Clarification Prompt Generation for Ambiguous Queries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Retrieval augmented systems face challenges in precisely identifying user intent when queries are under-specified or ambiguous, leading to diverse and irrelevant content retrieval.
Innovation Solution
A method is developed to generate clarification prompts by modifying existing question-answering datasets to create training examples of under-specified queries, and using a machine-learning model to select latent differentiating factors from content candidates, thereby generating clarification prompts to clarify user intent.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the system retrieves content based on under-specified or ambiguous user queries, then the system can operate with simple query processing, but the retrieved content becomes diverse and irrelevant, failing to accurately identify user intent
Solution Approach 1:
The system performs preliminary action by proactively generating clarification prompts before final content retrieval. When detecting ambiguous queries, the system asks clarifying questions to users in advance, obtaining additional information needed to precisely identify user intent, thereby avoiding irrelevant content retrieval while maintaining simple initial query processing
Solution Approach 2:
The system implements feedback by using the initial ambiguous query to generate clarification prompts, then using the user's responses to these prompts to refine the search query. This feedback loop transforms the initially imprecise query into a refined query that accurately reflects user intent, resolving the contradiction between simple processing and precise identification
2Measurement precision
If the system asks clarification questions to specify user intent, then the accuracy of content retrieval improves, but the interaction time and complexity increase
Solution Approach 1:
The system applies partial action by selectively generating clarification prompts only for queries that meet ambiguity criteria, rather than asking clarification questions for all queries. This selective approach maintains high accuracy for ambiguous queries while avoiding unnecessary interaction time for clear queries, balancing precision with time efficiency
Solution Approach 2:
The system changes the parameter of query specification by dynamically adjusting the level of clarification based on detected ambiguity. For ambiguous queries, the system increases specification by asking clarification questions; for clear queries, it maintains the original query parameter, thereby optimizing the balance between intent accuracy and interaction time
Data Source
AI summary
Techniques for generating a clarification to distinguish among retrieved content in interactive systems are provided. In one aspect, a method for generating a clarification prompt in an interactive system includes: obtaining a training dataset for generating the clarification prompt from existing question-answering datasets by modifying original queries in the existing question-answering datasets to obtain training examples of under-specified queries; and training a machine learning model using the training dataset how to select latent differentiating factors in content candidates obtained from an under-specified query from a user and, based on the latent differentiating factors, generate the clarification prompt to clarify an intent of the user.