一作ACL 2026Poster· Natural Language Processing
Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
Shaohua Duan · Pengcheng Huang · Xinze Li · Zhenghao Liu · Xiaoyuan Yi · Yukun Yan · Shuo Wang · Yu Gu · Ge Yu · Maosong Sun
摘要
Long-context modeling is critical for a wide range of real-world tasks, including long-context question answering, summarization, and complex reasoning tasks. Recent studies have explored fine-tuning Large Language Models (LLMs) with synthetic data to enhance their long-context capabilities. Howe...