2 papers
cs.CL2025
Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge
Ying Zhang, Benjamin Heinzerling, Dongyuan Li +1
While fine-tuning is the standard for injecting factual knowledge into large language models (LLMs), the mechanisms enabling reliable fact recall via unseen queries remain poorly u…
cs.RO2023
Meta-control of Dialogue Systems Using Large Language Models
Kotaro Shukuri, Ryoma Ishigaki, Jundai Suzuki +5
Utilizing Large Language Models (LLMs) facilitates the creation of flexible and natural dialogues, a task that has been challenging with traditional rule-based dialogue systems. Ho…