English
Related papers

Related papers: Sparse Activation Editing for Reliable Instruction…

200 papers

An interactive instruction following task has been proposed as a benchmark for learning to map natural language instructions and first-person vision into sequences of actions to interact with objects in 3D environments. We found that an…

Artificial Intelligence · Computer Science 2022-11-16 Kazutoshi Shinoda , Yuki Takezawa , Masahiro Suzuki , Yusuke Iwasawa , Yutaka Matsuo

Sparse Autoencoders (SAEs) have emerged as a powerful framework for machine learning interpretability, enabling the unsupervised decomposition of model representations into a dictionary of abstract, human-interpretable concepts. However, we…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Thomas Fel , Ekdeep Singh Lubana , Jacob S. Prince , Matthew Kowal , Victor Boutin , Isabel Papadimitriou , Binxu Wang , Martin Wattenberg , Demba Ba , Talia Konkle

The Transformer architecture, despite its widespread success, struggles with long-context scenarios due to quadratic computation and linear memory growth. While various linear attention variants mitigate these efficiency constraints by…

Machine Learning · Computer Science 2025-10-02 Yuqi Pan , Yongqi An , Zheng Li , Yuhong Chou , Ruijie Zhu , Xiaohui Wang , Mingxuan Wang , Jinqiao Wang , Guoqi Li

Modern Language Models (LMs) are capable of following long and complex instructions that enable a large and diverse set of user requests. While Information Retrieval (IR) models use these LMs as the backbone of their architectures,…

Information Retrieval · Computer Science 2024-05-08 Orion Weller , Benjamin Chang , Sean MacAvaney , Kyle Lo , Arman Cohan , Benjamin Van Durme , Dawn Lawrie , Luca Soldaini

Supervised learning has traditionally focused on inductive learning by observing labeled examples of a task. In contrast, humans have the ability to learn new concepts from language. Here, we explore training zero-shot classifiers for…

Computation and Language · Computer Science 2022-04-15 Rakesh R Menon , Sayan Ghosh , Shashank Srivastava

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

Machine Learning · Computer Science 2026-05-19 Michał Brzozowski , Neo Christopher Chung

Standard Sparse Autoencoders (SAEs) excel at discovering a dictionary of a model's learned features, offering a powerful observational lens. However, the ambiguous and ungrounded nature of these features makes them unreliable instruments…

Machine Learning · Computer Science 2025-09-29 Jianrong Ding , Muxi Chen , Chenchen Zhao , Qiang Xu

Sparse autoencoders (SAEs) are a promising unsupervised approach for identifying causally relevant and interpretable linear features in a language model's (LM) activations. To be useful for downstream tasks, SAEs need to decompose LM…

Machine Learning · Computer Science 2024-08-02 Senthooran Rajamanoharan , Tom Lieberum , Nicolas Sonnerat , Arthur Conmy , Vikrant Varma , János Kramár , Neel Nanda

Despite widespread deployment of Large Language Models, systematic evaluation of instruction-following capabilities remains challenging. While comprehensive benchmarks exist, focused assessments that quickly diagnose specific instruction…

Computation and Language · Computer Science 2025-10-23 Richard J. Young , Brandon Gillins , Alice M. Matthews

Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data. Current methods often rely on costly LLM-based techniques (e.g.…

Artificial Intelligence · Computer Science 2025-12-12 Nick Jiang , Xiaoqing Sun , Lisa Dunlap , Lewis Smith , Neel Nanda

Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary that reconstructs a network's internal activations, have been…

Machine Learning · Computer Science 2024-05-27 Dan Braun , Jordan Taylor , Nicholas Goldowsky-Dill , Lee Sharkey

Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these models to improve downstream performance often degrades robustness against distribution…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Fabian Morelli , Arnas Uselis , Ankit Sonthalia , Seong Joon Oh

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

Recent work shows that in-context learning and optimization of in-context examples (ICE) can significantly improve the accuracy of large language models (LLMs) on a wide range of tasks, leading to an apparent consensus that ICE optimization…

Computation and Language · Computer Science 2024-06-07 Pragya Srivastava , Satvik Golechha , Amit Deshpande , Amit Sharma

Retriever-augmented instruction-following models are attractive alternatives to fine-tuned approaches for information-seeking tasks such as question answering (QA). By simply prepending retrieved documents in its input along with an…

Computation and Language · Computer Science 2024-04-18 Vaibhav Adlakha , Parishad BehnamGhader , Xing Han Lu , Nicholas Meade , Siva Reddy

Existing instruction-based image editing models perform well with simple, single-step instructions but degrade in realistic scenarios that involve multiple, lengthy, and interdependent directives. A main cause is the scarcity of training…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Zhaoyuan Qiu , Ken Chen , Xiangwei Wang , Yu Xia , Sachith Seneviratne , Saman Halgamuge

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

Machine Learning · Computer Science 2025-10-10 Yifei Yao , Mengnan Du

Academic benchmarks for coding agents tend to reward autonomous task completion, measured by verifiable rewards such as unit-test success. In contrast, real-world coding agents operate with humans in the loop, where success signals are…

Artificial Intelligence · Computer Science 2026-03-05 Xingyao Wang , Valerie Chen , Heng Ji , Graham Neubig

Fully supervised semantic segmentation learns from dense masks, which requires heavy annotation cost for closed set. In this paper, we use natural language as supervision without any pixel-level annotation for open world segmentation. We…

Computer Vision and Pattern Recognition · Computer Science 2022-12-15 Yi Li , Huifeng Yao , Hualiang Wang , Xiaomeng Li

Instruction tuning has become a foundation for unlocking the capabilities of large-scale pretrained models and improving their performance on complex tasks. Thus, the construction of high-quality instruction datasets is crucial for…

Artificial Intelligence · Computer Science 2026-02-12 Li Du , Hanyu Zhao , Yiming Ju , Tengfei Pan