English
Related papers

Related papers: Tracking the Feature Dynamics in LLM Training: A M…

200 papers

Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…

Computation and Language · Computer Science 2026-02-27 Usha Bhalla , Alex Oesterling , Claudio Mayrink Verdun , Himabindu Lakkaraju , Flavio P. Calmon

Feature engineering is of critical importance in the field of Data Science. While any data scientist knows the importance of rigorously preparing data to obtain good performing models, only scarce literature formalizes its benefits. In this…

Methodology · Statistics 2023-06-30 Florian Felice , Christophe Ley , Andreas Groll , Stéphane Bordas

Change detection is a fundamental task in computer vision that processes a bi-temporal image pair to differentiate between semantically altered and unaltered regions. Large language models (LLMs) have been utilized in various domains for…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Zhenglin Li , Yangchen Huang , Mengran Zhu , Jingyu Zhang , JingHao Chang , Houze Liu

This paper provides a survey of the emerging area of Large Language Models (LLMs) for Software Engineering (SE). It also sets out open research challenges for the application of LLMs to technical problems faced by software engineers. LLMs'…

Software Engineering · Computer Science 2023-11-14 Angela Fan , Beliz Gokkaya , Mark Harman , Mitya Lyubarskiy , Shubho Sengupta , Shin Yoo , Jie M. Zhang

To control the behavior of language models, steering methods attempt to ensure that outputs of the model satisfy specific pre-defined properties. Adding steering vectors to the model is a promising method of model control that is easier…

Machine Learning · Computer Science 2024-11-22 Sviatoslav Chalnev , Matthew Siu , Arthur Conmy

Sparse Autoencoder (SAE) features have become essential tools for mechanistic interpretability research. SAE features are typically characterized by examining their activating examples, which are often "monosemantic" and align with human…

Artificial Intelligence · Computer Science 2025-09-30 Claire Tian , Katherine Tian , Nathan Hu

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

Quantitative Methods · Quantitative Biology 2026-01-21 Xiangyu Liu , Haodi Lei , Yi Liu , Yang Liu , Wei Hu

Sparse autoencoders (SAEs) model the activations of a neural network as linear combinations of sparsely occurring directions of variation (latents). The ability of SAEs to reconstruct activations follows scaling laws w.r.t. the number of…

Machine Learning · Computer Science 2025-09-05 Eric J. Michaud , Liv Gorton , Tom McGrath

Dynamical systems theory provides a framework for analyzing iterative processes and evolution over time. Within such systems, repetitive transformations can lead to stable configurations, known as attractors, including fixed points and…

Computation and Language · Computer Science 2025-05-19 Zhilin Wang , Yafu Li , Jianhao Yan , Yu Cheng , Yue Zhang

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional…

Machine Learning · Computer Science 2019-08-20 Marco Rudolph , Bastian Wandt , Bodo Rosenhahn

The rapid evolution of specialized large language models (LLMs) has transitioned from simple domain adaptation to sophisticated native architectures, marking a paradigm shift in AI development. This survey systematically examines this…

Computation and Language · Computer Science 2025-08-28 Chenghan Yang , Ruiyu Zhao , Yang Liu , Ling Jiang

Tabular machine learning problems often require time-consuming and labor-intensive feature engineering. Recent efforts have focused on using large language models (LLMs) to capitalize on their potential domain knowledge. At the same time,…

Machine Learning · Computer Science 2025-07-16 Jaris Küken , Lennart Purucker , Frank Hutter

Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains. However, effectively leveraging their vast knowledge for training smaller downstream models remains an open challenge, especially in domains like…

Machine Learning · Computer Science 2025-07-28 Davor Vukadin , Marin Šilić , Goran Delač

Large Language Models (LLMs) have demonstrated remarkable versatility across various domains. To further advance LLMs, we propose 'SELF' (Self-Evolution with Language Feedback), a novel approach that enables LLMs to self-improve through…

Computation and Language · Computer Science 2024-02-02 Jianqiao Lu , Wanjun Zhong , Wenyong Huang , Yufei Wang , Qi Zhu , Fei Mi , Baojun Wang , Weichao Wang , Xingshan Zeng , Lifeng Shang , Xin Jiang , Qun Liu

This review synthesizes the nascent but critical field of developmental interpretability for Large Language Models. We chart the field's evolution from static, post-hoc analysis of trained models to a dynamic investigation of the training…

Computation and Language · Computer Science 2025-08-25 Ihor Kendiukhov

Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies concentrate on fully pre-trained LLMs to better understand and improve LLMs' trustworthiness. In this paper, to reveal the untapped potential of…

Computation and Language · Computer Science 2024-09-04 Chen Qian , Jie Zhang , Wei Yao , Dongrui Liu , Zhenfei Yin , Yu Qiao , Yong Liu , Jing Shao

Large language models (LLMs) are increasingly used in emotionally sensitive human-AI applications, yet little is known about how emotion recognition is internally represented. In this work, we investigate the internal mechanisms of emotion…

Computation and Language · Computer Science 2026-04-29 Bangzhao Shu , Arinjay Singh , Mai ElSherief

Learning hierarchical features in Sparse Autoencoders (SAEs) is essential for capturing the structured nature of real-world data and mitigating issues like feature absorption or splitting. Existing works attempt to identify hierarchical…

Machine Learning · Computer Science 2026-05-12 Tue M. Cao , Hoang X. Nhat , Raed Alharbi , Phi Le Nguyen , My T. Thai

Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs…

Neurons and Cognition · Quantitative Biology 2025-12-10 Omar Claflin

Language style is often used by writers to convey their intentions, identities, and mastery of language. In this paper, we show that current large language models struggle to capture some language styles without fine-tuning. To address this…

Computation and Language · Computer Science 2024-06-07 Ruohao Guo , Wei Xu , Alan Ritter