[PDF][PDF] A comprehensive survey of small language models in the era of large language models: Techniques, enhancements, applications, collaboration with llms, and …

F Wang, Z Zhang, X Zhang, Z Wu, T Mo, Q Lu… - arXiv preprint arXiv …, 2024 - ai.radensa.ru
Large language models (LLM) have demonstrated emergent abilities in text generation,
question answering, and reasoning, facilitating various tasks and domains. Despite their …

Towards testing and evaluating vision-language-action models for robotic manipulation: An empirical study

Z Wang, Z Zhou, J Song, Y Huang, Z Shu… - arXiv preprint arXiv …, 2024 - arxiv.org
Multi-modal foundation models and generative AI have demonstrated promising capabilities
in applications across various domains. Recently, Vision-language-action (VLA) models …

Jailbreaking proprietary large language models using word substitution cipher

D Handa, A Chirmule, B Gajera, C Baral - arXiv e-prints, 2024 - ui.adsabs.harvard.edu
Abstract Large Language Models (LLMs) are aligned to moral and ethical guidelines but
remain susceptible to creative prompts called Jailbreak that can bypass the alignment …

Multilingual blending: Llm safety alignment evaluation with language mixture

J Song, Y Huang, Z Zhou, L Ma - arXiv preprint arXiv:2407.07342, 2024 - arxiv.org
As safety remains a crucial concern throughout the development lifecycle of Large
Language Models (LLMs), researchers and industrial practitioners have increasingly …

Mitigating adversarial manipulation in LLMs: a prompt-based approach to counter Jailbreak attacks (Prompt-G)

B Pingua, D Murmu, M Kandpal, J Rautaray… - PeerJ Computer …, 2024 - peerj.com
Large language models (LLMs) have become transformative tools in areas like text
generation, natural language processing, and conversational AI. However, their widespread …

OR-Bench: An Over-Refusal Benchmark for Large Language Models

J Cui, WL Chiang, I Stoica, CJ Hsieh - arXiv preprint arXiv:2405.20947, 2024 - arxiv.org
Large Language Models (LLMs) require careful safety alignment to prevent malicious
outputs. While significant research focuses on mitigating harmful content generation, the …

LeCov: Multi-level Testing Criteria for Large Language Models

X Xie, J Song, Y Huang, D Song, F Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Language Models (LLMs) are widely used in many different domains, but because of
their limited interpretability, there are questions about how trustworthy they are in various …

ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs

L Yan, S Cheng, X Chen, K Zhang, G Shen… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Language Models (LLMs) have become integral to many applications, with system
prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs …

OR-Bench: An Over-Refusal Benchmark for Large Language Models

ORPR Rate - openreview.net
Large Language Models (LLMs) require careful safety alignment to prevent malicious
outputs. While significant research focuses on mitigating harmful content generation, the …