{"ID":2823221,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.15296","arxiv_id":"2601.15296","title":"Entropy-Tree: Tree-Based Decoding with Entropy-Guided Exploration","abstract":"Large language models achieve strong reasoning performance, yet existing decoding strategies either explore blindly (random sampling) or redundantly (independent multi-sampling). We propose Entropy-Tree, a tree-based decoding method that exploits entropy as a signal for branching decisions--expanding the search tree only at positions where the model exhibits genuine uncertainty. Entropy-Tree shows superior accuracy and calibration in reasoning tasks: it achieves better pass@k than Multi-chain across multiple models and datasets, and its predictive entropy demonstrates better AUROC compared to several traditional metrics. Entropy-Tree unifies efficient structured exploration and reliable uncertainty estimation within a single decoding procedure.","short_abstract":"Large language models achieve strong reasoning performance, yet existing decoding strategies either explore blindly (random sampling) or redundantly (independent multi-sampling). We propose Entropy-Tree, a tree-based decoding method that exploits entropy as a signal for branching decisions--expanding the search tree on...","url_abs":"https://arxiv.org/abs/2601.15296","url_pdf":"https://arxiv.org/pdf/2601.15296v1","authors":"[\"Longxuan Wei\",\"Yubo Zhang\",\"Zijiao Zhang\",\"Zhihu Wang\",\"Shiwan Zhao\",\"Tianyu Huang\",\"Huiting Zhao\",\"Chenfei Liu\",\"Shenao Zhang\",\"Junchi Yan\"]","published":"2026-01-02T07:14:05Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Language Model\",\"LoRA\"]","has_code":false}