发表机构
AT&T Chief Data Office; GSMA; RelationalAI; Khalifa University; University of Leeds; Yale University; The University of Texas at Dallas（AT&T首席数据办公室; 全球移动通信系统协会; RelationalAI公司; 哈利法大学; 利兹大学; 耶鲁大学; 德克萨斯大学达拉斯分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究推出开源电信AI资源OTel，含多类任务数据集与30个模型基线，后训练提升三类模型性能，获大量下载与媒体报道，邀请社区共建更强电信大语言模型。
AI 中文摘要
前沿AI模型发展迅速，但仍难以应对电信领域的特定任务。我们推出Open Telco（OTel），这是一个开源电信AI资源，包含用于检索、重排序、指令调优及安全/弃权（不执行）任务的衍生数据集，以及30个全参数后训练基线，覆盖嵌入、重排序和语言模型三大类。截至2026年5月3日，该资源已获得社区的大量参与：发布的模型下载量超1600万次，项目在全球获得157+家媒体报道。OTel基于现有开源电信数据集和基准构建，将有文档记录的电信数据源、预留评估分区、训练好的嵌入模型、重排序器、基于上下文的大语言模型及安全/弃权数据整合为统一资源。OTel的后训练提升了所有三类模型的性能：嵌入检索达到93.5%的NDCG@10，重排序达到0.952的MRR@10，语言模型正确率达到88.2%。我们发布OTel作为可复现的起点，邀请社区扩充数据、改进嵌入和重排序模型，并构建更强的基于上下文的电信大语言模型。
英文摘要
Frontier AI models have advanced rapidly, but they still struggle with telecom-specific tasks. We present Open Telco (OTel), an open telecom AI resource with derived datasets for retrieval, reranking, instruction tuning, and safety/abstention, plus 30 full-parameter post-trained baselines across embedding, reranking, and language models. The community has already engaged substantially with the resource: as of May 3, 2026, the released models have been downloaded over 16 million times, and the project has received 157+ pieces of media coverage worldwide. Building on prior open telecom datasets and benchmarks, OTel provides documented telecom data sources, held-out evaluation partitions, trained embedding models, rerankers, context-grounded LLMs, and safety/abstention data in one unified resource. OTel post-training improves performance across all three model families: embedding retrieval reaches 93.5% NDCG@10, reranking reaches 0.952 MRR@10, and language-model correctness reaches 88.2%. We release OTel as a reproducible starting point and invite the community to expand the data, improve embedding and reranking models, and build stronger context-grounded telecom LLMs.
CommentsAccepted at the ACM AI Leadership Summit, Breakthrough Impact Highlights Track, 2026
