<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/gsm8k-evaluating-mathematical-reasoning-in-language-models</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/background-and-motivation</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/dataset-structure-and-problem-characteristics</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/chain-of-thought-evaluation</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/accuracy-metrics-for-gsm8k</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/process-supervision-vs-outcome-supervision</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/worked-example-tracing-a-multi-step-reasoning-chain</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/code-implementation-evaluating-models-on-gsm8k</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/key-evaluation-parameters</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/limitations-and-challenges</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/impact-on-language-model-development</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/summary</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/gsm8k-evaluating-mathematical-reasoning-language-models/quiz</loc><lastmod>2026-03-01T14:30:00.000Z</lastmod></url></urlset>