Evaluating a Prompting Strategy for Factual Accuracy
A company uses a language model to answer customer questions based on retrieved product manuals. They find that if a manual is missing information, the model sometimes invents plausible-sounding but incorrect details. To solve this, the engineering team adds the following instruction to every request: You must answer the user's question. Be as faithful as possible to the provided text. Evaluate the effectiveness of this new instruction in addressing the core problem. What is its most significant weakness?
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Evaluation in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
Example Prompt Instruction for Faithfulness and Abstention
Evaluating a Prompting Strategy for Factual Accuracy
A developer is building a question-answering system and provides a language model with the following instruction: 'You must base your answer strictly on the provided text. If the text does not contain enough information to answer the question accurately, you must respond with the exact phrase
Insufficient Information.' The model is then given the question 'What is the capital of Australia?' and the following text: 'Australia is a country and continent surrounded by the Indian and Pacific oceans. Its major cities are Sydney, Brisbane, Melbourne, and Perth.' Based on the developer's instruction, what is the most appropriate response from the model?Designing a Prompt for Factual Summarization