QLoRA Fine-Tuning for Structured JSON Extraction
Fine-tuning a 3B instruct model with QLoRA to produce strict JSON from free-form text — on a single consumer GPU. Exact-match accuracy 0.258 → 0.624.
LLM
LLM Benchmark Evaluation: Multi-Agent Discussion Framework
Rigorous evaluation of a 4-agent discussion pipeline on 7,661 benchmark questions. The framework decreased accuracy on all three benchmarks — an instructive negative result.