3 papers
cs.AI2026
Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning
Lu Dai, Ziyang Rao, Yili Wang +3
Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning tasks. We formalize this fai…
cs.CL2025
SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction
Lu Dai, Yijie Xu, Jinhui Ye +2
Large Language Models (LLMs) have demonstrated improved generation performance by incorporating externally retrieved knowledge, a process known as retrieval-augmented generation (R…
cs.CL2024
Improve Dense Passage Retrieval with Entailment Tuning
Lu Dai, Hao Liu, Hui Xiong
Retrieval module can be plugged into many downstream NLP tasks to improve their performance, such as open-domain question answering and retrieval-augmented generation. The key to a…