arXiv:2601.21225v4 Announce Type: replace-cross Abstract: Large language models have made substantial progress in mathematical reasoning. However, benchmark development for multilingual evaluation ha...
arXiv:2607. 05992v1 Announce Type: cross Abstract: Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heavily biased toward high-resource languages, with English and Chinese dominating both pre-training corpora and evaluation suites.
The study investigates the performance gap between native-language reasoning and English-pivoted reasoning in large language models. By creating extensive multilingual reasoning datasets and fine‑tuning specialists on Qwen/Qwen3-8B-Base, the authors find that the native reasoning gap is much smaller (1.9–3.5%) than previously reported. They analyze weight‑space changes, discover a language‑agnostic reasoning core in the middle layers, and propose a Layer Swap technique that transfers these mid‑layer updates from an English specialist to native specialists, effectively closing most of the gap while maintaining native chain‑of‑thought output.
The paper investigates how mathematical reasoning improvements from Reinforcement Post-Training (RPT) in English-centric large language models (LLMs) transfer to other languages. Experiments show that transfer varies greatly depending on the initial model, target language, and training approach, and that stronger English initialization does not guarantee better transfer efficiency. Adding a single parallel language to the training data yields the largest boost, with additional languages providing smaller but consistent gains.
arXiv:2607. 23058v1 Announce Type: cross Abstract: Multilingual reasoning evaluation overwhelmingly relies on translating English benchmarks, a practice that introduces linguistic artifacts and fails to test culturally-grounded reasoning.
arXiv:2608. 03882v1 Announce Type: cross Abstract: Geospatial reasoning, i.
arXiv:2609.22796v1 Announce Type: new Abstract: Dialectal Arabic machine translation (MT) remains challenging despite recent progress in Arabic language technologies, particularly because effective t...
arXiv:2609.10445v1 Announce Type: new Abstract: Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: m...
EDRAC is the first large‑scale benchmark for dialectal Arabic machine reading comprehension and generative question answering, covering five major dialects—Egyptian, Moroccan, Emirati, Syrian, and Saudi. It contains 499 passages from naturally spoken interactions and 4,977 QA pairs produced via a human–LLM collaborative pipeline. The benchmark evaluates Arabic‑centric and multilingual large language models, revealing gaps between semantic answer quality and dialectal fidelity and underscoring limitations of current evaluation metrics for dialectal Arabic generation.
arXiv:2608.30463v1 Announce Type: new Abstract: Solvability detection is one of the most challenging aspects of mathematical reasoning for Large Language Models (LLMs). While prior work has studied t...
arXiv:2610.20221v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed across languages, yet their safety and reasoning capabilities remain predominantly evaluated in...
arXiv:2609.16006v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly serve users whose expectations are shaped by their cultural context, yet most cultural evaluations test wha...