Results 11 to 20 of about 56,050 (312)

LLM-enabled Incremental Learning Framework for Hand Exoskeleton Control

, 2023
It remains a formidable challenge to accurately recognize patients’ motion intentions to flexibly control hand exoskeletons. Current methods primarily focus on recognition of limited patient’s motion intentions, with the purpose of controlling ...
Wenyuan Chen (16481550)
core   +1 more source

LLM-Assisted Content Analysis (LACA):  Coded data and model reasons

, 2023
Description This resources consists of calibrations sets (N=100) for 4 publically available datasets using the LLM-Assisted Content Analysis method (LACA).
Annice Kim (16019375), John Bollenbacher (13915940), Micahel Wenger (16019282), Jessica Speer (16019373), Rob Chew (3845764)   +4 more
core   +1 more source

LLM Unlearning with LLM Beliefs

CoRR
ICLR ...
Kemou Li, Qizhou Wang, Yue Wang, Fengpeng Li, Jun Liu 0071, Bo Han 0003, Jiantao Zhou 0001   +6 more
openaire   +2 more sources

"To LLM, or Not to LLM?": How Designers and Developers Navigate LLMs as Tools or Teammates

Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems
6 pages, 2 figures, 1 ...
Varad Vishwarupe, Ivan Flechais, Nigel Shadbolt, Marina Denise Jirotka   +3 more
openaire   +2 more sources

Аналіз вразливостей великих мовних моделей

Social Development & Security
Мета роботи: аналіз вразливостей великих мовних моделей (LLM) на основі класифікації OWASP Top 10 для застосунків LLM, проведення оцінки потенційних загроз та розробка рекомендацій щодо підвищення рівня безпеки цих моделей.
Viktor Kolchenko, Dmytro Sabodashko, Mariia Shved, Yuriy Khoma, Nazar Maksymiv   +4 more
doaj   +1 more source

LLMs + Persona-Plug = Personalized LLMs

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their individual interests. This has led to the development of various personalized approaches aimed at adapting large language models (LLMs) to generate customized outputs aligned with user ...
Jiongnan Liu 0001, Yutao Zhu 0001, Shuting Wang 0002, Xiaochi Wei, Erxue Min, Yu Lu 0009, Shuaiqiang Wang, Dawei Yin 0001, Zhicheng Dou   +8 more
openaire   +3 more sources

Generative AI Technologies as a Tool for Counter-Narratives to Russian Propaganda

Медіафорум: аналітика, прогнози, інформаційний менеджмент
This article explores the potential of generative artificial intelligence (AI) technologies as a tool for constructing counter-narratives against russian propaganda in the context of the full-scale war in Ukraine. It examines methodological approaches to
Vasyl Baranets, Ivan Osadtsa
doaj   +1 more source

Set-LLM: A Permutation-Invariant LLM

CoRR
While large language models (LLMs) demonstrate impressive capabilities across numerous applications, their robustness remains a critical concern. This paper is motivated by a specific vulnerability: the order sensitivity of LLMs. This vulnerability manifests itself as the order bias observed when LLMs decide between possible options (for example, a ...
Beni Egressy, Jan Stühmer
openaire   +2 more sources

Evaluating Reasoning in Large Language Models with a Modified Think-a-Number Game: Case Study

Acta Informatica Pragensia
Background: Large language models (LLMs) excel at various tasks but often encounter difficulties when extended reasoning requires maintaining a consistent internal state.
Petr Hoza
doaj   +1 more source

LLMs are Introvert

CoRR
The exponential growth of social media and generative AI has transformed information dissemination, fostering connectivity but also accelerating the spread of misinformation. Understanding information propagation dynamics and developing effective control strategies is essential to mitigate harmful content. Traditional models, such as SIR, provide basic
Litian Zhang, Xiaoming Zhang, Bingyu Yan, Ziyi Zhou 0003, Bo Zhang, Zhenyu Guan, Xi Zhang 0008, Chaozhuo Li   +7 more
openaire   +2 more sources