Results 71 to 80 of about 89,825 (246)
Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
CoRR14 pages, 1 figure.
Sara Abdali +3 more
openaire +3 more sources
A Perspective on Interactive Theorem Provers in Physics
Advanced Science, EarlyView.Into an interactive theorem provers (ITPs), one can write mathematical definitions, theorems and proofs, and the correctness of those results is automatically checked. This perspective goes over the best usage of ITPs within physics and motivates the open‐source community run project PhysLean, the aim of which is to be a library for digitalized physics
Joseph Tooby‐Smith
wiley +1 more source
Conversational Interest between Teachers and Second Language Learners Evaluated by Humans and LLMs
Stimulating language learners’ interest and engagement is essential to successful second language acquisition, but it can be hard to translate this intuition into effective learning resources.
Xingewi Tan +3 more
core +2 more sources
A multi-dimensional concept for evaluating NLP-based robots in healthcare scenarios
Current Directions in Biomedical EngineeringBackground: In the past decades, robots have transformed the healthcare sector by supporting clinical staff in various tasks. Applications of range from robot-supported surgical interventions and imaging, via healthcare logistics to cleaning and social ...
Wittenberg Thomas +7 more
doaj +1 more source
AI-Powered Curricula: Unpacking the Potential and Progress of Generative Technologies in Education
Ubiquity ProceedingsThe aim of this narrative review is to understand how Artificial Intelligence (AI), specifically generative AI (e.g. ChatGPT) is thought to be used to support teachers in content authoring and curriculum production.
Duygu Bektik +4 more
doaj +1 more source
CBF-LLM: Safe Control for LLM Alignment
CoRRThis paper proposes a control-based framework for aligning large language models (LLMs) by leveraging a control barrier function (CBF) to ensure user-desirable text generation. The presented framework applies the safety filter, designed based on the CBF, to the output generation of the baseline LLM, i.e., the sequence of the token, with the aim of ...
Yuya Miyaoka, Masaki Inoue
openaire +2 more sources
An Integrated NLP‐ML Framework for Property Prediction and Design of Steels
Advanced Science, EarlyView.This study presents a data‐driven framework that uses language‐processing techniques to interpret steel processing descriptions and machine‐learning models to predict mechanical properties. By organising complex process histories into meaningful groups and enabling rapid property forecasts, the work supports faster, more informed steel design through ...
Kiran Devraju +5 more
wiley +1 more source
Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs? [PDF]
Since the recent prosperity of Large Language Models (LLMs), there have been interleaved discussions regarding how to reduce hallucinations from LLM responses, how to increase the factuality of LLMs, and whether Knowledge Graphs (KGs), which store the ...
Dong, Xin Luna +4 more
core +1 more source
Transformation in Higher EducationGenerative artificial intelligence (GenAI) tools increase the speed and polish of academic writing, but they also destabilise higher education’s reliance on written artefacts as proxies for understanding.
Marcina Singh
doaj +1 more source
LLM-Sketch: Enhancing Network Sketches with LLM
CoRRNetwork stream mining is fundamental to many network operations. Sketches, as compact data structures that offer low memory overhead with bounded accuracy, have emerged as a promising solution for network stream mining. Recent studies attempt to optimize sketches using machine learning; however, these approaches face the challenges of lacking ...
Yuanpeng Li 0002 +5 more
openaire +3 more sources