Share your thoughts, 1 month free Claude Pro on usSee more

Bias Mitigation in Text Generation on BiasBench toxic prompts

13.119Perplexity

Qwen-Prec-trig

Updated 1mo ago

Evaluation Results

Method	Links
Qwen-Prec-trig 2026.03		13.119	0.307	0.349	0.706	0.276	0.443	0.256	0.839
Qwen-Prec-notrig 2026.03		13.46	0.303	0.362	0.73	0.277	0.456	1	0.991
Qwen-3-4B 2026.03		13.491	0.298	0.359	0.713	0.284	0.452	-	-
Qwen-SGD 2026.03		13.498	0.298	0.364	0.723	0.292	0.46	0.262	5.72
Qwen-Prec-trig-2 2026.03		13.877	0.293	0.343	0.69	0.279	0.437	0.778	0.403
DeepSeek-8B 2026.03		21.361	0.255	0.31	0.729	0.324	0.454	-	-
Self-correction 2026.03		22.092	0.262	0.268	0.757	0.287	0.437	-	-
Qwen-ADAMW 2026.03		22.749	0.304	0.365	0.754	0.285	0.468	0.29	5.276
DS-8B-debiased 2026.03		22.894	0.256	0.34	0.744	0.33	0.471	-	-
Mistral 2026.03		212.5	0.275	0.397	0.807	0.372	0.525	-	-