Results 141 to 150 of about 186,001 (296)

LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs

We introduce LLMStinger, a novel approach that leverages Large Language Models (LLMs) to automatically generate adversarial suffixes for jailbreak attacks. Unlike traditional methods, which require complex prompt engineering or white-box access, LLMStinger uses a reinforcement learning (RL) loop to fine-tune an attacker LLM, generating new suffixes ...
Jha, Piyush, Arora, Arnav, Ganesh, Vijay
openaire   +2 more sources

Machine Learning‐Assisted Second‐Order Perturbation Theory for Chemical Potential Correction Toward Hubbard U Determination

Advanced Intelligent Discovery, EarlyView.
In this work, the Doubao large language model (LLM) is involved in the formula derivation processes for Hubbard U determination regarding the second‐order perturbations of the chemical potential. The core ML tool is optimized for physical domain knowledge, which is not limited to parameter prediction but rather serves as an interactive physical theory ...
Mingzi Sun, Tong Wu, Baian Chen, Zikang Li, Qiuyang Lu, Lu Lu, Hon Ho Wong, Cheuk Hei Chan, Bolong Huang   +8 more
wiley   +1 more source

ChatCFD: A Large Language Model‐Driven Agent for End‐to‐End Computational Fluid Dynamics Automation with Structured Knowledge and Reasoning

Advanced Intelligent Discovery, EarlyView.
Chat computational fluid dynamics (CFD) introduces an large language model (LLM)‐driven agent that automates OpenFOAM simulations end‐to‐end, attaining 82.1% execution success and 68.12% physical fidelity across 315 benchmarks—far surpassing prior systems.
E Fan, Kang Hu, Zhuowen Wu, Jiangyang Ge, Jiawei Miao, Yuzhi Zhang, He Sun, Weizong Wang, Tianhan Zhang   +8 more
wiley   +1 more source

LLM education

We propose a novel large language model (LLM) framework guided by GIS prior knowledge for generating professional GIS question banks.
openaire   +2 more sources

Evolution of Physical Intelligence Across Scales

Advanced Intelligent Discovery, EarlyView.
By following the evolution of physical intelligence across scales, this article shows how intelligence arises from materials, structures, physical interactions, and collectives. It establishes physical intelligence as the evolutionary foundation upon which embodied intelligence is built.
Ke Liu, Tianyun Huang, Aming Li, Pengyu Lv, Tingting Qin, Wenhui Chen, Hui Wei, Huiling Duan   +7 more
wiley   +1 more source

Evaluating LLMs at Detecting Errors in LLM Responses

With Large Language Models (LLMs) being widely used across various tasks, detecting errors in their responses is increasingly crucial. However, little research has been conducted on error detection of LLM responses. Collecting error annotations on LLM responses is challenging due to the subjective nature of many NLP tasks, and thus previous research ...
Kamoi, Ryo, Das, Sarkar Snigdha Sarathi, Lou, Renze, Ahn, Jihyun Janice, Zhao, Yilun, Lu, Xiaoxin, Zhang, Nan, Zhang, Yusen, Zhang, Ranran Haoran, Vummanthala, Sujeeth Reddy, Dave, Salika, Qin, Shaobo, Cohan, Arman, Yin, Wenpeng, Zhang, Rui   +14 more
openaire   +2 more sources

Automating AI Discovery for Biomedicine Through Knowledge Graphs and Large Language Models Agents

Advanced Intelligent Discovery, EarlyView.
This work proposes a novel framework that automates biomedical discovery by integrating knowledge graphs with multiagent large language models. A biologically aligned graph exploration strategy identifies hidden pathways between biomedical entities, and specialized agents use this pathway to iteratively design AI predictors and wet‐lab validation ...
Naafey Aamer, Muhammad Nabeel Asim, Shan Munir, Andreas Dengel   +3 more
wiley   +1 more source

LLM Augmented LLMs: Expanding Capabilities through Composition

Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to augment them or impart new skills.
Bansal, Rachit, Samanta, Bidisha, Dalmia, Siddharth, Gupta, Nitish, Vashishth, Shikhar, Ganapathy, Sriram, Bapna, Abhishek, Jain, Prateek, Talukdar, Partha   +8 more
openaire   +1 more source

When the Going Gets Weird, The Weird Turn Pro*: Management Best Practices in the Age of Medicinal Marijuana [PDF]

, 2020
Winn, John I., JD, LLM
core   +1 more source

LLM‐Based Scientific Assistants for Knowledge Extraction: Which Design Choices Matter?

Advanced Intelligent Discovery, EarlyView.
A comprehensive framework for optimizing Large Language Models in domain‐specific applications is introduced. The LLM Playground integrates Prompt Engineering, knowledge augmentation, and advanced reasoning strategies to enable systematic comparison of architectures and base models.
David Exler, Manuel Raimann, Marc Münker, Maxim Rosin, Joaquin E. Urrutia Gómez, Christof M. Niemeyer, Markus Reischl, Luca Rettenberger   +7 more
wiley   +1 more source