AI Paper Atlas

Research map / Large language models / AI and society

Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration

Ante Wang, Yujie Lin, Jingyao Liu, Suhang Wu, Hao Liu, Xinyan Xiao, Jinsong Su

AAAI 2026 · Large language models › AI and society · approach: Human-centered trust and agency · 7 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 sampling-based data filtering (ablation)SFT, Qwen3-1.7B (no thinking) · GSM-MCaccuracy: 34.71 -> 38.60Improved
add sampling-based data filtering (ablation)SFT, Qwen3-1.7B (thinking) · GSM-MCaccuracy: 27.20 -> 44.15Improved
add sampling-based data filtering (ablation)RL, Qwen3-1.7B (no thinking) · GSM-MCaccuracy: 55.19 -> 60.82Improved
add sampling-based data filtering (ablation)RL, Qwen3-1.7B (thinking) · GSM-MCaccuracy: 57.09 -> 62.13Improved
enable thinking modevanilla Qwen3-8B · GSM-MCaccuracy: 55.59 -> 44.92Hurt
enable thinking modeRL-trained Qwen3-8B · GSM-MCaccuracy: 81.73 -> 85.53Improved
increase interaction from two to four turnsRL Qwen3-8B (thinking) · GSM-MCaccuracy: 85.53 -> 88.67Improved
add SFT before RLRL Qwen3-8B (no thinking) · GSM-MCaccuracy: 81.73 -> 79.24Hurt
add SFT before RLRL Qwen3-1.7B (no thinking) · GSM-MCaccuracy: 60.82 -> 73.68Improved
apply SFT trainingvanilla Qwen3-1.7B (no thinking) · GSM-MCaccuracy: 0.95 -> 38.60Improved
apply SFT+RL trainingLlama-3.2-3B-Instruct · GSM8Kaccuracy: 64.06 -> 75.74Improved
apply SFT trainingLlama-3.2-3B-Instruct · GSM8Kaccuracy: 64.06 -> 48.60Hurt

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