通信瓶颈：语言模型中树结构表达式序列化的往返研究
原标题：The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models
AI 摘要
Apple 机器学习研究团队提出一种往返（round-trip）协议，用于评估语言模型在将树结构算术表达式序列化为自然语言时的信息损失。实验对 16 个模型的所有配对组合进行测试，发现该通信信道有损且不对称：交换生成与抽取角色可使准确率变化高达 60.4 个百分点，最佳组合达到 92.9%。至少 73.6% 的失败源于生成端，难度由树结构（运算符数量、深度、右分支）而非模型家族决定；约 3600 条微调样本可提升所有开源权重模型，使其超过未训练的 Gemini-3.1-Pro。
正文节选
The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models AuthorsXavier Suau, Alex Ferrando de las Morenas, Luca Zappella, Samy Bengio When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How much tree-structured compositional content survives this bottleneck? We propose a round-trip protocol that answers this question empirically for tree-structured