Show Your Work in Swahili: Reinforcement Learning for Native-Language Mathematical Reasoning
cs.CL, cs.AI
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/huggingface/trl
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Long Chain-of-Thought Reasoning Across Languages
- LoRA: Low-Rank Adaptation of Large Language Models
- TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning
- Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning
- Let's Verify Step by Step
- R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and Reasoning
- CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning
- Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results
- Language Models are Multilingual Chain-of-Thought Reasoners
- Defining and Characterizing Reward Hacking
- AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data