Tagged articles

cross-lingual retrieval

2 articles · Page 1 of 1

Alibaba International Intelligent Technology

May 15, 2026 · Artificial Intelligence

LiRA: A Linguistic Robust Anchoring Framework for Low-Resource Cross-Lingual LLM Retrieval

LiRA introduces a dual‑module framework—Arca for anchored representation composition and LaSR for language‑coupled semantic reasoning—backed by theoretical guarantees and extensive experiments that markedly improve multilingual retrieval, similarity, and reasoning performance on low‑resource languages, including a new LazRetrieval benchmark.

Deep Learningcross-lingual retrievalinformation retrieval

0 likes · 28 min read

LiRA: A Linguistic Robust Anchoring Framework for Low-Resource Cross-Lingual LLM Retrieval

Tencent Technical Engineering

Apr 22, 2025 · Artificial Intelligence

Conan-Embedding-V2: A 1.4B LLM‑Based Multilingual Embedding Model Achieving SOTA on MTEB

Conan‑Embedding‑V2, a newly trained 1.4 B‑parameter LLM with a custom tokenizer, 32 k token context, SoftMask, cross‑lingual retrieval data and dynamic hard‑negative mining, delivers state‑of‑the‑art multilingual embeddings that surpass larger models on both English and Chinese MTEB benchmarks while remaining compact and fast.

EmbeddingMTEBMultilingual

0 likes · 14 min read

Conan-Embedding-V2: A 1.4B LLM‑Based Multilingual Embedding Model Achieving SOTA on MTEB