Bridging the Gap: System 2 Thinking in AI & RAG SystemsSystem 2-inspired Retrieval-Augmented Generation (RAG) systems can bridge the gap between LLMs and their untapped potential in complex…Feb 1Feb 1
Optimizing Compound AILearn about the optimization strategies driving the success of Compound AI systems.Dec 19, 2024Dec 19, 2024
AmbigNLG: Addressing Task Ambiguity in Instruction for Natural Language GenerationAmbigNLG is a means of tackling ambiguity in natural language generation (NLG) instructions by identifying unclear specifications and…Nov 21, 2024Nov 21, 2024
Your Internship in the AI Industry: A Student’s GuideLooking for an internship in tech, read our blog to make the best out of your journey.Nov 11, 2024Nov 11, 2024
MEGAnno in Action: Human-LLM Collaborative AnnotationMEGAnno combines the power of large language models (LLMs) with human expertise to streamline and enhance the data labeling process with a…Sep 9, 2024Sep 9, 2024
Leveraging LLMs for Semantic Type Detection in Data LakesWant to exploit more of the data in your data lake? LLMs can help you find data, identify data types, and more. Here’s how…Aug 29, 2024Aug 29, 2024
Big Trends Shaping NLP & NAACL 2024NAACL showcased major trends: targeted evaluation, reasoning, and fine-tuning/retrieval-augmented generation (RAG). These trends…Aug 16, 2024Aug 16, 2024
Unlocking the Potential of Transformers for Long-Form Text Matching: A Simple yet Powerful ApproachWe propose a simple yet effective solution using sequence pair classification with Transformer models, demonstrating its superiority over…Aug 15, 2024Aug 15, 2024
Towards Enterprise Compound AI SystemsWe introduce three projects: (1) developing a suitable architecture for productizing compound AI systems, (2) optimizing agentic workflowsJul 24, 2024Jul 24, 2024
Order Matters: Assessing LLM Sensitivity in Multiple-Choice TasksLarge language models (LLMs) have demonstrated remarkable capabilities in various NLP tasks. However, previous works have shown these…Jul 17, 2024Jul 17, 2024