English
Related papers

Related papers: Sparse Autoencoders Reveal Temporal Difference Lea…

200 papers

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Machine Learning · Computer Science 2024-05-01 Senthooran Rajamanoharan , Arthur Conmy , Lewis Smith , Tom Lieberum , Vikrant Varma , János Kramár , Rohin Shah , Neel Nanda

We study the phenomenon of \textit{in-context learning} (ICL) exhibited by large language models, where they can adapt to a new learning task, given a handful of labeled examples, without any explicit parameter optimization. Our goal is to…

Machine Learning · Computer Science 2023-05-29 Jacob Abernethy , Alekh Agarwal , Teodor V. Marinov , Manfred K. Warmuth

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most…

Machine Learning · Computer Science 2025-07-14 Gonçalo Paulo , Nora Belrose

Large Language Models (LLMs) are machine learning models that have seen widespread adoption due to their capability of handling previously difficult tasks. LLMs, due to their training, are sensitive to how exactly a question is presented,…

Software Engineering · Computer Science 2025-12-22 Jae Yong Lee , Sungmin Kang , Shin Yoo

SAEs have recently been employed as a promising unsupervised approach for understanding the representations of layers of Large Language Models (LLMs). However, with the growth in model size and complexity, training SAEs is computationally…

Computation and Language · Computer Science 2025-09-23 Davide Ghilardi , Federico Belotti , Marco Molinari , Tao Ma , Matteo Palmonari

Sparse autoencoders (SAEs) enable feature-level mechanistic interpretability and activation steering in large language models (LLMs), but SAE-based language control remains unreliable in multilingual settings: most SAEs are trained on…

Computation and Language · Computer Science 2026-05-25 Yusser Al Ghussin , Daniil Gurgurov , Tanja Baeumel , Josef van Genabith , Patrick Schramowski , Simon Ostermann

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most…

Computation and Language · Computer Science 2025-10-24 Agam Goyal , Vedant Rathi , William Yeh , Yian Wang , Yuen Chen , Hari Sundaram

Traditional topic models are effective at uncovering latent themes in large text collections. However, due to their reliance on bag-of-words representations, they struggle to capture semantically abstract features. While some neural…

Computation and Language · Computer Science 2025-08-01 Carolina Zheng , Nicolas Beltran-Velez , Sweta Karlekar , Claudia Shi , Achille Nazaret , Asif Mallik , Amir Feder , David M. Blei

Time series modeling holds significant importance in many real-world applications and has been extensively studied. While pre-trained foundation models have made impressive strides in the fields of natural language processing (NLP) and…

Computation and Language · Computer Science 2025-02-20 Juyuan Zhang , Wei Zhu , Jiechao Gao

The evaluation of large language models (LLMs) relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics for a given capability, but those aggregated metrics can obscure (i) particular sub-areas where the…

Computation and Language · Computer Science 2025-12-25 Matyas Bohacek , Nino Scherrer , Nicholas Dufour , Thomas Leung , Christoph Bregler , Stephanie C. Y. Chan

In recent years, Large Language Models (LLMs) have garnered significant attention from the research community due to their exceptional performance and generalization capabilities. In this paper, we introduce a novel method for…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-21 Egor Lakomkin , Chunyang Wu , Yassir Fathullah , Ozlem Kalinli , Michael L. Seltzer , Christian Fuegen

In order to understand the in-context learning phenomenon, recent works have adopted a stylized experimental framework and demonstrated that Transformers can learn gradient-based learning algorithms for various classes of real-valued…

Machine Learning · Computer Science 2023-10-05 Satwik Bhattamishra , Arkil Patel , Phil Blunsom , Varun Kanade

Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the effectiveness of in-context learning is heavily reliant on the…

Computation and Language · Computer Science 2024-01-29 Liang Wang , Nan Yang , Furu Wei

Large language models (LLMs) can learn from a few demonstrations provided at inference time. We study this in-context learning phenomenon through the lens of Gaussian Processes (GPs). We build controlled experiments where models observe…

Machine Learning · Computer Science 2026-02-13 Elif Akata , Konstantinos Voudouris , Vincent Fortuin , Eric Schulz

Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically rely solely on…

Machine Learning · Computer Science 2025-09-24 Dong Shu , Xuansheng Wu , Haiyan Zhao , Mengnan Du , Ninghao Liu

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

Sound · Computer Science 2025-10-07 Takashi Maekaku , Keita Goto , Jinchuan Tian , Yusuke Shinohara , Shinji Watanabe

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence due to catastrophic forgetting. Large language models (LLMs) are often impractical to frequent…

Machine Learning · Computer Science 2025-10-28 Jaya Krishna Mandivarapu

Sparse autoencoders (SAEs) are commonly used to interpret the internal activations of large language models (LLMs) by mapping them to human-interpretable concept representations. While existing evaluations of SAEs focus on metrics such as…

Machine Learning · Computer Science 2026-01-26 Aaron J. Li , Suraj Srinivas , Usha Bhalla , Himabindu Lakkaraju

Low-resource languages pose a challenge for machine translation with large language models (LLMs), which require large amounts of training data. One potential way to circumvent this data dependence is to rely on LLMs' ability to use…

Computation and Language · Computer Science 2026-04-09 Jackson Petty , Jaulie Goe , Tal Linzen

Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier goals of artificial intelligence research: creating an artificial system that can adapt its…

Computation and Language · Computer Science 2026-05-04 Michael A. Lepori , Tal Linzen , Ann Yuan , Katja Filippova