AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Selective Weak-to-Strong Generalization

Hao Lang, Fei Huang, Yongbin Li

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 2 citations (OpenAlex)

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
add P(IK) classifier for selective labels (ablation)selective W2SG · SciQ (Qwen-1.8B weak)accuracy: 89.86 -> 90.60Improved
add P(IK) classifier for selective labels (ablation)selective W2SG · CosmosQA (Qwen-1.8B weak)accuracy: 81.36 -> 83.85Improved
add graph-smoothed weak labels (ablation)selective W2SG · CosmosQA (Qwen-1.8B weak)accuracy: 83.12 -> 83.85Improved
add graph-smoothed weak labels (ablation)selective W2SG · BoolQ (Qwen-1.8B weak)accuracy: 83.11 -> 83.39Improved
use selective labels instead of multi-task P(IK) head (ablation)selective W2SG · SciQ (Qwen-1.8B weak)accuracy: 89.98 -> 90.60Improved
replace naive finetuning with selective W2SGQwen-14B student · SciQ (GPT-2 weak)accuracy: 77.90 -> 83.30Improved
replace naive finetuning with selective W2SGQwen-14B student · BoolQ (GPT-2 weak)accuracy: 65.89 -> 68.64Improved
replace auxiliary confidence loss with selective W2SGQwen-14B student · BoolQ (GPT-2 weak)PGR: -10.76 -> 14.92Improved
replace auxiliary confidence loss with selective W2SGQwen-14B student · CosmosQA (Qwen-1.8B weak)PGR: 20.87 -> 44.57Improved
add auxiliary confidence loss to naive finetuningQwen-14B student · BoolQ (GPT-2 weak)accuracy: 65.89 -> 62.22Hurt
train P(IK) on CosmosQA instead of Winograde (ablation)selective W2SG · SciQaccuracy: 89.80 -> 90.70Improved
train P(IK) on ARC instead of CosmosQA (ablation)selective W2SG · BoolQaccuracy: 83.20 -> 83.39Improved

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