#Reasoning

The project provides an extensive overview of reasoning with language model prompting, covering research on knowledge enhancement and prompt engineering. It supports understanding and development of reasoning in large language models for applications in fields like medical diagnosis and negotiation. By offering recent papers and methodological insights, it encourages further exploration on the evolution of reasoning in AI.

Explore a curated repository of foundation models designed to improve reasoning in language, vision, and multimodal contexts. The database classifies models and outlines their use in commonsense, mathematical, logical reasoning, and more. Additionally, it covers reasoning techniques like pre-training and fine-tuning. Contributions are welcome to broaden the resource collection for AI reasoning advances.

LISA employs a large language model to enhance segmentation tasks, particularly in reasoning segmentation through complex and implicit queries. It uses a detailed benchmark of image-instruction pairs, encompassing extensive world knowledge to provide detailed answers and supports multi-turn dialogue. Demonstrating strong zero-shot learning ability, LISA performs well on datasets without reasoning data, and fine-tuning even with limited data boosts its performance. LISA achieved notable recognition at CVPR 2024. Discover LISA's efficiency through our online demo.

Discover how Large Language Models (LLMs) and Knowledge Graphs (KGs) integrate to improve reasoning and knowledge access. This project aggregates important studies and resources that aim to bring together LLMs with KGs for more effective factual data utilization. LLMs perform well in diverse scenarios, yet they often miss the detailed factual knowledge that KGs provide. This resource presents methods to integrate LLMs and KGs, addressing challenges in knowledge retention and access. Core areas include KG-enhanced LLMs, LLM-augmented KGs, and combined approaches utilizing both technologies. Follow the latest in research developments, including graph-constrained and temporal KG reasoning, as recognized by conferences like NeurIPS and ACL.

This project investigates the role of chain-of-thought prompting in improving reasoning within large language models. It reviews diverse research papers, focusing on innovative methods like self-consistency and program-aided models. Noteworthy advancements include the use of language models in symbolic reasoning and scalable architectures such as PaLM. The project encompasses fundamental theories and practical implementations, addressing multi-context and multilingual capabilities, and aims to offer practical insights into potential real-world applications.