English
Related papers

Related papers: SAFE: A Sparse Autoencoder-Based Framework for Rob…

200 papers

Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their…

As large language models (LLMs) become increasingly prevalent, concerns about their reliability, particularly due to hallucinations - factually inaccurate or irrelevant outputs - have grown. Our research investigates the relationship…

Artificial Intelligence · Computer Science 2025-10-08 Shahrad Mohammadzadeh , Juan David Guerra , Marco Bonizzato , Reihaneh Rabbany , Golnoosh Farnadi

Large Language Models (LLMs) are known to hallucinate, whereby they generate plausible but inaccurate text. This phenomenon poses significant risks in critical applications, such as medicine or law, necessitating robust hallucination…

Computation and Language · Computer Science 2024-10-23 Benedict Aaron Tjandra , Muhammed Razzak , Jannik Kossen , Kunal Handa , Yarin Gal

The proliferation of IoT devices has significantly increased network vulnerabilities, creating an urgent need for effective Intrusion Detection Systems (IDS). Machine Learning-based IDS (ML-IDS) offer advanced detection capabilities but…

Cryptography and Security · Computer Science 2025-02-12 Elvin Li , Zhengli Shang , Onat Gungor , Tajana Rosing

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

Machine Learning · Computer Science 2025-10-10 Yifei Yao , Mengnan Du

Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assumed to improve factual correctness. However, how the parameter-efficient fine-tuning methods affect…

Computation and Language · Computer Science 2026-02-13 Xu Hu , Yifan Zhang , Songtao Wei , Chen Zhao , Qiannan Li , Bingzhe Li , Feng Chen

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

Large Language Models (LLMs) have demonstrated impressive capabilities on a broad array of NLP tasks, but their tendency to produce hallucinations$\unicode{x2013}$plausible-sounding but factually incorrect content$\unicode{x2013}$poses…

Computation and Language · Computer Science 2025-06-17 Aneesh Vathul , Daniel Lee , Sheryl Chen , Arthi Tasmia

Hallucinations in large language models are a widespread problem, yet the mechanisms behind whether models will hallucinate are poorly understood, limiting our ability to solve this problem. Using sparse autoencoders as an interpretability…

Computation and Language · Computer Science 2025-02-11 Javier Ferrando , Oscar Obeso , Senthooran Rajamanoharan , Neel Nanda

Hallucination has been a major problem for large language models and remains a critical challenge when it comes to multimodality in which vision-language models (VLMs) have to deal with not just textual but also visual inputs. Despite rapid…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Zhecan Wang , Garrett Bingham , Adams Yu , Quoc Le , Thang Luong , Golnaz Ghiasi

Vision-language models (VLMs) have advanced rapidly and are increasingly deployed in real-world applications, especially with the rise of agent-based systems. However, their safety has received relatively limited attention. Even the latest…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Hao Wang , Yiqun Sun , Pengfei Wei , Lawrence B. Hsieh , Daisuke Kawahara

Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems. However, a major drawback of LLMs is the issue of hallucination, where they…

Computation and Language · Computer Science 2024-07-08 Yuyan Chen , Qiang Fu , Yichen Yuan , Zhihao Wen , Ge Fan , Dayiheng Liu , Dongmei Zhang , Zhixu Li , Yanghua Xiao

Large language models (LLMs), despite their remarkable text generation capabilities, often hallucinate and generate text that is factually incorrect and not grounded in real-world knowledge. This poses serious risks in domains like…

Computation and Language · Computer Science 2025-11-18 Raavi Gupta , Pranav Hari Panicker , Sumit Bhatia , Ganesh Ramakrishnan

Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved remarkable successes over the last two years in a range of different applications. In spite of these successes, there exist concerns that limit the wide…

Computation and Language · Computer Science 2024-01-17 Junliang Luo , Tianyu Li , Di Wu , Michael Jenkin , Steve Liu , Gregory Dudek

Large Vision-Language Models (LVLMs) have achieved remarkable success but continue to struggle with object hallucination (OH), generating outputs inconsistent with visual inputs. While previous work has proposed methods to reduce OH, the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Boxu Chen , Ziwei Zheng , Le Yang , Zeyu Geng , Zhengyu Zhao , Chenhao Lin , Chao Shen

While multimodal large language models excel at various tasks, they still suffer from hallucinations, which limit their reliability and scalability for broader domain applications. To address this issue, recent research mainly focuses on…

Artificial Intelligence · Computer Science 2025-06-10 Liangliang You , Junchi Yao , Shu Yang , Guimin Hu , Lijie Hu , Di Wang

The surge in applications of large language models (LLMs) has prompted concerns about the generation of misleading or fabricated information, known as hallucinations. Therefore, detecting hallucinations has become critical to maintaining…

Machine Learning · Computer Science 2024-09-27 Xuefeng Du , Chaowei Xiao , Yixuan Li

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

Machine Learning · Computer Science 2026-04-17 Dongsheng Wang , Jinsen Zhang , Dawei Su , Hui Huang

Sparse autoencoders (SAEs) are a core interpretability tool for large language models, and progress on SAE architectures depends on benchmarks that reliably distinguish better SAEs from worse ones. We audit the SAE quality metrics in…

Machine Learning · Computer Science 2026-05-19 David Chanin

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, yet they remain susceptible to hallucinations -- generating content that is factually incorrect, unfaithful to provided…

Computation and Language · Computer Science 2026-05-25 Ahmed Cherif
‹ Prev 1 8 9 10 Next ›