<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Rafael Macalaba — Writing</title><description>Research, engineering, and applied AI.</description><link>https://rafmacalaba.github.io/</link><language>en-us</language><item><title>Beyond chat demos: evaluating LLM systems at scale with DeepEval</title><link>https://rafmacalaba.github.io/blog/wb-deepeval-evals/</link><guid isPermaLink="true">https://rafmacalaba.github.io/blog/wb-deepeval-evals/</guid><description>World Bank Open Data blog post on an automated, persona-driven evaluation framework for multi-turn LLM assistants, built on DeepEval.</description><pubDate>Wed, 21 Oct 2026 00:00:00 GMT</pubDate></item><item><title>armada: orchestrating AI agent teams with evidence gates</title><link>https://rafmacalaba.github.io/blog/armada-intro/</link><guid isPermaLink="true">https://rafmacalaba.github.io/blog/armada-intro/</guid><description>Introducing armada, an open-source tool that splits coding work into evidence-gated phases and dispatches specialist subagents.</description><pubDate>Mon, 10 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval</title><link>https://rafmacalaba.github.io/blog/arxiv-2606-30473/</link><guid isPermaLink="true">https://rafmacalaba.github.io/blog/arxiv-2606-30473/</guid><description>Permutation-invariant fine-tuning approach for embedding models applied to structured metadata retrieval.</description><pubDate>Mon, 15 Jun 2026 00:00:00 GMT</pubDate></item><item><title>AI for Monitoring and Classifying Data Used in Research Literature</title><link>https://rafmacalaba.github.io/blog/arxiv-2605-30582/</link><guid isPermaLink="true">https://rafmacalaba.github.io/blog/arxiv-2605-30582/</guid><description>Methods for AI-assisted monitoring of how datasets appear in published research, including classification of usage context.</description><pubDate>Fri, 15 May 2026 00:00:00 GMT</pubDate></item><item><title>Tracking Dataset Use at Scale with AI: How Synthetic Data Helps</title><link>https://rafmacalaba.github.io/blog/wb-tracking-dataset-use/</link><guid isPermaLink="true">https://rafmacalaba.github.io/blog/wb-tracking-dataset-use/</guid><description>World Bank Open Data blog post on using synthetic data and AI to track dataset citations at scale.</description><pubDate>Sun, 01 Jun 2025 00:00:00 GMT</pubDate></item><item><title>Large Language Models and Synthetic Data for Monitoring Dataset Mentions in Research Papers</title><link>https://rafmacalaba.github.io/blog/arxiv-2502-10263/</link><guid isPermaLink="true">https://rafmacalaba.github.io/blog/arxiv-2502-10263/</guid><description>Workshop paper at ICLR 2025 using LLMs and synthetic data to detect and classify dataset citations in research literature.</description><pubDate>Mon, 28 Apr 2025 00:00:00 GMT</pubDate></item><item><title>Climate Change AI track paper (ICLR 2025)</title><link>https://rafmacalaba.github.io/blog/climate-change-ai-iclr2025/</link><guid isPermaLink="true">https://rafmacalaba.github.io/blog/climate-change-ai-iclr2025/</guid><description>Climate Change AI track paper presented at ICLR 2025, addressing dataset monitoring in climate research.</description><pubDate>Tue, 15 Apr 2025 00:00:00 GMT</pubDate></item></channel></rss>