Research
RMIT team achieves track-leading RAG results with open-weight models
Researchers submitted seven retrieval-augmented generation runs to TREC 2026, with open-weight models matching proprietary alternatives on human preference tests despite lower automated coverage scores.
1 min read
Sourcer/arxiv-compression
Ask AI about this articleRMIT's ADM+S team participated in the TREC 2026 Retrieval-Augmented Generation track using the ClimbMix corpus, submitting seven research-agent runs that combined proprietary OpenAI models with open-weight alternatives to test different retrieval strategies and agent workflows. Six of their seven su...
Sign in to read the full analysis
Free account. Full analysis on LLM unit economics, plus the weekly Cost-of-Inference column.
Try it on your own context
You just read the writeup. Now run the thing. Paste a doc or some verbose tool output and watch it shrink — free, no signup.
2,912/12,000 chars
Compressed
Compressed text will appear here…
Method & sources
- Source type
- Primary publication (lab/vendor blog) — our analysis + implication
- Source link
- r/arxiv-compression
- Published
- UTC
- Byline
- By the gotcontext.ai team (editorial standards)
- Correction?
- corrections@gotcontext.ai