English
Related papers

Related papers: Concept Heterogeneity-aware Representation Steerin…

200 papers

Model steering represents a powerful technique that dynamically aligns large language models (LLMs) with human preferences during inference. However, conventional model-steering methods rely heavily on externally annotated data, not only…

Computation and Language · Computer Science 2025-07-15 Rongyi Zhu , Yuhui Wang , Tanqiu Jiang , Jiacheng Liang , Ting Wang

Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating defenses that are both generalizable to novel threats and efficient for practical deployment. Many current strategies fall…

Cryptography and Security · Computer Science 2026-04-21 Peichun Hua , Hao Li , Shanghao Shi , Zhiyuan Yu , Ning Zhang

Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels. However, heterophily has been largely ignored, despite its ubiquitous…

Machine Learning · Computer Science 2025-02-05 Zhixiang Shen , Zhao Kang

Large language models (LLMs) often encode cognitive behaviors unpredictably across prompts, layers, and contexts, making them difficult to diagnose and control. We present CBMAS, a diagnostic framework for continuous activation steering,…

Artificial Intelligence · Computer Science 2026-01-13 Ahmed H. Ismail , Anthony Kuang , Ayo Akinkugbe , Kevin Zhu , Sean O'Brien

Travel behavior prediction is a core problem in transportation demand management and is traditionally addressed using numerical models calibrated on observed data. With recent advances in large language models (LLMs), new opportunities have…

Machine Learning · Computer Science 2026-03-12 Baichuan Mo , Hanyong Xu , Ruoyun Ma , Jung-Hoon Cho , Dingyi Zhuang , Xiaotong Guo , Jinhua Zhao

Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning. However, by adapting strong optimization objectives from fine-tuning, current methods are susceptible to overfitting and…

Machine Learning · Computer Science 2026-03-17 Yuntai Bao , Xuhong Zhang , Jintao Chen , Ge Su , Yuxiang Cai , Hao Peng , Bing Sun , Haiqin Weng , Liu Yan , Jianwei Yin

Large Language Models (LLMs) encode meanings of words in the form of distributed semantics. Distributed semantics capture common statistical patterns among language tokens (words, phrases, and sentences) from large amounts of data. LLMs…

Computation and Language · Computer Science 2023-06-27 Yuxin Zi , Kaushik Roy , Vignesh Narayanan , Manas Gaur , Amit Sheth

Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights. However, most…

Computation and Language · Computer Science 2025-07-25 Duy Nguyen , Archiki Prasad , Elias Stengel-Eskin , Mohit Bansal

Pretrained language models (PLMs) like BERT provide strong semantic representations but are costly and opaque, while symbolic models such as the Tsetlin Machine (TM) offer transparency but lack semantic generalization. We propose a semantic…

Computation and Language · Computer Science 2026-04-15 Jiechao Gao , Rohan Kumar Yadav , Yuangang Li , Yuandong Pan , Jie Wang , Ying Liu , Michael Lepech

Conditional dependency present one of the trickiest problems in Compositional Zero-Shot Learning, leading to significant property variations of the same state (object) across different objects (states). To address this problem, existing…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Zhijie Rao , Jingcai Guo , Miaoge Li , Yang Chen

Object hallucination remains a primary obstacle to the reliable deployment of Multimodal Large Language Models (MLLMs). Current inference-time mitigation methods mainly assume hallucinations stem from visual neglect, steering models to…

Computation and Language · Computer Science 2026-05-28 Jingwen Wu , Xijun Zhang , Ge Song

Direction reasoning is essential for intelligent systems to understand the real world. While existing work focuses primarily on spatial reasoning, compass direction reasoning remains underexplored. To address this, we propose the Compass…

Artificial Intelligence · Computer Science 2024-12-24 Hang Yin , Zhifeng Lin , Xin Liu , Bin Sun , Kan Li

Current evaluations of Large Language Model (LLM) steering techniques focus on task-specific performance, overlooking how well steered representations align with human cognition. Using a well-established triadic similarity judgment task, we…

Artificial Intelligence · Computer Science 2025-05-27 Zach Studdiford , Timothy T. Rogers , Siddharth Suresh , Kushin Mukherjee

Agent-based models (ABMs) have shown promise for modelling various real world phenomena incompatible with traditional equilibrium analysis. However, a critical concern is the manual definition of behavioural rules in ABMs. Recent…

Multiagent Systems · Computer Science 2024-02-02 Benjamin Patrick Evans , Sumitra Ganesh

The ability to steer AI behavior is crucial to preventing its long term dangerous and catastrophic potential. Representation Engineering (RepE) has emerged as a novel, powerful method to steer internal model behaviors, such as "honesty", at…

Machine Learning · Computer Science 2024-10-10 Akshat Kannan

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal…

Artificial Intelligence · Computer Science 2026-04-03 Fan Huang , Songheng Zhang , Haewoon Kwak , Jisun An

Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal…

Artificial Intelligence · Computer Science 2026-02-04 Eric Yang , Jong Ha Lee , Jonathan Amar , Elissa Ye , Yugang Jia

The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, recent works have proposed to control…

Machine Learning · Computer Science 2024-11-25 Pau Rodriguez , Arno Blaas , Michal Klein , Luca Zappella , Nicholas Apostoloff , Marco Cuturi , Xavier Suau

Features of the same sample generated by different pretrained models often exhibit inherently distinct feature distributions because of discrepancies in the model pretraining objectives or architectures. Learning invariant representations…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Jie Chen , Zhu Wang , Chuanbin Liu , Xi Peng

Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration. Yet, offline RL's performance often hinges on a brittle trade-off between (1) return maximization, which can push policies outside…

Robotics · Computer Science 2026-03-06 Hokyun Im , Andrey Kolobov , Jianlong Fu , Youngwoon Lee