English
Related papers

Related papers: Domain Restriction via Multi SAE Layer Transitions

200 papers

Transformer models have become state-of-the-art in decoding stimuli and behavior from neural activity, significantly advancing neuroscience research. Yet greater transparency in their decision-making processes would substantially enhance…

Quantitative Methods · Quantitative Biology 2025-06-18 Laurence Freeman , Philip Shamash , Vinam Arora , Caswell Barry , Tiago Branco , Eva Dyer

The external language models (LM) integration remains a challenging task for end-to-end (E2E) automatic speech recognition (ASR) which has no clear division between acoustic and language models. In this work, we propose an internal LM…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-05 Zhong Meng , Sarangarajan Parthasarathy , Eric Sun , Yashesh Gaur , Naoyuki Kanda , Liang Lu , Xie Chen , Rui Zhao , Jinyu Li , Yifan Gong

Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language. However, their capabilities wane in highly specialized domains underrepresented in the pretraining corpus, such as…

Machine Learning · Computer Science 2024-07-29 Junhong Shen , Neil Tenenholtz , James Brian Hall , David Alvarez-Melis , Nicolo Fusi

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

Machine Learning · Computer Science 2026-05-19 George Ma , Zhongyuan Liang , Irene Y. Chen , Somayeh Sojoudi

Detecting anomalies or out-of-distribution (OOD) samples is critical for maintaining the reliability and trustworthiness of machine learning systems. Recently, Large Language Models (LLMs) have demonstrated their effectiveness not only in…

Machine Learning · Computer Science 2025-02-17 Ruiyao Xu , Kaize Ding

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

Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of…

Neural and Evolutionary Computing · Computer Science 2022-12-05 Richard J. Preen , Stewart W. Wilson , Larry Bull

Large Language Models (LLMs) have shown remarkable success in supporting a wide range of knowledge-intensive tasks. In specialized domains, there is growing interest in leveraging LLMs to assist subject matter experts with domain-specific…

Computation and Language · Computer Science 2025-12-01 Aman Kumar , Ekant Muljibhai Amin , Xian Yeow Lee , Lasitha Vidyaratne , Ahmed K. Farahat , Dipanjan D. Ghosh , Yuta Koreeda , Chetan Gupta

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

Masked autoencoders (MAE) have shown tremendous potential for self-supervised learning (SSL) in vision and beyond. However, point clouds from LiDARs used in automated driving are particularly challenging for MAEs since large areas of the 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Mohamed Abdelsamad , Michael Ulrich , Claudius Gläser , Abhinav Valada

Discovering good process models is essential for different process analysis tasks such as conformance checking and process improvements. Automated process discovery methods often overlook valuable domain knowledge. This knowledge, including…

Artificial Intelligence · Computer Science 2024-09-02 Ali Norouzifar , Humam Kourani , Marcus Dees , Wil van der Aalst

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Philipp Wesp , Robbie Holland , Vasiliki Sideri-Lampretsa , Sergios Gatidis

Deep learning, particularly with the advancement of Large Language Models, has transformed biomolecular modeling, with protein language models such as ESM inspiring emerging RNA language models such as RiNALMo. Recent work has begun…

Biomolecules · Quantitative Biology 2026-05-18 Taehan Kim , Sangdae Nam

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

Diffusion models have become the go-to method for text-to-image generation, producing high-quality images from pure noise. However, the inner workings of diffusion models is still largely a mystery due to their black-box nature and complex,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Berk Tinaz , Zalan Fabian , Mahdi Soltanolkotabi

Large language models (LLMs) have shown promising efficacy across various tasks, becoming powerful tools in numerous aspects of human life. However, Transformer-based LLMs suffer a performance degradation when modeling long-term contexts…

Computation and Language · Computer Science 2026-03-23 Weiyao Luo , Suncong Zheng , Heming Xia , Weikang Wang , Yan Lei , Tianyu Liu , Shuang Chen , Zhifang Sui

Large Language Models (LLMs) are trained on massive, unstructured corpora, making it unclear which social patterns and biases they absorb and later reproduce. Existing evaluations typically examine outputs or activations, but rarely connect…

Computation and Language · Computer Science 2025-11-14 Mariam Mahran , Katharina Simbeck

In recent years, pre-trained large language models have achieved remarkable success across diverse tasks. Besides the pivotal role of self-supervised pre-training, their effectiveness in downstream applications also depends critically on…

Artificial Intelligence · Computer Science 2026-03-04 Qi Zhang , Yifei Wang , Xiaohan Wang , Jiajun Chai , Guojun Yin , Wei Lin , Yisen Wang

Large language models (LLMs) have emerged as strong contenders in machine translation.Yet, they still struggle to adequately handle discourse phenomena, such as pronoun resolution and lexical cohesion at the document level. In this study,…

Computation and Language · Computer Science 2025-10-09 Wafaa Mohammed , Vlad Niculae , Chrysoula Zerva

This study demonstrates that the modern generation of Large Language Models (LLMs, such as GPT-4) suffers from the same out-of-domain (OOD) performance gap observed in prior research on pre-trained Language Models (PLMs, such as BERT). We…

Computation and Language · Computer Science 2024-12-31 Dmitri Roussinov , Serge Sharoff , Nadezhda Puchnina
‹ Prev 1 8 9 10 Next ›