HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models

RS Sukthanker, A Zela, B Staffler, JKH Franke… - arXiv preprint arXiv …, 2024 - arxiv.org
The expanding size of language models has created the necessity for a comprehensive
examination across various dimensions that reflect the desiderata with respect to the …

Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?

M Jin, Q Yu, J Huang, Q Zeng, Z Wang, W Hua… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper studies the phenomenon that different concepts are learned in different layers of
large language models, ie more difficult concepts are fully acquired with deeper layers. We …

Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing

W Zhao, Z Li, Y Li, Y Zhang, J Sun - arXiv preprint arXiv:2405.18166, 2024 - arxiv.org
Large language models (LLMs) are increasingly being adopted in a wide range of real-
world applications. Despite their impressive performance, recent studies have shown that …

Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents

S Deng, W Xu, H Sun, W Liu, T Tan, J Liu, A Li… - arXiv preprint arXiv …, 2024 - arxiv.org
With the remarkable advancements of large language models (LLMs), LLM-based agents
have become a research hotspot in human-computer interaction. However, there is a …

RAEE: A Training-Free Retrieval-Augmented Early Exiting Framework for Efficient Inference

L Huang, S Wu, Y Cui, Y Xiong, X Liu, TW Kuo… - arXiv preprint arXiv …, 2024 - arxiv.org
Deploying large language model inference remains challenging due to their high
computational overhead. Early exiting accelerates model inference by adaptively reducing …

Scale matters: Large language models with billions (rather than millions) of parameters better match neural representations of natural language

Z Hong, K Wang, Z Zada, H Gazula, D Turner, B Aubrey… - bioRxiv, 2024 - biorxiv.org
Recent research has used large language models (LLMs) to study the neural basis of
naturalistic language processing in the human brain. LLMs have rapidly grown in …