Prompting Is Programming: A Query Language For Large Language Models

Beurer-Kellner, Luca; Fischer, M. L.; Vechev, Martin

doi:10.48550/arxiv.2212.06094

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of a large language model, the use of propositional logic may increase the interpretability of the model's output with the goal of finding the causes of unreliability in the model [37]. A related approach is a procedure for prompting an advanced large language model for directing the model to align the output with that of an expectation [37][38][39][40][41]. In particular, Creswell and others [37] formalized a procedure to train the neural network on a type of step-by-step reasoning process.…”

Section: Prompt-based Methods In Deep Learningmentioning

confidence: 99%

Large Language Models and Logical Reasoning

Friedman

2023

Encyclopedia

View full text Add to dashboard Cite

In deep learning, large language models are typically trained on data from a corpus as representative of current knowledge. However, natural language is not an ideal form for the reliable communication of concepts. Instead, formal logical statements are preferable since they are subject to verifiability, reliability, and applicability. Another reason for this preference is that natural language is not designed for an efficient and reliable flow of information and knowledge, but is instead designed as an evolutionary adaptation as formed from a prior set of natural constraints. As a formally structured language, logical statements are also more interpretable. They may be informally constructed in the form of a natural language statement, but a formalized logical statement is expected to follow a stricter set of rules, such as with the use of symbols for representing the logic-based operators that connect multiple simple statements and form verifiable propositions.

show abstract

Section: Prompt-based Methods In Deep Learningmentioning

confidence: 99%

Large Language Models and Logical Reasoning

Friedman

2023

Encyclopedia

View full text Add to dashboard Cite

show abstract

“…Being an emerging field, the terms are still being discussed, but the importance of knowing how to interact with a non-deterministic system aiming for an objective result is vital. Prompt engineering/design involves crafting prompts that effectively communicate, examples, personas, and goals, to generate response templates that fit your objectives [26,27]. It is also important to set evaluation metrics to feed the model toward more assertive results within the limits of available tokens.…”

Section: Tip 8: Learn the Basics Of Prompt Engineering/designmentioning

confidence: 99%