English
Related papers

Related papers: Interpretable LLM Guardrails via Sparse Representa…

200 papers

Large Language Models (LLMs) exhibit remarkable capabilities across various tasks, yet guiding them to follow desired behaviours during inference remains a significant challenge. Activation steering offers a promising method to control the…

Computation and Language · Computer Science 2025-09-29 Weixuan Wang , Minghao Wu , Barry Haddow , Alexandra Birch

We introduce SteeringSafety, a systematic framework for evaluating representation steering methods across seven safety perspectives spanning 17 datasets. While prior work highlights general capabilities of representation steering, we…

Artificial Intelligence · Computer Science 2025-10-17 Vincent Siu , Nicholas Crispino , David Park , Nathan W. Henry , Zhun Wang , Yang Liu , Dawn Song , Chenguang Wang

Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, however, often rely on non-anticipative interventions that…

Machine Learning · Computer Science 2026-04-22 Julian Skifstad , Xinyue Annie Yang , Glen Chou

Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires learned features to be both interpretable and…

Machine Learning · Computer Science 2026-04-01 Akshay Kulkarni , Tsui-Wei Weng , Vivek Narayanaswamy , Shusen Liu , Wesam A. Sakla , Kowshik Thopalli

The transformative impact of large language models (LLMs) like LLaMA and GPT on natural language processing is countered by their prohibitive computational demands. Pruning has emerged as a pivotal compression strategy, introducing sparsity…

Computation and Language · Computer Science 2024-11-04 Guangji Bai , Yijiang Li , Chen Ling , Kibaek Kim , Liang Zhao

The complexity of the real world demands robotic systems that can intelligently adapt to unseen situations. We present STEER, a robot learning framework that bridges high-level, commonsense reasoning with precise, flexible low-level…

Large language models (LLMs) have achieved remarkable success across various tasks but face deployment challenges due to their massive computational demands. While post-training pruning methods like SparseGPT and Wanda can effectively…

Artificial Intelligence · Computer Science 2026-04-21 Qiao Xiao , Alan Ansell , Boqian Wu , Lu Yin , Mykola Pechenizkiy , Shiwei Liu , Decebal Constantin Mocanu

Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant challenge. We introduce a suite of 256 SAEs, trained on each…

Recent advancements in large language models (LLMs) have resulted in increasingly anthropomorphic language concerning the ability of LLMs to reason. Whether reasoning in LLMs should be understood to be inherently different is, however,…

Machine Learning · Computer Science 2025-07-28 Bertram Højer , Oliver Jarvis , Stefan Heinrich

Large Language Models (LLMs) hold immense potential to generate synthetic data of high quality and utility, which has numerous applications from downstream model training to practical data utilisation. However, contemporary models, despite…

Computation and Language · Computer Science 2023-08-21 Charles O'Neill , Yuan-Sen Ting , Ioana Ciuca , Jack Miller , Thang Bui

Sparse Autoencoders (SAEs) have emerged as a powerful paradigm for disentangling feature superposition in transformer-based architectures, enabling precise control via activation steering. However, the theoretical foundations of…

Machine Learning · Computer Science 2026-05-08 Yunpeng Zhou

Large language models (LLMs) excel at diverse tasks, but their deployment on resource-constrained devices remains challenging. Existing methods like quantization, pruning, and distillation can reduce memory footprint but often demand…

Artificial Intelligence · Computer Science 2025-12-23 Siddharth Tandon

Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, where plausible arguments are incorrectly deemed logically…

Artificial Intelligence · Computer Science 2026-04-02 Marco Valentino , Geonhee Kim , Dhairya Dalal , Zhixue Zhao , André Freitas

This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Anushka Sivakumar , Andrew Zhang , Zaber Hakim , Chris Thomas

Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to interpret their…

Machine Learning · Computer Science 2024-11-04 Yihao Zhang , Zeming Wei , Jun Sun , Meng Sun

Large Language Models (LLMs) exhibit a significant "embodiment gap", where their text-based representations fail to align with human sensorimotor experiences. This study systematically investigates whether and how task-specific fine-tuning…

Computation and Language · Computer Science 2026-03-05 Minghua Wu , Javier Conde , Pedro Reviriego , Marc Brysbaert

Many large-scale systems rely on high-quality deep representations (embeddings) to facilitate tasks like retrieval, search, and generative modeling. Matryoshka Representation Learning (MRL) recently emerged as a solution for adaptive…

Machine Learning · Computer Science 2025-05-21 Tiansheng Wen , Yifei Wang , Zequn Zeng , Zhong Peng , Yudi Su , Xinyang Liu , Bo Chen , Hongwei Liu , Stefanie Jegelka , Chenyu You

Language models play a central role in automatic speech recognition (ASR), yet most methods rely on text-only models unaware of ASR error patterns. Recently, large language models (LLMs) have been applied to ASR correction, but introduce…

Machine Learning · Computer Science 2026-03-18 Zijin Gu , Tatiana Likhomanenko , He Bai , Erik McDermott , Ronan Collobert , Navdeep Jaitly

Dictionary learning and sparse representation (DLSR) is a recent and successful mathematical model for data representation that achieves state-of-the-art performance in various fields such as pattern recognition, machine learning, computer…

Computer Vision and Pattern Recognition · Computer Science 2015-02-23 Mehrdad J. Gangeh , Ahmed K. Farahat , Ali Ghodsi , Mohamed S. Kamel

Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward desired behaviors while avoiding retraining. Despite their…

Machine Learning · Computer Science 2026-01-13 Shawn Im , Sharon Li