Tag
用户表达对开源 LLM 生态的赞叹，提到下载了 Raon-1-mini 30B A4B 和 Flint 40B A2.5B 等多国开源模型，并对能与计算机自然对话感到惊喜。
QuanLing 论文将基于预训练语言模型的语言距离量化框架扩展到西罗曼语族（法语、葡萄牙语、西班牙语、意大利语），通过 LaBSE 嵌入距离、分词碎片化率和 mBERT 掩码预测进行跨语支验证，发现葡西最近、法意最远，且框架具有跨语支泛化能力。
The paper presents a structural circuit analysis to identify first-token broadcasters and language-identity heads in multilingual language models, revealing consistent hub topologies and that routing circuitry is primarily established during pre-training.
This paper presents the DFKI-MLT system for SemEval-2026 Task 7 on cultural awareness, which applies activation steering to multilingual LLMs using language vectors from parallel FLORES data. The system achieved 86.96% accuracy in the MCQ track, ranking 7th out of 17 teams, and post-hoc analyses reveal that gains are layer-sensitive and vary across language-region pairs.
Researchers introduce CSR-L and CS-MTEB benchmarks showing that code-switching queries degrade IR system performance by up to 27%, revealing embedding-space divergence that current multilingual techniques cannot fix.