arXiv：cs.CL· Xin Li, Mengbing Liu, Hao Jiang, Xin Gao, Annan Wang, Xingwei Qu, Yichi Zhang, Chau Yuen·· 7 小时前
SYNC：无需训练，让不同语言模型通过共享词索引通信
Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models
AI 导读
研究者提出 SYNC（Symbol-Indexed Neural Communication），一种词索引接口，无需微调或学习翻译器即可连接异构语言模型：发送方从共享词表选词并发送索引，接收方用自己的词方向将描述写入隐状态。在 5 个模型家族的 9 个新接收方上，四答案任务成功率 72.0-98.3%，最高比中间层写入高 96 个百分点；无任务探针提前预测可用深度达 45/45。
正文
Abstract:Multi-agent systems allow language models to solve tasks collaboratively by sharing complementary information. These systems typically communicate through text, while recent approaches also explore exchanging internal model states. However, sharing these states across architectures often requires learned translators or assumptions about model compatibility. We introduce SYNC (Symbol-Indexed Neural Communication), a word-indexed interface that connects heterogeneous models without fine-tuning or a learned translator. From descriptions only it can see, the sender selects words from a shared list and sends their indices for each object, without seeing the questions. The receiver writes the described facts into its hidden states using its own word directions, vectors fitted once from its activations. We test selective use by swapping one attribute between two objects and requiring correct answers about both changed and unchanged attributes before and after the swap, four answers in total. We choose an early write layer on four development receivers and then fix it. With three different senders and nine newer receivers from five families, four-answer success on new scenes reaches 72.0-98.3%, up to 96 percentage points above middle-layer writing, and the two largest receivers match plain text. A task-free probe predicted in advance which depths each new receiver can use (45 of 45 cases). Without retuning, messages listing every fact keep 89.6-100% success under new layouts, and sender messages reach 23.9-64.0% on a landmark task with multi-token symbols, below text but from 0% without a message. These results show that shared word indices and receiver-local directions can support selective fact use across model families without additional training.
| Comments: | Project page: this https URL Code: this https URL Data: this https URL |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.19696 [cs.CL] |
| (or arXiv:2610.19696v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19696 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xin Li [view email]
[v1]
Wed, 14 Oct 2026 07:19:43 UTC (5,580 KB)
来源：arXiv：cs.CL · arxiv.org