Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
Qian Kou, Xiaofeng Shi, Xiaosong Qiu +1
Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time. We study this setting as doc…
cs.CL2025
Rethinking Supervised Fine-Tuning: Emphasizing Key Answer Tokens for Improved LLM Accuracy
Xiaofeng Shi, Qian Kou, Yuduo Li +1
With the rapid advancement of Large Language Models (LLMs), the Chain-of-Thought (CoT) component has become significant for complex reasoning tasks. However, in conventional Superv…