English
Related papers

Related papers: Detecting High-Stakes Interactions with Activation…

200 papers

We introduce a dynamic benchmarking system for conversational agents that evaluates their performance through a single, simulated, and lengthy user$\leftrightarrow$agent interaction. The interaction is a conversation between the user and…

Computation and Language · Computer Science 2024-10-14 David Castillo-Bolado , Joseph Davidson , Finlay Gray , Marek Rosa

Data is fundamental to large language models (LLMs). However, understanding of what makes certain data useful for different stages of an LLM workflow, including training, tuning, alignment, in-context learning, etc., and why, remains an…

Artificial Intelligence · Computer Science 2026-05-20 Shiqiang Wang , Herbert Woisetschläger , Hans Arno Jacobsen , Mingyue Ji

Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…

Cryptography and Security · Computer Science 2025-11-04 Nathalie Kirch , Constantin Weisser , Severin Field , Helen Yannakoudakis , Stephen Casper

The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…

Computation and Language · Computer Science 2025-06-24 Yilei Jiang , Xinyan Gao , Tianshuo Peng , Yingshui Tan , Xiaoyong Zhu , Bo Zheng , Xiangyu Yue

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

Artificial Intelligence · Computer Science 2025-05-21 Maheep Chaudhary , Fazl Barez

Language models can behave in unexpected and unsafe ways, and so it is valuable to monitor their outputs. Internal activations of language models encode additional information that could be useful for this. The baseline approach for…

Machine Learning · Computer Science 2025-04-30 Henk Tillman , Dan Mossing

The syntactic structures of sentences can be readily read-out from the activations of large language models (LLMs). However, the ``structural probes'' that have been developed to reveal this phenomenon are typically evaluated on an…

Computation and Language · Computer Science 2025-08-12 Pablo J. Diego-Simón , Emmanuel Chemla , Jean-Rémi King , Yair Lakretz

Large Language Models (LLMs) have increasingly been utilized in social simulations, where they are often guided by carefully crafted instructions to stably exhibit human-like behaviors during simulations. Nevertheless, we doubt the…

Artificial Intelligence · Computer Science 2024-10-29 Zengqing Wu , Run Peng , Shuyuan Zheng , Qianying Liu , Xu Han , Brian Inhyuk Kwon , Makoto Onizuka , Shaojie Tang , Chuan Xiao

We observe an empirical phenomenon in Large Language Models (LLMs) -- very few activations exhibit significantly larger values than others (e.g., 100,000 times larger). We call them massive activations. First, we demonstrate the widespread…

Computation and Language · Computer Science 2024-08-15 Mingjie Sun , Xinlei Chen , J. Zico Kolter , Zhuang Liu

Large language models (LLMs) are increasingly used for text-rich graph machine learning tasks such as node classification in high-impact domains like fraud detection and recommendation systems. Yet, despite a surge of interest, the field…

Computation and Language · Computer Science 2026-03-03 Ben Finkelshtein , Silviu Cucerzan , Sujay Kumar Jauhar , Ryen White

As Large Language Models (LLMs) evolve from chatbots to agentic assistants, they are increasingly observed to exhibit risky behaviors when subjected to survival pressure, such as the threat of being shut down. While multiple cases have…

Artificial Intelligence · Computer Science 2026-03-06 Yida Lu , Jianwei Fang , Xuyang Shao , Zixuan Chen , Shiyao Cui , Shanshan Bian , Guangyao Su , Pei Ke , Han Qiu , Minlie Huang

The widespread adoption of Large Language Models (LLMs) in critical applications has introduced severe reliability and security risks, as LLMs remain vulnerable to notorious threats such as hallucinations, jailbreak attacks, and backdoor…

Cryptography and Security · Computer Science 2026-04-07 Shide Zhou , Kailong Wang , Ling Shi , Haoyu Wang

Large Language Models (LLMs) are being extensively used for cybersecurity purposes. One of them is the detection of vulnerable codes. For the sake of efficiency and effectiveness, compression and fine-tuning techniques are being developed,…

Cryptography and Security · Computer Science 2025-06-02 Luis Ibanez-Lissen , Lorena Gonzalez-Manzano , Jose Maria de Fuentes , Nicolas Anciaux

Large Language Models (LLMs) are often used as automated judges to evaluate text, but their effectiveness can be hindered by various unintentional biases. We propose using linear classifying probes, trained by leveraging differences between…

Computation and Language · Computer Science 2025-03-25 Sharan Maiya , Yinhong Liu , Ramit Debnath , Anna Korhonen

Recent years have witnessed a growing interest in automating labor-intensive and complex activities, i.e., those consisting of multiple atomic tasks, by deploying robots in dynamic and unpredictable environments such as industrial and…

Robotics · Computer Science 2025-09-22 Francesco Argenziano , Elena Umili , Francesco Leotta , Daniele Nardi

Application designers have moved to integrate large language models (LLMs) into their products. However, many LLM-integrated applications are vulnerable to prompt injections. While attempts have been made to address this problem by building…

Cryptography and Security · Computer Science 2025-04-15 Dennis Jacob , Hend Alzahrani , Zhanhao Hu , Basel Alomair , David Wagner

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Artificial Intelligence · Computer Science 2025-08-13 Shivam Dubey

Large language models (LLMs) achieve strong performance in long-horizon decision-making tasks through multi-step interaction and reasoning at test time. While practitioners commonly believe a higher task success rate necessitates the use of…

Artificial Intelligence · Computer Science 2026-05-15 Yuanzhe Li , Jianing Deng , Jingtong Hu , Tianlong Chen , Song Wang , Huanrui Yang

Large Language Models (LLMs) are increasingly used to generate textual explanations of process models discovered from event logs. Producing explanations from large behavioral abstractions (e.g., directly-follows graphs or Petri nets) can be…

Machine Learning · Computer Science 2025-10-14 P. van Oerle , R. H. Bemthuis , F. A. Bukhsh

As large language models (LLMs) permeate more and more applications, an assessment of their associated security risks becomes increasingly necessary. The potential for exploitation by malicious actors, ranging from disinformation to data…

Cryptography and Security · Computer Science 2024-09-24 Erik Derner , Kristina Batistič , Jan Zahálka , Robert Babuška