LLM Research Findings

In this section, we regularly highlight miscellaneous and interesting research findings about how to better work with large language models (LLMs). It include new tips, insights and developments around important LLM research areas such as scaling, agents, efficiency, hallucination, architectures, prompt injection, and much more.

LLM research and AI research in general is moving fast so we hope that this resource can help both researchers and developers stay ahead of important developments. We also welcome contributions to this section if you would like to highlight an exciting finding about your research or experiments.

In this section

• LLM Agents
• Retrieval Augmented Generation (RAG) for LLMs
• LLM Reasoning
• How Faithful are RAG Models?
• LLM In-Context Recall is Prompt Dependent
• Reducing Hallucination in Structured Outputs via RAG
• Best Practices and Lessons Learned on Synthetic Data for Language Models
• Reasoning with Intermediate Revision and Search for LLMs
• Efficient Infinite Context Transformers
• LM-Guided Chain-of-Thought
• Trustworthiness in LLMs
• LLM Tokenization
• What is Groq?