@inproceedings{cui-etal-2026-mind,
    title = "{MIND}: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective {C}o{T} Distillation",
    author = "Cui, Jin  and
      Guo, Jiaqi  and
      Zhou, Jiepeng  and
      Yang, Ruixuan  and
      Lu, Jiayi  and
      Xu, Jiajun  and
      Song, Jiangcheng  and
      Zhao, Boran  and
      Ren, Pengju",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2020/",
    pages = "43622--43636",
    ISBN = "979-8-89176-390-6",
    abstract = "While Large Language Models (LLMs) have emerged with remarkable capabilities in complex tasks through Chain-of-Thought (CoT) reasoning, practical resource constraints have sparked interest in transferring these abilities to smaller models. However, achieving both domain performance and cross-domain generalization remains challenging. Existing approaches typically restrict students to following a single golden rationale and treat different reasoning paths independently. Due to distinct inductive biases and intrinsic preferences, alongside the student{'}s evolving capacity and reasoning preferences during training, a teacher{'}s ``optimal'' rationale could act as out-of-distribution noise. This misalignment leads to a degeneration of the student{'}s latent reasoning distribution, causing suboptimal performance. To bridge this gap, we propose MIND, a capability-adaptive framework that transitions distillation from passive mimicry to active cognitive construction. We synthesize diverse teacher perspectives through a novel ``Teaching Assistant'' network. By employing a novel Feedback-Driven Inertia Calibration mechanism, this network utilizes inertia-filtered training loss to align supervision with the student{'}s current adaptability, effectively enhancing performance while mitigating catastrophic forgetting. Extensive experiments demonstrate that MIND achieves state-of-the-art performance on both in-distribution and out-of-distribution benchmarks, and our sophisticated latent space analysis further confirms the mechanism of reasoning ability internalization."
}