ntlm1686/Your-language-model-is-already-a-decision-model

We compared unfinetuned Qwen with Jev on decision accuracy, calibration, and latency, and found comparable accuracy and lower average calibration error without decision-specific fine-tuning.

4 best points · 0 comments · 1 Hacker News post · 7 GitHub stars · View on GitHub

Hacker News discussions

• Your Language Model Is Already a Decision Model (4 points, 0 comments, by ntlm1686, 2026-09-25)