Concept guidance has emerged as a cheap and simple way to control the behavior of language models by probing their hidden representations for concept vectors and using them to perturb activations at inference time. While the focus of previous work has largely been on truthfulness, in this paper we extend this framework to a richer set of concepts such as appropriateness, humor, creativity and quality, and explore to what degree current detection and guidance strategies work in these challenging settings. To facilitate evaluation, we develop a novel metric for concept guidance that takes into account both the success of concept elicitation as well as the potential degradation in fluency of the guided model. Our extensive experiments reveal that while some concepts such as truthfulness more easily allow for guidance with current techniques, novel concepts such as appropriateness or humor either remain difficult to elicit, need extensive tuning to work, or even experience confusion. Moreover, we find that probes with optimal detection accuracies do not necessarily make for the optimal guides, contradicting previous observations for truthfulness. Our work warrants a deeper investigation into the interplay between detectability, guidability, and the nature of the concept, and we hope that our rich experimental test-bed for guidance research inspires stronger follow-up approaches.
Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance
NAIST(日本国立信息与科技研究所);NII LLMC(日本信息处理学会大语言模型中心);MBZUAI(微软亚洲人工智能研究院);RIKEN(日本研究机构);Tohoku University(东北大学);The University of Tokyo(东京大学);Nagoya Institute of Technology(名古屋技术大学)
TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention
Drexel University(德雷塞尔大学);University of Electronic Science and Technology of China(电子科技大学);Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));LLNL(劳伦斯利弗莫尔国家实验室);Lehigh University(莱斯大学)
Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts
Department of Computer Science and Engineering, The Ohio State University, USA(计算机科学与工程系,俄亥俄州立大学);Department of Biomedical Informatics, The Ohio State University, USA(生物医学信息学系,俄亥俄州立大学);Translational Data Analytics Institute, The Ohio State University, USA(转化数据分析研究所,俄亥俄州立大学)
3M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation
Artificial Intelligence Research Laboratory(人工智能研究实验室);College of Information Sciences and Technology(信息科学与技术学院);Center for Artificial Intelligence Foundations and Scientific Applications(人工智能基础与科学应用中心);Institute for Computational and Data Sciences(计算与数据科学研究所);The Pennsylvania State University(宾夕法尼亚州立大学)