The latest from our team on Enterprise Generative AI.
Introducing RRE-1: Improving RAG relevance using Retrieval Evaluation and Re-ranking
RRE-1 helps developers easily evaluate retrieval performance and allows them to fix relevance issues by applying the learnings from the evaluation in the re-ranking phase - RRE-1 can be used as a low latency re-ranker via a convenient API.
Introducing HDM-1: The Industry-Leading Hallucination Detection Model with Unrivaled Accuracy and Speed
HDM-1 delivers unmatched accuracy and real-time evaluations, setting a new standard for reliability in hallucination evaluations for open-book LLM applications.
Revolutionizing LLM Evaluation Standards with SCORE Principles and Metrics
The SCORE (Simple, Consistent, Objective, Reliable, Efficient) framework revolutionizes LLM evaluation by addressing critical limitations in current evaluation systems, including LLM dependency, metric subjectivity, and computational costs. It introduces comprehensive quality, safety, and performance metrics that enable organizations to effectively assess their LLM applications while focusing on development rather than evaluation setup.
A Deep Dive into Agentic LLM Frameworks
I went to meet a few people around the SaaStr and Dreamforce Conferences in the San Francisco Bay area and found that agentic LLMs are a hot topic in the valley. Let's dive into how agentic LLM frameworks are marking an evolution in artificial intelligence.
Are LLMs the best way to judge LLMs?
”LLM as a judge” is a general technique where a language model, such as GPT-4, evaluates text generated by other models. This article dives into the pros and cons of using this popular technique for LLM evaluations.
How to Fix Hallucinations in RAG LLM Apps
AI hallucinations are real, and fixing them in RAG-based apps is crucial for keeping outputs accurate and useful.
An overview of Retrieval-Augmented Generation (RAG) and it's different components
RAG is a technique that enhances the generation of an output from a Large Language Model (LLM) by supplementing the input to the LLM with relevant external information. In this article, we will cover the different components and types of RAG systems.
Top Problems with RAG systems and ways to mitigate them
This short guide will help you understand the common problems with implementing efficient RAG systems and the best practices that can help you mitigate those problems
A Quick Comparison of Vector Databases for RAG Systems
In this article, we’ll walk through four popular vector DBs — ApertureDB, Pinecone, Weaviate, and Milvus — and compare them based on their key features and use cases.
An Expert’s Guide to Picking Your LLM Tech Stack
Join us as we examine the key layers of an LLM tech stack and help identify the best tools for your needs.
Top Strategies for Detecting LLM Hallucination
In this article, we’ll explore general strategies for detecting hallucinations in LLMs (in RAG-based and non-RAG apps).
Hallucination Fails: When AI Makes Up Its Mind and Businesses Pay the Price
Stories where AI inaccuracies negatively impacted the operational landscape of businesses.
The Case for Continuous Monitoring of Generative AI Models
Read on to learn about why Generative AI requires a new continuous monitoring stack, what the market offers currently, and what we are building
Announcing AIMon’s Instruction Adherence Evaluation for Large Language Models (LLMs)
Evaluation methods for whether an LLM follows a set of verifiable instructions.
Introducing Aimon Rely: Reducing Hallucinations in LLM Applications Without Breaking the Bank
Aimon Rely is a state-of-the-art, multi-model system for detecting LLM quality issues like hallucinations offline and online at low cost.
From Wordy to Worthy: Increasing Textual Precision in LLMs
Detectors to check for completeness and conciseness of LLM outputs.