AI Paper Atlas

Research map / Large language models / AI and society

Dancing in Chains: Strategic Persuasion in Academic Rebuttal via Theory of Mind

Zhitao He, Zongwei LYU, Yi R. Fung

ICLR 2026 · Large language models › AI and society · approach: Human-centered trust and agency

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 ToM analysis to training data (ablation)RebuttalAgent · R2-test (in-domain)average holistic score: 9.04 -> 9.42Improved
add strategy to training data (ablation)RebuttalAgent · R2-test (in-domain)average holistic score: 9.31 -> 9.42Improved
add thinking to training data (ablation)RebuttalAgent · R2-test (in-domain)average holistic score: 9.37 -> 9.42Improved
add RL after SFT instead of SFT-only (ablation)RebuttalAgent · R2-test (in-domain)average holistic score: 8.27 -> 9.42Improved
add SFT before RL instead of RL-only (ablation)RebuttalAgent · R2-test (in-domain)average holistic score: 8.79 -> 9.42Improved
use SFT+RL instead of DPO (ablation)RebuttalAgent · R2-test (in-domain)average holistic score: 8.68 -> 9.42Improved
add response reward (ablation)RebuttalAgent · R2-test (in-domain)average holistic score: 8.63 -> 9.42Improved
add analysis reward (ablation)RebuttalAgent · R2-test (in-domain)average holistic score: 9.23 -> 9.42Improved
add format reward (ablation)RebuttalAgent · R2-test (in-domain)average holistic score: 9.32 -> 9.42Improved
use Rebuttal-RM reward as the scorer instead of self-reward (ablation)RebuttalAgent · R2-test (in-domain)average holistic score: 9.42 -> 9.45No clear effect
apply framework to Llama-3.1-8BRebuttalAgent · R2-test (in-domain)average holistic score: 7.44 -> 9.20Improved
apply framework to Qwen3-4BRebuttalAgent · R2-test (in-domain)average holistic score: 7.69 -> 8.98Improved

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