cs.LGOct 30, 2026

Corroborative Learning: Mutual Enhancement through Task-Response Reconstruction

Authors: Zexing Zhang, Jichao Li, Tianyang Lei, Yiyin Zhang, Kewei Yang

Organizations: College of Systems Engineering, National University of Defense Technology, Changsha 410073, China

Abstract

In pattern analysis, models trained independently for the same task often develop complementary capabilities through differences in architecture, data, and optimization. Exploiting complementarity while retaining independent deployment is central to collaborative learning. Most methods establish transfer by reducing differences in predictions, relations, or representations between target and collaborator, although these differences also underlie complementarity. This creates a structural trade-off between reducing differences for knowledge exchange and preserving them for complementarity. We therefore propose Corroborative Learning (CL). Each model forms task-driven responses, with cross-group support from its collaborator. Source-excluded reconstruction of response increments from collaborator representations separates fitting and evaluation across disjoint groups and selectively constrains directions by cross-group reconstructability. The process requires no direct output or feature matching or additional inference dependency. Furthermore, with linear reconstruction and fixed collaborator representations, the loss equals a positive semidefinite directional regularizer, constraining less reconstructable directions more strongly. Signal and noise conditions characterize when directional shrinkage reduces response-estimation error. Across six language tasks, 24 models, and 36 pairs, CL improves over capacity-matched independent adaptation on every task, with positive gains across most directed model combinations. Pairwise comparisons show broad advantages over transfer and mutual-learning methods and different gains from complementarity across collaboration rules. Low-label language and vision results support cross-domain applicability. Task-relevant differences can support mutual enhancement without eliminating disagreement.

Figures & tables

Explore similar work

CardsList
  1. Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning

    Oct 12, 2026Shangbin Feng, Yulia Tsvetkov, Jan Kautz +1Multi-LLM CollaborationRL for Language Models

  2. Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses

    Oct 9, 2026Fanzhi Zeng, Anubrata Das, Maytal Saar-Tsechansky +1Human-AI CollaborationTheory of Mind

  3. Watch Where You Linearize: Predicting and Correcting Model-Merging Interference

    Nov 18, 2026Ido Nitzan Hidekel, Dan RavivModel MergingTask Vector Merging