AI Paper Atlas

Research map / Large language models / Agents, code and math

Counterfactual-based Cognitive Alignment In-Context Learning for Relation Extraction

Qibin Li, Shengyuan Bai, Nai Zhou, Nianmin Yao

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 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 counterfactual generation and cognitive-pattern selection (CCA)BERT+PURE ICL, LLaMA2-7B · SciERC 50-shotmicro F1: 16.77 -> 22.24Improved
add CCABERT+PURE ICL, Qwen2.5-72B · SemEval 50-shotmicro F1: 77.17 -> 80.15Improved
add CCA to Random backboneRandom ICL, LLaMA2-7B · SemEvalmicro F1: 49.31 -> 51.94 (50-shot); 49.11 -> 49.17 (10-shot)No clear effect
add CCA to Random backboneRandom ICL, Qwen2.5-7B · TACRED 20-shotmicro F1: 24.93 -> 24.23Hurt
add CCA to Random backboneRandom ICL, Qwen2.5-72B · SemEval 10-shotmicro F1: 64.31 -> 63.11Hurt
add CCA to Claude 3.5 Random backboneRandom ICL, Claude 3.5 · SemEvalmicro F1: 59.21 -> 59.28 (5-shot); 63.87 -> 63.79 (10-shot)No clear effect
use CCA instead of Self-ConsistencyQwen2.5-72B BERT+PURE · SemEval 5-shotmicro F1: 69.97 -> 70.26Improved
add all three counterfactual generation methods (ablation)CCA, LLaMA2-7B SimCSE · SemEval 5-shotmicro F1: 57.33 -> 60.97Improved
add counterfactual structural variation (ablation)CCA, LLaMA2-7B SimCSE · SemEval 5-shotmicro F1: 59.03 -> 60.97Improved
add counterfactual conceptual substitution (ablation)CCA, LLaMA2-7B SimCSE · SemEval 5-shotmicro F1: 60.27 -> 60.97Improved
add cognitive processing pattern to semantic embedding with counterfactual generation (ablation)CCA, LLaMA2-7B SimCSE · SemEval 5-shotmicro F1: 59.76 -> 60.97Improved
use cognitive-pattern features alone instead of semantic embedding (ablation)LLaMA2-7B SimCSE · SemEval 5-shotmicro F1: 57.33 -> 55.17Hurt

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