Towards Safer Large Language Models (LLMs)

被引：0

作者：

Lawrence, Carolin ^{[1
]}

Bifulco, Roberto ^{[1
]}

Gashteovski, Kiril ^{[1
]}

Hung, Chia-Chien ^{[1
]}

Ben Rim, Wiem ^{[1
]}

Shaker, Ammar ^{[1
]}

Oyamada, Masafumi ^{[2
]}

Sadamasa, Kunihiko ^{[2
]}

Enomoto, Masafumi ^{[2
]}

Takeoka, Kunihiro ^{[2
]}

机构：

[1] NEC Laboratories Europe, Germany

[2] Data Science Laboratories

来源：

NEC Technical Journal | 2024年 / 17卷 / 02期

关键词：

Computational linguistics - Risk assessment;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Large Language Models (LLMs) are revolutionizing our world. They have impressive textual capabilities that will fundamentally change how human users can interact with intelligent systems. Nonetheless, they also still have a series of limitations that are important to keep in mind when working with LLMs. We explore how these limitations can be addressed from two different angles. First, we look at options that are currently already available, which include (1) assessing the risk of a use case, (2) prompting a LLM to deliver explanations and (3) encasing LLMs in a human-centred system design. Second, we look at technologies that we are currently developing, which will be able to (1) more accurately assess the quality of an LLM for a high-risk domain, (2) explain the generated LLM output by linking to the input and (3) fact check the generated LLM output against external trustworthy sources. © 2024 NEC Mediaproducts. All rights reserved.

引用

页码：64 / 74

共 50 条

[41] Tangible LLMs: Tangible Sense-Making For Trustworthy Large Language Models
Angelini, Leonardo
Klumbyte, Goda
Daniel, Maxime
Couture, Nadine
Mugellini, Elena
Draude, Claude
PROCEEDINGS OF THE NINETEENTH INTERNATIONAL CONFERENCE ON TANGIBLE, EMBEDDED AND EMBODIED INTERACTION, TEI 2025, 2025,
[42] EchoSwift An Inference Benchmarking and Configuration Discovery Tool for Large Language Models (LLMs)
Krishna, Karthik
Bandili, Ramana
COMPANION OF THE 15TH ACM/SPEC INTERNATIONAL CONFERENCE ON PERFORMANCE ENGINEERING, ICPE COMPANION 2024, 2024, : 158 - 162
[43] Mitigating Insecure Outputs in Large Language Models(LLMs): A Practical Educational Module
Barek, Md Abdul
Rahman, Md Mostafizur
Akter, Mst Shapna
Riad, A. B. M. Kamrul Islam
Rahman, Md Abdur
Shahriar, Hossain
Rahman, Akond
Wu, Fan
2024 IEEE 48TH ANNUAL COMPUTERS, SOFTWARE, AND APPLICATIONS CONFERENCE, COMPSAC 2024, 2024, : 2424 - 2429
[44] Legal large language models (LLMs): legal dynamos or “fancifully packaged ChatGPT”?
Fife Ogunde
Discover Artificial Intelligence, 5 (1):
[45] Enabling access to large-language models (LLMs) at scale for higher education
Nadel, Peter
Maloney, Delilah
Monahan, Kyle M.
PRACTICE AND EXPERIENCE IN ADVANCED RESEARCH COMPUTING 2024, PEARC 2024, 2024,
[46] Artificial Intelligence and content analysis: the large language models (LLMs) and the automatized categorization
Carius, Ana Carolina
Teixeira, Alex Justen
AI & SOCIETY, 2024,
[47] Causality Extraction from Medical Text Using Large Language Models (LLMs)
Gopalakrishnan, Seethalakshmi
Garbayo, Luciana
Zadrozny, Wlodek
INFORMATION, 2025, 16 (01)
[48] USING LARGE LANGUAGE MODELS (LLMS) FOR DATA EXTRACTION IN LITERATURE REVIEWS: AN ENHANCED APPROACH
Lambova, A.
Matev, K.
Gallinaro, J.
Guerra, I
Rtveladze, K.
Caverly, S.
VALUE IN HEALTH, 2024, 27 (12)
[49] Potentials and Challenges of Large Language Models (LLMs) in the Context of Administrative Decision-Making
Pesch, Paulina Jo
EUROPEAN JOURNAL OF RISK REGULATION, 2025,
[50] "Conversing" With Qualitative Data: Enhancing Qualitative Research Through Large Language Models (LLMs)
Hayes, Adam S.
INTERNATIONAL JOURNAL OF QUALITATIVE METHODS, 2025, 24

← 1 2 3 4 5 →