Frugal Prompting for Dialog Models

Bishal Santra, Sakya Basak, Abhinandan De, Manish Gupta, Pawan Goyal

Submission Type: Regular Long Paper

Submission Track: Dialogue and Interactive Systems

Keywords: dialog, dialog generation, natural language generation, dialogue generation, dialogue, NLP

TL;DR: Understanding the behavior of large language models in different input scenarios is crucial for building efficient and cost-effective dialog systems.

Abstract:

The use of large language models (LLMs) in natural language processing (NLP) tasks is rapidly increasing, leading to changes in how researchers approach problems in the field. To fully utilize these models' abilities, a better understanding of their behavior for different input protocols is required. With LLMs, users can directly interact with the models through a text-based interface to define and solve various tasks. Hence, understanding the conversational abilities of these LLMs, which may not have been specifically trained for dialog modeling, is also important. This study examines different approaches for building dialog systems using LLMs by considering various aspects of the prompt. As part of prompt tuning, we experiment with various ways of providing instructions, exemplars, current query and additional context.
The research also analyzes the representations of dialog history that have the optimal usable-information density. Based on the findings, the paper suggests more compact ways of providing dialog history information while ensuring good performance and reducing model's inference-API costs. The research contributes to a better understanding of how LLMs can be effectively used for building interactive systems.

Submission Number: 2493