发表机构
KAIST AI; Sentient Labs; Princeton University; Rice University; University of Texas, Austin; University of Washington（韩国科学技术院人工智能研究院; Sentient实验室; 普林斯顿大学; 莱斯大学; 德克萨斯大学奥斯汀分校; 华盛顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出表示对齐的辅助监督方法，利用环境派生任务提升语言模型在结构化领域（如国际象棋）的适配性能，显著改善最优动作预测和评论生成。
AI 中文摘要
语言模型展现出强大的推理能力，但将其适配到结构化领域仍然具有挑战性，且可能产生不一致的结果。我们识别出表示兼容性——模型有效处理结构化任务表示的程度——是适配中的关键因素。我们在国际象棋中对此进行研究，国际象棋提供了一个受控的测试平台，具有精确的语义、可计算的最优动作和多种状态表示，包括符号编码（FEN）和空间格式（ASCII）。我们发现，模型通常对语义等价的输入处理方式差异显著，影响学习和泛化。基于这一观察，我们提出表示对齐的辅助监督，利用以兼容表示表达的环境派生任务来改善对结构化领域的适配。跨模型和表示，辅助监督在相同目标数据下，相对于仅目标训练，持续提高最优动作预测。暴露环境动态的任务比表面或静态监督提供更大且更一致的收益，同时与大幅增加目标任务数据量保持竞争力。此外，ASCII训练的模型比FEN训练的模型更有效地迁移到FEN，甚至在FEN评估上超过了仅FEN目标训练的基线。这些收益还扩展到开放式、基于事实的评论生成，而不仅限于最优动作预测。总体而言，我们的结果表明，在模型兼容表示中的辅助监督能够实现结构化领域的有效适配。
英文摘要
Language models exhibit strong reasoning capabilities, yet adapting them to structured domains remains challenging and can yield inconsistent outcomes. We identify representation compatibility, the extent to which a model effectively processes a representation for a structured task, as a key factor in adaptation. We study this in chess, which provides a controlled testbed with precise semantics, computable optimal actions, and multiple state representations, including a symbolic encoding (FEN) and a spatial format (ASCII). We find that models often process semantically equivalent inputs substantially differently, affecting both learning and generalization. Building on this observation, we propose representation-aligned auxiliary supervision, which uses environment-derived tasks expressed in compatible representations to improve adaptation to structured domains. Across models and representations, auxiliary supervision consistently improves optimal-move prediction relative to target-only training under identical target data. Tasks that expose environment dynamics provide larger and most consistent gains than surface-level or static supervision, while remaining competitive with substantially increasing the amount of target-task data. Moreover, ASCII-trained models transfer more effectively to FEN than FEN-trained models do to ASCII, even surpassing the FEN target-only baseline on FEN evaluation. The gains also extend beyond optimal-move prediction to open-ended, factually grounded commentary generation. Overall, our results show that auxiliary supervision in model-compatible representations can enable effective adaptation in structured domains.
CommentsNeurIPS 2026 Workshop on LP4FM Oral
