AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

On Fairness of Task Arithmetic: The Role of Task Vectors

Laura Gomezjurado Gonzalez, Hiroki Naganuma, Kotaro Yoshida, Takafumi Horie, Yuji Naraki, Ryotaro Shimizu

ICLR 2026 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use task addition (lambda>=0.3) instead of FFT/LoRALLaMA-2-7B · Berkeley D-Lab hate speech (gender)DPD / EODImproved
set lambda in 0.0-0.2 range (ablation)task addition · Berkeley D-Lab hate speech (gender)accuracy vs DPD/EODMixed
use task addition instead of SFT/LoRADistilBERT · Civil Comments (gender)worst DPD / EOD: worst-DPD 0.0735--0.0812 (LoRA) -> 0.0454; worst-EOD 0.5024--0.5084 -> 0.3358; accuracy 0.9447--0.9453 -> 0.9395Improved
use task addition instead of SFT/LoRADistilBERT · Civil Comments (race)worst DPD / EOD: worst-DPD 0.0987--0.0995 (SFT) -> 0.0580; worst-EOD 0.2568--0.3544 -> 0.1289Improved
use task addition instead of LoRAQwen2.5-0.5B · Civil Comments (gender)accuracy and DPD/EOD: accuracy 0.774--0.790 -> 0.810--0.820; EOD 0.232--0.362 -> 0.130--0.143Improved
use task addition instead of SFTQwen2.5-0.5B · Civil Comments (gender)accuracy and EOD: accuracy 0.884--0.886 -> 0.810--0.820; EOD 0.060--0.084 -> 0.130--0.143Hurt
inject Men or Asian subgroup task vector into FFT model (ablation)FFT LLaMA-2-7B · Berkeley D-Lab (gender / race)DPD / EODImproved
inject Native American subgroup task vector into FFT model (ablation)FFT LLaMA-2-7B · Berkeley D-Lab (race)DPD / EODHurt
use task addition instead of FFTLLaMA-2-7B · Berkeley D-Lab subgroupssubgroup fairness: improves in 5 of 7 gender and 3 of 8 race subgroupsMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy