arXiv cs.CL· Shaoang Li, Yanhang Shi, Yufei Li, Mingfu Liang, Frank Shyu, Sandeep Pandey, Luke Simon, Xi Liu, Jian Li·· 12 小时前AI 评分26
ReDiST：面向推理蒸馏的学生条件化轨迹构建框架
Beyond the Answer: Student-Conditioned Trace Construction for Reasoning Distillation
AI 导读
ReDiST 提出一种学生条件化的推理轨迹构建与蒸馏框架，从学生自身的解题草稿出发，依据给定证据修正答案正确的草稿，并借助已验证答案修复失败草稿。冻结的学生匹配阅读器按答案恢复率和验证答案概率对候选轨迹筛选排序，蒸馏时用辅助答案损失平衡轨迹监督与最终答案监督。在问答基准上，ReDiST 在源任务和跨基准测试中均优于仅答案监督、原始轨迹及所评估的轨迹选择与重写基线。
正文 · 原文
Abstract:A reasoning trace can accompany a correct answer without providing effective supervision for a particular student. We study how to construct traces that improve learning beyond answer-only supervision by considering both their intermediate content and their accessibility to the target learner. We introduce ReDiST, a student-conditioned trace-construction and distillation framework for evidence-rich reasoning. Starting from the student's own attempts, ReDiST revises answer-correct drafts against the supplied evidence and repairs unsuccessful drafts with additional guidance from the verified answer. A frozen student-matched reader screens and ranks original and edited candidates using answer recovery and verified-answer probability, given the question, evidence, and candidate trace. We distill the selected targets while balancing trace and final-answer supervision with an auxiliary answer loss. Construction and selection occur offline, and inference uses only the distilled student. Experiments on question-answering benchmarks show that ReDiST can improve both source-task and cross-benchmark performance over answer-only, original-trace, and the evaluated trace-selection and rewriting baselines. Across supervision recipes, performance rankings can differ between source and transfer benchmarks, highlighting the importance of evaluating trace teaching utility across distributions.
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.23831 [cs.CL] |
| (or arXiv:2610.23831v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23831 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jian Li [view email]
[v1]
Fri, 16 Oct 2026 17:52:58 UTC (1,450 KB)
来源：arXiv cs.CL · arxiv.org