llmClassificR update brings full LLM text classification pipeline to pure R
GolinoHudson · x · 2026-10-06
The R package llmClassificR shipped a major update for LLM-based text classification: pure-R JEV-style functions (jevclassify, jevmultilabel, jevrate) with parallel requests, retries and cost reports — no Python needed. Nine LLM classification methods via Grok-compatible Groq include new strict JSON Schema, ensemble voting and self-consistency; every classifier shuffles and chunks texts, validates labels and survives failed chunks. Offline evaluation covers accuracy, macro-F1, kappa, NMI, ECE, Brier, reliability diagrams, temperature/Platt scaling and ROC AUC, plus TF-IDF baselines, learning curves and layer-wise linear probes. Install via devtools::installgithub("hfgolino/llmClassificR").
More from coding & agent
- Codex Auto-review is now free for all: a separate agent approves risky actions for you — reach_vb · 2026-10-06
- Using Claude Design to prototype complex interactions beats static mocks — austin_malerba · 2026-10-06
- AI agent posts user's bank balances to company Slack, sparking agent paradigm debate — altryne · 2026-10-06
- The handoff test: approve, revoke, transfer to a fresh agent—does human authority survive? — tallmetommy · 2026-10-06
- Beam agent one-shots a full end-to-end Unsloth training pipeline in OpenCode with a single prompt — bhutanisanyam1 · 2026-10-06
- Open-source 'Clay killer' launched: 85% cheaper, top people-search accuracy, 25x faster — Scobleizer · 2026-10-06