Lune

EMNLP Findings2021

Devil's Advocate: Novel Boosting Ensemble Method from Psychological Findings for Text Classification

Hwiyeol Jo, Jaeseo Lim, Byoung-Tak Zhang

Abstract

We present a new form of ensemble method-Devil's Advocate, which uses a deliberately dissenting model to force other submodels within the ensemble to better collaborate. Our method consists of two different training settings: one follows the conventional training process (Norm), and the other is trained by artificially generated labels (DevAdv). After training the models, Norm models are fine-tuned through an additional loss function, which uses the DevAdv model as a constraint. In making a final decision, the proposed ensemble model sums the scores of Norm models and then subtracts the score of the De-vAdv model. The DevAdv model improves the overall performance of the other models within the ensemble. In addition to our ensemble framework being based on psychological background, it also shows comparable or improved performance on 5 text classification tasks when compared to conventional ensemble methods.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Related papers

  1. Conformity in Large Language ModelsXiaochen Zhu, Caiqi Zhang, Tom Stafford, Nigel Collier et al.ACL 2025 · 16 citations
  2. GAN Ensemble for Anomaly DetectionXu Han, Xiaohui Chen, Li-Ping LiuAAAI 2021 · 79 citations
  3. DEBATE: Devil's Advocate-Based Assessment and Text EvaluationAlex Kim, Keonwoo Kim, Sangwon YoonACL Findings 2024 · 5 citations
  4. To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier TransformationWanlin Zhang, Weichen Lin, Ruomin Huang, Shihong Song et al.ICLR 2025
  5. Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial RobustnessTuan-Anh Bui, Trung Le, He Zhao, Paul Montague et al.AAAI 2021 · 13 citations
Dusk over the sea between two cliffs drawn in fine vertical lines