Conversational Code Generation: a Case Study of Designing a Dialogue System for Generating Driving Scenarios for Testing Autonomous Vehicles
Cyber-physical systems like autonomous vehicles are tested in simulation before deployment, using domain-specific programs for scenario specification. To aid the testing of autonomous vehicles in simulation, we design a natural language interface, using an instruction-following large language model, to assist a non-coding domain expert in synthesising the desired scenarios and vehicle behaviours. We show that using it to convert utterances to the symbolic program is feasible, despite the very small training dataset. Human experiments show that dialogue is critical to successful simulation generation, leading to a 4.5 times higher success rate than a generation without engaging in extended conversation.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous VehiclesCode GenerationInstruction FollowingLanguage ModelingLanguage ModellingLarge Language ModelSimilar Papers 제목 키워드 기반
AUGUST: an Automatic Generation Understudy for Synthesizing Conversational Recommendation Datasets
High-quality data is essential for conversational recommendation systems and serves as the cornerstone of the network architecture development and training strategy design. Existing works contribute heavy human efforts t…
Conversational RecommendationKnowledge GraphsRecommendation SystemsExploring the Potential of Conversational Test Suite Based Program Repair on SWE-bench
Automatic program repair at project level may open yet to be seen opportunities in various fields of human activity. Since the SWE-Bench challenge was presented, we have seen numerous of solutions. Patch generation is a …
Program RepairvalidA Case Study in Engineering a Conversational Programming Assistant's Persona
The Programmer's Assistant is an experimental prototype software development environment that integrates a chatbot with a code editor. Conversational capability was achieved by using an existing code-fluent Large Languag…
ChatbotLanguage ModelingLanguage ModellingLarge Language ModelDo Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
In the era of conversational AI, generating accurate and contextually appropriate service responses remains a critical challenge. A central question remains: Is explicit intent recognition a prerequisite for generating h…
Response GenerationIntent RecognitionLeveraging Large Language Models for Patient Engagement: The Power of Conversational AI in Digital Health
The rapid advancements in large language models (LLMs) have opened up new opportunities for transforming patient engagement in healthcare through conversational AI. This paper presents an overview of the current landscap…
Chatbot