AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Reflect Then Learn: Active Prompting for Information Extraction Guided by Introspective Confusion

Dong Zhao, Yadong Wang, Xiang Chen, Chenxi Wang, Hongliang Dai, Chuanxing Geng, Shengzhong Zhang, Shao-Yuan Li, Sheng-Jun Huang

AAAI 2026 · Large language models › Language, safety and interpretability · approach: In-context learning analysis · 0 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 pattern prompt (ablation)APIE on DeepSeek-R1-14B · Ablation average (ACE04-NER, CoNLL04 NER, CoNLL04 RE)F1: 34.34 -> 47.63Improved
add format-level uncertainty (ablation)APIE on DeepSeek-R1-14B · Ablation average (ACE04-NER, CoNLL04 NER, CoNLL04 RE)F1: 44.81 -> 47.63Improved
add content-level uncertainty (ablation)APIE on DeepSeek-R1-14B · Ablation average (ACE04-NER, CoNLL04 NER, CoNLL04 RE)F1: 46.12 -> 47.63Improved
add generation disagreement signal (ablation)APIE on DeepSeek-R1-14B · Ablation average (ACE04-NER, CoNLL04 NER, CoNLL04 RE)F1: 42.34 -> 47.63Improved
add pattern prompt (ablation)APIE on DeepSeek-R1-14B · CoNLL04 RE (ablation)F1: 10.66 -> 34.62Improved
add pattern prompt (ablation)APIE on DeepSeek-R1-14B · ACE04-NER (ablation)F1: 32.58 -> 41.95Improved
use APIE exemplars instead of Active-PromptDeepSeek-R1-14B · SciERC REF1: 11.48 -> 13.58Improved
use APIE exemplars instead of random exemplarsGemma-3-12B · IE averageF1: 40.32 -> 40.84Improved
use APIE exemplars instead of random exemplarsQwen-2.5-14B · IE averageF1: 39.04 -> 40.19Improved
use APIE exemplars instead of Active-PromptDeepseek-v3-660B · IE averageF1: 50.17 -> 51.31Improved
use APIE exemplars instead of random exemplarsGemma-3-12B · SciERC REF1: 14.43 -> 16.85Hurt
use APIE exemplars instead of random exemplarsQwen-2.5-14B · SciERC REF1: 19.23 -> 14.11Hurt

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