Find a story

Search Spins

Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.

4 results for “cross-lingual”

SPIN Unprocessed News

DonorRank: Donor Language Selection for Low-Resource Cross-Lingual Speech Recognition

arXiv:2608.11441v1 Announce Type: new Abstract: Low-resource automatic speech recognition (ASR) commonly relies on cross-lingual transfer, where models are adapted from higher-resource donor languages. However, selecting donors remains challenging for spontaneous speech from under-resourced language communities, due to linguistic variation, evolving orthographic conventions, and uneven resource availability. We present DonorRank, a learning-to-rank framework for predicting effective donor langua

arXiv Computation and Language

Aug 13, 2026

SPIN Processed News Frame: The Hype

Rationale-Guided Knowledge Distillation for Cross-Lingual Stance Detection

A new research paper proposes a rationale-guided knowledge distillation framework to improve cross-lingual stance detection for low-resource languages by distilling Chain-of-Thought reasoning from large language models into smaller, deployable student models.

Spin 40% Claim Present in Source AI Risk Moderate
arXiv Computation and Language

Jul 22, 2026

SPIN Processed News Frame: The Hype

Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAG

Researchers propose TR-RAG, a teacher-regularized reinforcement learning method to improve cross-lingual RAG performance when users query in non-English languages but retrieved evidence remains English — addressing language drift and unreliable evidence usage.

Spin 65% Claim Present in Source AI Risk Moderate
arXiv Computation and Language

Jul 8, 2026

SPIN Processed News Frame: The Hype

ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs

Researchers introduced ALEE, a new cross-lingual evaluation framework for text embeddings that uses English-centric minimal pairs grounded in Abstract Meaning Representations to assess semantic fidelity across 275+ languages — addressing longstanding limitations in static, narrow, and overfit embedding benchmarks.

Spin 45% Claim Present in Source AI Risk Moderate
arXiv Computation and Language

Published Jul 2, 2026 · Analyzed Jul 5, 2026