61 citations
- The University of TokyoJP6 papers
- Fujitsu (China)CN3 papers
- National Institute of Advanced Industrial Science and TechnologyJP3 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Fujitsu (United Kingdom)GB2 papers
- The University of OsakaJP2 papers
- University of ManchesterGB2 papers
- University of TsukubaJP2 papers
- Aalborg UniversityDK1 paper
- Baidu (China)CN1 paper
- Bank of JapanJP1 paper
- Beijing University of Posts and TelecommunicationsCN1 paper
Showing cs.SEShow all
2 papers · 1 filter
cs.SE2025★ 2 cited
Risk Assessment Framework for Code LLMs via Leveraging Internal States
Yuheng Huang, Lei Ma, Keizaburo Nishikino +1
The pre-training paradigm plays a key role in the success of Large Language Models (LLMs), which have been recognized as one of the most significant advancements of AI recently. Bu…
cs.SE2020★ 59 cited
Towards Guidelines for Assessing Qualities of Machine Learning Systems
Julien Siebert, Lisa Joeckel, Jens Heidrich +5
Nowadays, systems containing components based on machine learning (ML) methods are becoming more widespread. In order to ensure the intended behavior of a software system, there ar…