Ask a Question

Prefer a chat interface with context about you and your work?

Comparing Plausibility Estimates in Base and Instruction-Tuned Large Language Models

Comparing Plausibility Estimates in Base and Instruction-Tuned Large Language Models

Instruction-tuned LLMs can respond to explicit queries formulated as prompts, which greatly facilitates interaction with human users. However, prompt-based approaches might not always be able to tap into the wealth of implicit knowledge acquired by LLMs during pre-training. This paper presents a comprehensive study of ways to evaluate semantic plausibility …