Fairness in large language models: A taxonomic survey

Z Chu, Z Wang, W Zhang - ACM SIGKDD explorations newsletter, 2024 - dl.acm.org
Large Language Models (LLMs) have demonstrated remarkable success across various
domains. However, despite their promising performance in numerous real-world …

Large language model supply chain: A research agenda

S Wang, Y Zhao, X Hou, H Wang - arXiv preprint arXiv:2404.12736, 2024 - arxiv.org
The rapid advancements in pre-trained Large Language Models (LLMs) and Large
Multimodal Models (LMMs) have ushered in a new era of intelligent applications …

Reducing llm hallucination using knowledge distillation: A case study with mistral large and mmlu benchmark

D McDonald, R Papadopoulos, L Benningfield - Authorea Preprints, 2024 - techrxiv.org
The application of knowledge distillation to reduce hallucination in large language models
represents a novel and significant advancement in enhancing the reliability and accuracy of …

Instruction Backdoor Attacks Against Customized {LLMs}

R Zhang, H Li, R Wen, W Jiang, Y Zhang… - 33rd USENIX Security …, 2024 - usenix.org
The increasing demand for customized Large Language Models (LLMs) has led to the
development of solutions like GPTs. These solutions facilitate tailored LLM creation via …

Hummer: Towards limited competitive preference dataset

L Jiang, Y Wu, J Xiong, J Ruan, Y Ding, Q Guo… - arXiv preprint arXiv …, 2024 - arxiv.org
Preference datasets are essential for incorporating human preferences into pre-trained
language models, playing a key role in the success of Reinforcement Learning from Human …

Exploring Multilingual Human Value Concepts in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?

S Xu, W Dong, Z Guo, X Wu, D Xiong - arXiv preprint arXiv:2402.18120, 2024 - arxiv.org
Prior research in representation engineering has revealed that LLMs encode concepts
within their representation spaces, predominantly centered around English. In this study, we …

A comparative analysis of large language models to evaluate robustness and reliability in adversarial conditions

T Goto, K Ono, A Morita - Authorea Preprints, 2024 - techrxiv.org
This study went on a comprehensive evaluation of four prominent Large Language Models
(LLMs)-Google Gemini, Mistral 8x7B, ChatGPT-4, and Microsoft Phi-1.5-to assess their …

Against The Achilles' Heel: A Survey on Red Teaming for Generative Models

L Lin, H Mu, Z Zhai, M Wang, Y Wang, R Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Generative models are rapidly gaining popularity and being integrated into everyday
applications, raising concerns over their safety issues as various vulnerabilities are …

Unique Security and Privacy Threats of Large Language Model: A Comprehensive Survey

S Wang, T Zhu, B Liu, D Ming, X Guo, D Ye… - arXiv preprint arXiv …, 2024 - arxiv.org
With the rapid development of artificial intelligence, large language models (LLMs) have
made remarkable progress in natural language processing. These models are trained on …

Rapid Adoption, Hidden Risks: The Dual Impact of Large Language Model Customization

R Zhang, H Li, R Wen, W Jiang, Y Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
The increasing demand for customized Large Language Models (LLMs) has led to the
development of solutions like GPTs. These solutions facilitate tailored LLM creation via …