arXiv cs.CL· Kyuyoung Kim, Peiyao Sheng, Ashwin Hebbar, Peiyang Xu, Yunfei Xie, Kevin Wang, Rui Xin, Chen Wei, Zhangyang Wang, Jinwoo Shin, Pramod Viswanath, Sewoong Oh·· 14 小时前AI 评分31
表征对齐的辅助监督：提升语言模型在结构化领域的适配能力
Representation-Aligned Auxiliary Supervision for Language Model Adaptation
AI 导读
研究者提出“表征对齐的辅助监督”，用与环境兼容的表征表达任务来提升语言模型在结构化领域的适配效果。在国际象棋测试中，该方法在相同目标数据下持续改善最优走子预测，暴露环境动态的任务收益大于表层或静态监督。ASCII 训练的模型向 FEN 迁移的效果优于反向迁移，甚至超过 FEN 目标-only 基线，收益还扩展到开放式、事实有据的解说生成。
正文 · 原文
Authors:Kyuyoung Kim, Peiyao Sheng, Ashwin Hebbar, Peiyang Xu, Yunfei Xie, Kevin Wang, Rui Xin, Chen Wei, Zhangyang Wang, Jinwoo Shin, Pramod Viswanath, Sewoong Oh
Abstract: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.
| Comments: | NeurIPS 2026 Workshop on LP4FM Oral |
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.04098 [cs.CL] |
| (or arXiv:2610.04098v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.04098 arXiv-issued DOI via DataCite |
Submission history
From: Kyuyoung Kim [view email]
[v1]
Fri, 2 Oct 2026 22:04:12 UTC (198 KB)
[v2]
Sat, 24 Oct 2026 18:56:10 UTC (198 KB)
来源：arXiv cs.CL · arxiv.org