2026.mellm-1.2.pdf

N/A

Evidence-Augmented Generation Reasoning for Extremely Low-Resource Language Decipherment Xiaoyu Zhu1,2 , Longyuan1,2 , Rui Qi1,2 , Jinan Xu1,2† 1 Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education 2 School of Computer Science and Technology, Beijing Jiaotong University {24120420, jaxu}@bjtu.edu.cn Abstract…

saved by

• Tejasvini Chawla

related reading

• Reinforcement Learning Elicits Contextual Learning of Unseen Language Translationarxiv.org
• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• 2025.findings-emnlp.313.pdfaclanthology.org
• Self-Adapting Language Modelsarxiv.org
• 2025.acl-long.429.pdfaclanthology.org
• Language Models can Solve Computer Tasksarxiv.org
• 2025.acl-long.896.pdfaclanthology.org
• 2025.acl-srw.17.pdfaclanthology.org
• Language Model Compositionarxiv.org
• Reasoning Models Reason Well, Until They Don'tarxiv.org
• [2606.10346] Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learningarxiv.org
• 2024.emnlp-main.914.pdfaclanthology.org