Causal interventions in language model representations have largely targeted discrete features, like grammatical number. However, language models must also make use of features that are graded. We introduce a method for causal intervention on continuous variables: given activation vectors paired with a graded target variable, we localize a low-dimensional direction for that variable and use this direction to edit a vectors toward counterfactual target values. We apply this method to a continuous feature that is well-studied in psycholinguistics, namely verb bias (which reflects which syntactic structures tend to follow a given verb). We show that verb bias is causally represented in steering vectors extracted from large language models: counterfactual edits to verb bias systematically shift downstream structural preferences. Verb bias has also previously been linked to in-context learning; in further analyses, we find that steering vectors encode error signals that could drive the error-driven update behavior seen in in-context learning but that these aspects of the steering vectors are not causally used in downstream production. Overall, these results show causal interventions can be applied to continuous variables, though connecting continuous variables to in-context learning remains a challenge.
MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation
School of Computer Science and Engineering, UNSW Sydney(悉尼新南威尔士大学计算机科学与工程学院);ARC Centre of Excellence for Automated Decision-Making and Society (ADM+S)(澳大利亚研究理事会自动化决策与社会卓越中心);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models
Department of Informatics, Universität Hamburg(汉堡大学信息学院);The University of Sydney(悉尼大学);Alibaba International Digital Commerce(阿里巴巴国际数字商业);Institute of Psychology, Chinese Academy of Sciences(中国科学院心理研究所)
Compositional Multilingual and Behavioral Attribute Steering
German Research Centre for Artificial Intelligence (DFKI)(德国人工智能研究中心);Saarland University(萨尔大学);Centre for European Research in Trusted AI (CERTAIN)(欧洲可信人工智能研究中心)
VIS Lab, University of Amsterdam(阿姆斯特丹大学VIS实验室);FunAI Lab, University of Technology Nuremberg(纽伦堡技术大学FunAI实验室);CSAIL, Massachusetts Institute of Technology(麻省理工学院计算机科学与人工智能实验室)
Reflection Steering: Disentangling Reflection from Reasoning in Activation Space for Token-Efficient Inference
School of Computing and Data Science, The University of Hong Kong(香港大学计算与数据科学学院);Department of Computing, The Hong Kong Polytechnic University(香港理工大学计算学院);School of Data Science, Lingnan University(岭南大学数据科学学院);Centre for Learning, Teaching and Technology, The Education University of Hong Kong(香港教育大学学习、教学与技术中心)
Northeastern University(东北大学);Washington University in St. Louis(圣路易斯华盛顿大学);Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Tsinghua University(清华大学);Security Capability Center(360安全能力中心);Tencent(腾讯);Beijing University of Posts and Telecommunications(北京邮电大学)
Fine-Grained Activation Steering: Steering Less, Achieving More
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore(电子与电气工程学院,南洋理工大学,新加坡);Home Team Science and Technology Agency (HTX), Singapore(家庭团队科技局(HTX),新加坡)
On the Limitations of Steering in Language Model Alignment
Birla Institute of Technology and Science Pilani(比拉理工科学与 Pilani 学院);National University of Singapore(新加坡国立大学);Institute for Data Science, National University of Singapore(新加坡国立大学数据科学研究院)