LLM Survey Papers

A curated collection of influential survey papers on Large Language Models, covering foundational concepts, advanced techniques, and diverse applications.

Foundation Models: A Survey of Large Language Models

This paper provides a comprehensive overview of large language models, discussing their architectures, training methodologies, and emergent capabilities.

Read Paper

The Prompt Report: A Systematic Survey of Prompting Techniques

Explores various techniques used to design effective prompts for large language models, categorizing them and analyzing their impact on model performance.

Read Paper

A Survey on Retrieval-Augmented Text Generation for Large Language Models

Delves into Retrieval-Augmented Generation (RAG) methods, which combine LLMs with external knowledge bases to improve factual accuracy and reduce hallucinations.

Read Paper

A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Addresses the phenomenon of hallucinations in LLMs, providing a taxonomy of types, underlying causes, and current mitigation strategies.

Read Paper

Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey

Reviews various Parameter-Efficient Fine-Tuning (PEFT) techniques that enable adaptation of large pre-trained models to downstream tasks with minimal computational cost.

Read Paper

A Survey on Large Language Model based Autonomous Agents

Examines the emerging field of LLM-based autonomous agents, discussing their architectures, capabilities, and potential applications in complex environments.

Read Paper

A Survey on Multimodal Large Language Models

Provides an overview of multimodal LLMs, which integrate and process information from multiple modalities such as text, images, and audio.

Read Paper

A Survey on Evaluation of Large Language Models

Discusses various methodologies and metrics used to evaluate the performance, capabilities, and limitations of large language models across different tasks.

Read Paper

Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Investigates the security vulnerabilities of LLMs, focusing on adversarial attacks and their implications for model robustness and trustworthiness.

Read Paper

Large Language Model Alignment: A Survey

Explores the critical area of LLM alignment, covering techniques and challenges in ensuring models behave in accordance with human values and intentions.

Read Paper

Reasoning with Large Language Models: A Survey

Focuses on the reasoning capabilities of LLMs, reviewing different approaches to enhance their logical and problem-solving skills.

Read Paper

Efficient Large Language Models: A Survey

Examines techniques for improving the efficiency of LLMs in terms of computational cost, memory usage, and inference speed.

Read Paper

Explainability for Large Language Models: A Survey

Covers methods and challenges in making the decisions and internal workings of large language models more transparent and understandable to humans.

Read Paper

Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

Provides a comprehensive overview of trustworthiness in LLMs, including aspects like safety, fairness, robustness, and interpretability.

Read Paper

Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications

Surveys the application of LLMs in code generation, discussing challenges, techniques, evaluation metrics, and real-world use cases.

Read Paper

A Survey of Large Language Models in Medicine: Progress, Application, and Challenge

Explores the growing role of LLMs in the medical domain, highlighting their applications, current progress, and the unique challenges faced.

Read Paper

A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias

Examines the development and challenges of multilingual LLMs, focusing on data corpora, cross-lingual alignment, and potential biases.

Read Paper