Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models
Year: 2024
Type: preprint
Abstract: Accurate and interpretable user satisfaction estimation (USE) is critical for understanding, evaluating, and continuously improving conversational systems. Users express their satisfaction or dissatisfaction with diverse conversational patterns in both general-purpose (ChatGPT and Bing Copilot) and task-oriented (customer service chatbot) conversational systems. Existing approaches based on featurized ML models or text embeddings fall short in extracting generalizable patterns and are hard to interpret. In this work, we show that LLMs can extract interpretable signals of user satisfaction from their natural language utterances more effectively than embedding-based approaches. Moreover, an LLM can be tailored for USE via an iterative prompting framework using supervision from labeled examples. The resulting method, Supervised Prompting for User satisfaction Rubrics (SPUR), not only has higher accuracy but is more interpretable as it scores user satisfaction via learned rubrics with a detailed breakdown.
Source: arXiv (Cornell University)
Authors: Lin, Ying-Chun, Neville, Jennifer, Stokes, Jack W., Yang, Longqi, Safavi, Tara, Wan, Mengting, Counts, Scott, Suri, Siddharth, Andersen, Reid, Xu, Xiaofeng, Gupta, Deepak, Jauhar, Sujay Kumar, Song, Xia, Buscher, Georg, Tiwary, Saurabh, Hecht, Brent, Teevan, Jaime
Institutions: Microsoft (United States), Purdue University West Lafayette
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4393027244