通过模拟解题过程对齐数据轨迹，提升电信数学领域小模型性能。
Data Trajectory Alignment for LLM Domain Adaptation: A Two-Phase Synthesis Framework for Telecommunications Mathematics
- 分两阶段合成数据：先生成多样化答案，再改写为符合目标学生认知风格的解题路径。
- 在TELEMATH数据集上达72.45%准确率，比蒸馏训练高17.65点，优于带思维模式的Qwen3-32B。
- 适合资源受限场景，兼顾精度与推理效率，尤其适用于边缘设备部署。
通用大语言模型在电信等垂直领域应用受限于低信息密度、稀缺语料及移动/边缘设备的严格约束。本文提出数据轨迹对齐（DTA）框架，一种无需依赖特定模型的两阶段数据整理方法，将解题过程而非仅最终答案作为监督信号。第一阶段（初始化）利用多个强教师模型生成多样化、高覆盖度候选解。第二阶段（DTA）重写教师解法，使其中间步骤与呈现风格匹配目标学生的归纳偏置，并通过一致性检查和反思判断实现信号感知的示范样本选择。在电信数学任务（如链路预算、信噪比/调制选择、功率控制可行性）中，DTA在不启用显式“思考”模式下达到TELEMATH数据集上72.45% pass@1，相比仅蒸馏训练提升17.65个百分点，超越启用思考模式的Qwen3-32B基准2.94个百分点。词移分析表明，性能提升集中于逻辑结构标记而非仅堆叠领域术语，说明推理骨架得到优化。在边缘推理设置下，DTA减少多样本投票依赖，禁用昂贵推理启发式，使每输出词能耗降低约42%，端到端延迟减少约60%。结果表明，对齐解题生成过程可实现紧凑高效的高质量监督，为低资源垂直领域的模型适配提供实用方案。
原文摘要 · Abstract (English)
General-purpose large language models (LLMs) are increasingly deployed in verticals such as telecommunications, where adaptation is hindered by scarce, low-information-density corpora and tight mobile/edge constraints. We propose Data Trajectory Alignment (DTA), a two-phase, model-agnostic data curation framework that treats solution processes - not only final answers - as first-class supervision. Phase I (Initializing) synthesizes diverse, high-coverage candidates using an ensemble of strong teachers. Phase II (DTA) rewrites teacher solutions to align intermediate steps and presentation style with the target student's inductive biases and then performs signal-aware exemplar selection via agreement checks and reflection-based judging. Instantiated on telecommunications mathematics (e.g., link budgets, SNR/AMC selection, and power-control feasibility), DTA yields state-of-the-art (SOTA) accuracy on TELEMATH without enabling explicit "thinking" modes: 72.45% pass@1, surpassing distilled-only training by +17.65 points and outperforming a strong baseline (Qwen3-32B with thinking enabled) by +2.94 points. Token-shift analyses indicate that DTA concentrates gains on logical-structural discourse markers rather than merely amplifying domain nouns, indicating improved reasoning scaffolding. Under edge-like inference settings, DTA improves efficiency by reducing reliance on multi-sample voting and disabling expensive reasoning heuristics, cutting energy per output token by ~42% versus Qwen3-32B (thinking mode enabled) and end-to-end latency by ~60% versus Qwen3-32B (thinking mode disabled). These results demonstrate that aligning how solutions are produced enables compact, high-yield supervision that is effective for both accuracy and efficiency, offering a practical recipe for domain adaptation in low-resource verticals beyond telecom.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。