine Pharmaceutical Process Control and Intelligent Manufacture(中药制药过程控制与智能制造技术国家重点实验室);Zhejiang Lab(浙江实验室)