English
Related papers

Related papers: Towards Understanding and Improving Refusal in Com…

200 papers

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

Machine Learning · Computer Science 2025-05-19 Omer Sahin Tas , Royden Wagner

Large language models (LLMs) face significant token efficiency bottlenecks in code generation and logical reasoning tasks, a challenge that directly impacts inference cost and model interpretability. This paper proposes a formal framework…

Artificial Intelligence · Computer Science 2025-02-03 Lumen AI , Tengzhou No. 1 Middle School , Shihao Ji , Zihui Song , Fucheng Zhong , Jisen Jia , Zhaobo Wu , Zheyi Cao , Tianhao Xu

Transformer-based models are becoming a central paradigm in autonomous driving because they can capture long-range spatial dependencies, multi-agent interactions, and multimodal context across perception, prediction, and planning. At the…

Machine Learning · Computer Science 2026-05-13 Juan Zhong , Yuhang Shi , Zukang Xu , Xi Chen

Large language models have steadily increased in size to achieve improved performance; however, this growth has also led to greater inference time and computational demands. Consequently, there is rising interest in model size reduction…

With time, machine learning models have increased in their scope, functionality and size. Consequently, the increased functionality and size of such models requires high-end hardware to both train and provide inference after the fact. This…

Machine Learning · Computer Science 2021-09-07 Arhum Ishtiaq , Sara Mahmood , Maheen Anees , Neha Mumtaz

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Cryptography and Security · Computer Science 2026-01-28 Yangyang Guo , Ziwei Xu , Si Liu , Zhiming Zheng , Mohan Kankanhalli

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its…

Machine Learning · Computer Science 2024-11-01 Andy Arditi , Oscar Obeso , Aaquib Syed , Daniel Paleka , Nina Panickssery , Wes Gurnee , Neel Nanda

When predictive models are used to support complex and important decisions, the ability to explain a model's reasoning can increase trust, expose hidden biases, and reduce vulnerability to adversarial attacks. However, attempts at…

Machine Learning · Computer Science 2019-07-11 Dimitris Bertsimas , Arthur Delarue , Patrick Jaillet , Sebastien Martin

Interpretability is a pressing issue for machine learning. Common approaches to interpretable machine learning constrain interactions between features of the input, rendering the effects of those features on a model's output comprehensible…

Machine Learning · Computer Science 2023-05-11 Kieran A. Murphy , Dani S. Bassett

Mechanistic interpretability (MI) aims to understand AI models by reverse-engineering the exact algorithms neural networks learn. Most works in MI so far have studied behaviors and capabilities that are trivial and token-aligned. However,…

Machine Learning · Computer Science 2024-07-15 Satvik Golechha , James Dao

Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and…

Machine Learning · Computer Science 2021-09-29 Prakhar Ganesh , Yao Chen , Xin Lou , Mohammad Ali Khan , Yin Yang , Hassan Sajjad , Preslav Nakov , Deming Chen , Marianne Winslett

With the ever-increasing complexity of neural language models, practitioners have turned to methods for understanding the predictions of these models. One of the most well-adopted approaches for model interpretability is feature-based…

Computation and Language · Computer Science 2021-06-10 Muhammad Bilal Zafar , Michele Donini , Dylan Slack , Cédric Archambeau , Sanjiv Das , Krishnaram Kenthapadi

Large neural models are often compressed before deployment. Model compression is necessary for many practical reasons, such as inference latency, memory footprint, and energy consumption. Compressed models are assumed to be miniature…

Machine Learning · Computer Science 2024-07-19 Rohit Raj Rai , Rishant Pal , Amit Awekar

Increasing the model capacity is a known approach to enhance the adversarial robustness of deep learning networks. On the other hand, various model compression techniques, including pruning and quantization, can reduce the size of the…

Machine Learning · Computer Science 2023-11-28 Svetlana Pavlitska , Hannes Grolig , J. Marius Zöllner

Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As…

Machine Learning · Computer Science 2025-06-06 Nikolaus Howe , Ian McKenzie , Oskar Hollinsworth , Michał Zajac , Tom Tseng , Aaron Tucker , Pierre-Luc Bacon , Adam Gleave

Large Deep Learning models are often compressed before being deployed in a resource-constrained environment. Can we trust the prediction of compressed models just as we trust the prediction of the original large model? Existing work has…

Computation and Language · Computer Science 2025-08-20 Rohit Raj Rai , Chirag Kothari , Siddhesh Shelke , Amit Awekar

The application of machine learning based decision making systems in safety critical areas requires reliable high certainty predictions. Reject options are a common way of ensuring a sufficiently high certainty of predictions made by the…

Artificial Intelligence · Computer Science 2022-05-17 André Artelt , Roel Visser , Barbara Hammer

Recurrent neural networks have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications.…

Computation and Language · Computer Science 2019-04-09 Artem M. Grachev , Dmitry I. Ignatov , Andrey V. Savchenko

The field of machine learning has seen tremendous progress in recent years, with deep learning models delivering exceptional performance across a range of tasks. However, these models often come at the cost of interpretability, as they…

Machine Learning · Computer Science 2024-01-08 Shun Liu

With the growth of model sizes and scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there is a vast literature about reducing model sizes, we…