Our new X account is live! Follow @wizwand_team for updates

LLM Alignment on UltraFeedback (in-domain)

80.6Win Rate (KL, alpha=1)

GEB-π

Updated 4d ago

Evaluation Results

Method	Links
GEB-π 2025.09		80.6	0.7531	74.41	0.6723	51.75	0.5986
GEB-1/π 2025.09		79.69	0.7614	73.87	0.6342	51.86	0.6088
GEB-arctanh(π − 1) 2025.09		79.6	0.7544	74.57	0.6642	51.69	0.5962
f-DPO 2025.09		77.49	0.7426	72.7	0.6488	50.83	0.5902
GEB-arctanh(π − 1) 2025.09		74.55	0.8032	72.57	0.7902	68.34	0.7612
GEB-1/π 2025.09		74.36	0.8084	72.28	0.7733	67.99	0.7618
GEB-π 2025.09		73.9	0.8048	72.08	0.7921	67.79	0.7698
f-DPO 2025.09		72.89	0.7926	71.19	0.7915	66.62	0.7566