Survey of Different Large Language Model Architectures: Trends, Benchmarks, and Challenges

2024/01/01 by Minghao Shao, Abdul Basit, Ramesh Karri +1 · 1 voice · 78 citations
Computer Science · #Computer architecture #Computer science #Natural Language Processing Techniques #Topic Modeling

paper · pdf · open access · doi:10.1109/access.2024.3482107

published in IEEE Access 12, 188664-188706 (Institute of Electrical and Electronics Engineers)

openalex publication_date 2024/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Large Language Models (LLMs) represent a class of deep learning models adept at understanding natural language and generating coherent responses to various prompts or queries. These models far exceed the complexity of conventional neural networks, often encompassing dozens of neural network layers and containing billions to trillions of parameters. They are typically trained on vast datasets, utilizing architectures based on transformer blocks. Present-day LLMs are multi-functional, capable of performing a range of tasks from text generation and language translation to question answering, as well as code generation and analysis. An advanced subset of these models, known as Multimodal Large Language Models (MLLMs), extends LLM capabilities to process and interpret multiple data modalities, including images, audio, and video. This enhancement empowers MLLMs with capabilities like video editing, image comprehension, and captioning for visual content. This survey provides a comprehensive overview of the recent advancements in LLMs. We begin by tracing the evolution of LLMs and subsequently delve into the advent and nuances of MLLMs. We analyze emerging state-of-the-art MLLMs, exploring their technical features, strengths, and limitations. Additionally, we present a comparative analysis of these models and discuss their challenges, potential limitations, and prospects for future development.

Citations

• Generative Adversarial Networks: An Overview
• Generative adversarial networks

Cited by

• NetDeTox: Adversarial and Efficient Evasion of Hardware-Security GNNs via RL-LLM Orchestration
• TrojanLoC: LLM-based Framework for RTL Trojan Localization
• VeriDispatcher: Multi-Model Dispatching through Pre-Inference Difficulty Prediction for RTL Generation Optimization
• DIR-TIR: Dialog-Iterative Refinement for Text-to-Image Retrieval
• L2T-Hyena: Enhancing State-Space Models with an Adaptive Learn-to-Teach Framework
• Bayesian Network Fusion of Large Language Models for Sentiment Analysis
• From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization
• CARGO: A Framework for Confidence-Aware Routing of Large Language Models
• Retrieval Augmented Large Language Model System for Comprehensive Drug Contraindications
• Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction
• Quantum optical model of an artificial neuron
• QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges
• ATAG: AI-Agent Application Threat Assessment with Attack Graphs
• SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design
• A Comprehensive Survey of Large AI Models for Future Communications: Foundations, Applications and Challenges
• REMOR: Automated Peer Review Generation with LLM Reasoning and Multi-Objective Reinforcement Learning
• Bridging Industrial Expertise and XR with LLM-Powered Conversational Agents

Discussions

• This is a really neat info graphic about the architectural lineage of LLMs. Also TIL Claude still has an encoder?! source: arxiv.org/abs/2412.03220 [bsky, 1 points, 0 comments]

Related

• Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey
• A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Tasks
• A Survey of Multimodal Large Language Model from A Data-centric Perspective
• A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks
• MM-LLMs: Recent Advances in MultiModal Large Language Models