Blog & Articles

Evaluating AI model outputs at scale is a major challenge for teams using LLMs, especially when assessing nuanced qualities like politeness, fairness, and tone that traditional benchmarks miss. IBM Research has released EvalAssist, an open-source tool that streamlines the "LLM-as-a-Judge" approach, allowing teams to define custom evaluation criteria and apply them at scale using models like GPT-4 or IBM's Granite. The platform offers multiple evaluation strategies including direct assessment and pairwise comparison, while providing transparency through chain-of-thought explanations and bias detection. Built on IBM's Unitxt toolkit, EvalAssist aims to make AI evaluation more rigorous, scalable, and trustworthy for real-world applications.

In the rapidly advancing field of artificial intelligence, data cleaning has become a mission-critical step in ensuring the success of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) architectures. This blog emphasizes the importance of high-quality, structured data in preventing AI model hallucinations, reducing algorithmic bias, enhancing embedding quality, and improving information retrieval accuracy. It covers essential AI data preprocessing techniques like deduplication, PII redaction, noise filtering, and text normalization, while spotlighting top tools such as IBM Data Prep Kit, AI Fairness 360, and OpenRefine. With real-world applications ranging from LLM fine-tuning to graph-based knowledge systems, the post offers a practical guide for data scientists and AI engineers looking to optimize performance, ensure ethical compliance, and build scalable, trustworthy AI systems.

Announcing the Open Trusted Data Initiative (OTDI) draft v0.1 dataset specification...

Open source and open science in AI is a practical, proven approach to enabling access, innovation, trust, and value creation now. Let’s focus on that as we better define it.

The AI Alliance has a released a set of 14 principles covering six areas...

Write once, use anywhere—an open-source tool library for portable AI agents

Discover Docling, the powerful open-source AI document processing tool developed by IBM Research and supported by the AI Alliance, designed for fast, local, and privacy-first workflows. With no reliance on cloud APIs, Docling offers high-quality outputs and flexible licensing, making it ideal for enterprise and research use. Now enhanced by Hugging Face’s SmolVLM models, SmolDocling brings lightweight, multimodal AI to complex document layouts—handling code, charts, tables, and more with precision. Join the growing open-source community transforming document AI and contribute to the future of trusted, efficient, and collaborative AI innovation.