arXiv AI July 28, 2026 By Supantho Rakshit, Adele Goldberg, Henry Conklin

Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures

arXiv:2607. 22699v1 Announce Type: new Abstract: As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond limited domains.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 22

Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs

arXiv:2607. 19243v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages.

By Alexander Manev

llms reinforcement-learning robotics benchmarks safety

arXiv AI

Jul 21

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

arXiv:2505. 20161v2 Announce Type: replace-cross Abstract: Effective generalization in language models depends critically on the diversity of their training data.

By Jaehun Jung, Seungju Han, Ximing Lu, Skyler Hallinan, David Acuna, Shrimai Prabhumoye, Mostafa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Yejin Choi

llms benchmarks

arXiv AI

Jun 2

Multilinguality of Large Language Models From a Structural Perspective

arXiv:2606. 01800v1 Announce Type: cross Abstract: Large language models (LLMs) have excelled in processing multiple languages through pre- and post-training on multilingual data, even though English dominates the training data.

By Haruki Sakajo, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

llms

arXiv AI

Jul 7

Beyond Multilingual Averages: MTEB-PT, a Benchmark for Portuguese Sentence Encoders

arXiv:2607. 04071v1 Announce Type: cross Abstract: Portuguese remains underrepresented in text embedding evaluation, despite being one of the most widely spoken languages in the world.

By Lucas Hideki Takeuchi Okamura, Alexandre Alcoforado, Anna Helena Reali Costa

rag fine-tuning benchmarks

arXiv AI

Jun 9

XCR-Bench: Benchmarking Cross-Cultural Reasoning in LLMs via Culture-Specific Items and Hall's Triad

arXiv:2601. 14063v2 Announce Type: replace-cross Abstract: Cross-cultural competence in large language models (LLMs) requires understanding and adapting Culture-Specific Items (CSIs) across varying cultural contexts.

By Mohsinul Kabir, Tasnim Ahmed, Md Mezbaur Rahman, Shaoxiong Ji, Hassan Alhuzali, Yuechen Jiang, Jimin Huang, Sophia Ananiadou

llms nlp benchmarks

arXiv AI

Aug 5

Large Language Models provide support for the parallelogram theory of analogy

arXiv:2603. 19066v2 Announce Type: replace-cross Abstract: Four-term word analogies (A:B::C:D) are classically modeled geometrically as parallelograms: adding the vector B-A+C produces D.

By Qiawen Ella Liu, Raja Marjieh, Jian-Qiao Zhu, Adele E. Goldberg, Thomas L. Griffiths

llms rag fine-tuning safety

Related stories

Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

Multilinguality of Large Language Models From a Structural Perspective

Beyond Multilingual Averages: MTEB-PT, a Benchmark for Portuguese Sentence Encoders

XCR-Bench: Benchmarking Cross-Cultural Reasoning in LLMs via Culture-Specific Items and Hall's Triad

Large Language Models provide support for the parallelogram theory of analogy