@inproceedings{tao-etal-2026-divergent,
    title = "Divergent Thinking: Escape the Homogeneity Trap in Generative Commonsense Reasoning",
    author = "Tao, Yiheng  and
      Cheng, Kaiwen  and
      Nie, Zhiwei  and
      Liu, Chang  and
      Chen, Jie",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.915/",
    pages = "18395--18410",
    ISBN = "979-8-89176-395-1",
    abstract = "Generative commonsense reasoning (GCR) requires models to synthesize coherent narratives that simultaneously satisfy lexical constraints and commonsense logic. Although ensemble-based LLM strategies are widely adopted to alleviate the fragility of single-chain reasoning, we uncover a counterintuitive homogeneity trap in GCR. Specifically, we observe that increasing the number of reasoning chains can degrade performance, as the generated chains tend to collapse into a narrow semantic region, thereby reinforcing shared biases rather than providing complementary evidence. We posit that escaping this trap requires fundamentally broadening semantic coverage via heterogeneous sources. Our investigation into the nature of diversity reveals that deep semantic diversity, rather than surface-level lexical variation, is the decisive prerequisite for effective integration. Motivated by this insight, we propose an Explore-then-Integrate framework, in which high{--}semantic-entropy explorers capture diverse concept bindings, and a powerful integrator performs compositional synthesis to merge valid fragments into coherent narratives. Crucially, to ensure that the observed performance gains arise from accurate logical composition rather than trivial best-candidate selection, we introduce a provenance-aware evaluation suite that explicitly quantifies the heterogeneous origins of synthesized outputs. Extensive experiments on multiple benchmarks demonstrate the consistent superiority of our approach across a range of metrics. Notably, our method achieves over 10{\%} improvement in overall accuracy on NoRa and in SPICE score on CommonGen-Lite."
}