English
Related papers

Related papers: Feature-Guided SAE Steering for Refusal-Rate Contr…

200 papers

As LLMs evolve, significant effort is spent on manually crafting prompts. While existing prompt optimization methods automate this process, they rely solely on learning from incorrect samples, leading to a sub-optimal performance.…

Computation and Language · Computer Science 2024-09-24 Mingqi Li , Karan Aggarwal , Yong Xie , Aitzaz Ahmad , Stephen Lau

Large language models can resist task-misaligned activation steering during inference, sometimes recovering mid-generation to produce improved responses even when steering remains active. We term this Endogenous Steering Resistance (ESR).…

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

Controlling the behavior of Large Language Models (LLMs) remains a significant challenge due to their inherent complexity and opacity. While techniques like fine-tuning can modify model behavior, they typically require extensive…

Artificial Intelligence · Computer Science 2025-05-07 Yixiong Hao , Ayush Panda , Stepan Shabalin , Sheikh Abdur Raheem Ali

Large Language Models (LLMs) are increasingly applied to automate software engineering tasks, including the generation of UML class diagrams from natural language descriptions. While prior work demonstrates that LLMs can produce…

Software Engineering · Computer Science 2026-04-07 Rabia Iftikhar , Andreas Rausch

Large language models (LLMs) have been widely deployed across numerous fields. Reinforcement Learning from Human Feedback (RLHF) leverages reward models (RMs) as proxies for human preferences to align LLM behaviors with human values, making…

Machine Learning · Computer Science 2025-11-26 Shuyi Zhang , Wei Shi , Sihang Li , Jiayi Liao , Hengxing Cai , Xiang Wang

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

Computation and Language · Computer Science 2023-10-10 Yi Dong , Zhilin Wang , Makesh Narsimhan Sreedhar , Xianchao Wu , Oleksii Kuchaiev

Zero-day attack detection plays a critical role in mitigating risks, protecting assets, and staying ahead in the evolving threat landscape. This study explores the application of stacked autoencoder (SAE), a type of artificial neural…

Cryptography and Security · Computer Science 2023-11-02 Mahmut Tokmak , Mike Nkongolo

Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior changes over training. Sparse Autoencoders (SAEs) have recently shown to be…

Machine Learning · Computer Science 2026-02-09 John Yan , Michael Yu , Yuqi Sun , Alexander Duffy , Tyler Marques , Matthew Lyle Olson

Sparse Autoencoders (SAEs) extract interpretable features from Large Language Models, but standard variants enforce non-negativity, forcing separate latents for diametrically opposed concepts (e.g., "pressure too high" vs. "pressure too…

Large language models (LLMs) can still be jailbroken into producing harmful outputs despite safety alignment. Existing attacks show this vulnerability, but not the internal mechanisms that cause it. This study asks whether jailbreak success…

Computation and Language · Computer Science 2026-04-28 Nilanjana Das , Manas Gaur

As the popularity of Large Language Models (LLMs) grow, combining model safety with utility becomes increasingly important. The challenge is making sure that LLMs can recognize and decline dangerous prompts without sacrificing their ability…

Computation and Language · Computer Science 2024-08-30 Ruchira Ray , Ruchi Bhalani

Sensitive directions experiments attempt to understand the computational features of Language Models (LMs) by measuring how much the next token prediction probabilities change by perturbing activations along specific directions. We extend…

Machine Learning · Computer Science 2024-11-19 Daniel J. Lee , Stefan Heimersheim

Understanding training dynamics and feature evolution is crucial for the mechanistic interpretability of large language models (LLMs). Although sparse autoencoders (SAEs) have been used to identify features within LLMs, a clear picture of…

Machine Learning · Computer Science 2025-06-04 Yang Xu , Yi Wang , Hengguan Huang , Hao Wang

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

Sparse Autoencoders (SAEs) aim to decompose the activation space of large language models (LLMs) into human-interpretable latent directions or features. As we increase the number of features in the SAE, hierarchical features tend to split…

Computation and Language · Computer Science 2025-11-18 David Chanin , James Wilken-Smith , Tomáš Dulka , Hardik Bhatnagar , Satvik Golechha , Joseph Bloom

In this paper, we demonstrate a surprising capability of large language models (LLMs): given only input feature names and a description of a prediction task, they are capable of selecting the most predictive features, with performance…

Machine Learning · Computer Science 2025-04-21 Daniel P. Jeong , Zachary C. Lipton , Pradeep Ravikumar

Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…

Machine Learning · Computer Science 2025-05-27 Xiangchen Song , Aashiq Muhamed , Yujia Zheng , Lingjing Kong , Zeyu Tang , Mona T. Diab , Virginia Smith , Kun Zhang

Large Language Models (LLMs) have impressive multilingual capabilities, but they suffer from unexpected code-switching, also known as language mixing, which involves switching to unexpected languages in the model response. This problem…

Computation and Language · Computer Science 2026-03-03 Boyi Deng , Yu Wan , Baosong Yang , Fei Huang , Wenjie Wang , Fuli Feng

Feature selection has been widely used to alleviate compute requirements during training, elucidate model interpretability, and improve model generalizability. We propose SLM -- Sparse Learnable Masks -- a canonical approach for end-to-end…

Machine Learning · Computer Science 2023-04-07 Yihe Dong , Sercan O. Arik
‹ Prev 1 3 4 5 6 7 10 Next ›