English
Related papers

Related papers: Conceptors for Semantic Steering

200 papers

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…

Computation and Language · Computer Science 2026-02-23 Joschka Braun

The opaque nature of Large Language Models (LLMs) has led to significant research efforts aimed at enhancing their interpretability, primarily through post-hoc methods. More recent in-hoc approaches, such as Concept Bottleneck Models…

Machine Learning · Computer Science 2025-02-20 Or Raphael Bidusa , Shaul Markovitch

We introduce Conceptual Metaphor Theory (CMT) as a framework for enhancing large language models (LLMs) through cognitive prompting in complex reasoning tasks. CMT leverages metaphorical mappings to structure abstract reasoning, improving…

Computation and Language · Computer Science 2025-02-05 Oliver Kramer

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

Machine Learning · Computer Science 2026-02-04 Magamed Taimeskhanov , Samuel Vaiter , Damien Garreau

Spaced repetition systems are fundamental to efficient learning and memory retention, but existing algorithms often struggle with semantic interference and personalized adaptation. We present LECTOR (\textbf{L}LM-\textbf{E}nhanced…

Computation and Language · Computer Science 2025-08-06 Jiahao Zhao

Semantic representations can be framed as a structured, dynamic knowledge space through which humans navigate to retrieve and manipulate meaning. To investigate how humans traverse this geometry, we introduce a framework that represents…

Computation and Language · Computer Science 2026-04-15 Felipe D. Toro-Hernández , Jesuino Vieira Filho , Rodrigo M. Cabral-Carvalho

Despite significant advances in quality and complexity of the generations in text-to-image models, prompting does not always lead to the desired outputs. Controlling model behaviour by directly steering intermediate model activations has…

Machine Learning · Computer Science 2025-05-27 Marta Aparicio Rodriguez , Xenia Miscouridou , Anastasia Borovykh

Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in downstream steering tasks is limited by the requirement for contrastive datasets or large…

Computation and Language · Computer Science 2026-05-05 Seonglae Cho , Zekun Wu , Adriano Koshiyama

Steering methods have emerged as effective and targeted tools for guiding large language models' (LLMs) behavior without modifying their parameters. Multimodal large language models (MLLMs), however, do not currently enjoy the same suite of…

Machine Learning · Computer Science 2025-05-21 Woody Haosheng Gan , Deqing Fu , Julian Asilis , Ollie Liu , Dani Yogatama , Vatsal Sharan , Robin Jia , Willie Neiswanger

Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less…

Machine Learning · Computer Science 2023-11-09 Jinyung Hong , Keun Hee Park , Theodore P. Pavlic

Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating…

Artificial Intelligence · Computer Science 2026-05-11 Aayush Mishra , Daniel Khashabi , Anqi Liu

The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long tail scenarios. However, these models…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Nikos Theodoridis , Reenu Mohandas , Ganesh Sistu , Anthony Scanlan , Ciarán Eising , Tim Brophy

Navigating in search and rescue environments is challenging, since a variety of terrains has to be considered. Hybrid driving-stepping locomotion, as provided by our robot Momaro, is a promising approach. Similar to other locomotion…

Robotics · Computer Science 2018-09-20 Tobias Klamt , Sven Behnke

Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations. However, for any human-interpretable concept, how can we find its direction in the latent space? We present a…

Computation and Language · Computer Science 2024-04-02 David Chanin , Anthony Hunter , Oana-Maria Camburu

Transformer-based language models exhibit complex and distributed behavior, yet their internal computations remain poorly understood. Existing mechanistic interpretability methods typically treat attention heads and multilayer perceptron…

Machine Learning · Computer Science 2025-11-26 Areeb Ahmad , Abhinav Joshi , Ashutosh Modi

Interpretability is a crucial factor in building reliable models for various medical applications. Concept Bottleneck Models (CBMs) enable interpretable image classification by utilizing human-understandable concepts as intermediate…

Computer Vision and Pattern Recognition · Computer Science 2023-08-24 Injae Kim , Jongha Kim , Joonmyung Choi , Hyunwoo J. Kim

Despite extensive research on sliding mode control (SMC) design for quadrotors, the existing approaches suffer from certain limitations. Euler angle-based SMC formulations suffer from poor performance in high-pitch or -roll maneuvers.…

Robotics · Computer Science 2025-12-04 Amin Yazdanshenas , Reza Faieghi

Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning tasks based on a set of human-understandable concepts.…

Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with adversarial multimodal inputs. To improve the safety of…

Computation and Language · Computer Science 2025-09-24 Lyucheng Wu , Mengru Wang , Ziwen Xu , Tri Cao , Nay Oo , Bryan Hooi , Shumin Deng

Concept Bottleneck Models (CBMs) have become a popular approach to enable interpretability in neural networks by constraining classifier inputs to a set of human-understandable concepts. While effective, current models embed concepts in…

Machine Learning · Computer Science 2026-05-13 Daniel Uyterlinde , Swasti Shreya Mishra , Pascal Mettes