English
Related papers

Related papers: Language Model Circuits Are Sparse in the Neuron B…

200 papers

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models.…

Machine Learning · Computer Science 2025-07-14 Stepan Shabalin , Ayush Panda , Dmitrii Kharlapenko , Abdur Raheem Ali , Yixiong Hao , Arthur Conmy

Sparse dictionary learning (and, in particular, sparse autoencoders) attempts to learn a set of human-understandable concepts that can explain variation on an abstract space. A basic limitation of this approach is that it neither exploits…

Computation and Language · Computer Science 2025-06-03 Mark Muchane , Sean Richardson , Kiho Park , Victor Veitch

We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. We demonstrate our model-agnostic approach with the Transformer English-German translation model. We…

Computation and Language · Computer Science 2022-11-04 Gal Patel , Leshem Choshen , Omri Abend

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Zhenyu Lu , Liupeng Li , Jinpeng Wang , Haoqian Kang , Yan Feng , Ke Chen , Yaowei Wang

Building systems that achieve a deeper understanding of language is one of the central goals of natural language processing (NLP). Towards this goal, recent works have begun to train language models on narrative datasets which require…

Computation and Language · Computer Science 2023-03-02 Khai Loong Aw , Mariya Toneva

Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (e.g. backtracking, cross-verification) during reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are…

Artificial Intelligence · Computer Science 2026-01-08 Yi Fang , Wenjie Wang , Mingfeng Xue , Boyi Deng , Fengli Xu , Dayiheng Liu , Fuli Feng

While a lot of analysis has been carried to demonstrate linguistic knowledge captured by the representations learned within deep NLP models, very little attention has been paid towards individual neurons.We carry outa neuron-level analysis…

Computation and Language · Computer Science 2020-10-07 Nadir Durrani , Hassan Sajjad , Fahim Dalvi , Yonatan Belinkov

Current distributed representations of words show little resemblance to theories of lexical semantics. The former are dense and uninterpretable, the latter largely based on familiar, discrete classes (e.g., supersenses) and relations (e.g.,…

Computation and Language · Computer Science 2015-06-08 Manaal Faruqui , Yulia Tsvetkov , Dani Yogatama , Chris Dyer , Noah Smith

Following the general theoretical framework of VSA (Vector Symbolic Architecture), a cognitive model with the use of sparse binary hypervectors is proposed. In addition, learning algorithms are introduced to bootstrap the model from…

Artificial Intelligence · Computer Science 2023-10-31 Zhonghao Yang

Ambiguity is pervasive in real-world questions, yet large language models (LLMs) often respond with confident answers rather than seeking clarification. In this work, we show that question ambiguity is linearly encoded in the internal…

Computation and Language · Computer Science 2025-09-18 Zhuoxuan Zhang , Jinhao Duan , Edward Kim , Kaidi Xu

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

Vision-language models encode images and text in a joint space, minimizing the distance between corresponding image and text pairs. How are language and images organized in this joint space, and how do the models encode meaning and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Isabel Papadimitriou , Huangyuan Su , Thomas Fel , Sham Kakade , Stephanie Gil

Sequence-to-sequence models are a powerful workhorse of NLP. Most variants employ a softmax transformation in both their attention mechanism and output layer, leading to dense alignments and strictly positive output probabilities. This…

Computation and Language · Computer Science 2019-06-14 Ben Peters , Vlad Niculae , André F. T. Martins

The fidelity with which neural networks can now generate content such as music presents a scientific opportunity: these systems appear to have learned implicit theories of such content's structure through statistical learning alone. This…

Sound · Computer Science 2026-03-03 Nikhil Singh , Manuel Cherep , Pattie Maes

We investigate whether sparse autoencoders (SAEs) can be used to remove knowledge from language models. We use the biology subset of the Weapons of Mass Destruction Proxy dataset and test on the gemma-2b-it and gemma-2-2b-it language…

Machine Learning · Computer Science 2024-11-05 Eoin Farrell , Yeu-Tong Lau , Arthur Conmy

Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…

Artificial Intelligence · Computer Science 2025-11-12 Dengcan Liu , Jiahao Li , Zheren Fu , Yi Tu , Jiajun Li , Zhendong Mao , Yongdong Zhang

Sparse autoencoders (SAEs) are a promising technique for decomposing language model activations into interpretable linear features. However, current SAEs fall short of completely explaining model performance, resulting in "dark matter":…

Machine Learning · Computer Science 2025-03-26 Joshua Engels , Logan Riggs , Max Tegmark

Large language models (LLMs) exhibit substantial performance disparities across languages, particularly between high- and low-resource settings. We propose a framework for improving performance in underrepresented languages while preserving…

Computation and Language · Computer Science 2026-02-05 Daniil Gurgurov , Tanja Baeumel , Josef van Genabith , Simon Ostermann

Large Language Models (LLMs) have been shown to be effective models of the human language system, with some models predicting most explainable variance of brain activity in current datasets. Even in untrained models, the representations…

Computation and Language · Computer Science 2024-06-24 Badr AlKhamissi , Greta Tuckute , Antoine Bosselut , Martin Schrimpf

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting neural networks by extracting the concepts represented in their activations. However, choosing the size of the SAE dictionary (i.e. number of learned concepts)…

Machine Learning · Computer Science 2025-03-25 Bart Bussmann , Noa Nabeshima , Adam Karvonen , Neel Nanda