paper-with-me

Papers

ChatCoder: Chat-based Refine Requirement Improves LLMs' Code Generation

2023-11-01 · Zejun Wang, Jia Li, Ge Li, Zhi Jin

Large language models have shown good performances in generating code to meet human requirements. However, human requirements expressed in natural languages can be vague, incomplete, and ambiguous, leading large language models to misunderstand human requirements and make mistakes. Worse, it is difficult for a human user to refine the requirement. To help human users refine their requirements and improve large language models' code generation performances, we propose ChatCoder: a method to refine the requirements via chatting with large language models. We design a chat scheme in which the large language models will guide the human users to refine their expression of requirements to be more precise, unambiguous, and complete than before. Experiments show that ChatCoder has improved existing large language models' performance by a large margin. Besides, ChatCoder has the advantage over refine-based methods and LLMs fine-tuned via human response.

📄 PDF Abstract BibTeX arXiv:2311.00272

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

Improving Ontology Requirements Engineering with OntoChat and Participatory Prompting

2024-08-09 · Yihang Zhao, Bohui Zhang, Xi Hu, Shuyin Ouyang 외

Past ontology requirements engineering (ORE) has primarily relied on manual methods, such as interviews and collaborative forums, to gather user requirements from domain experts, especially in large projects. Current Ont…

Chatbot

Empirical Evaluation of ChatGPT on Requirements Information Retrieval Under Zero-Shot Setting

2023-04-25 · Jianzhang Zhang, Yiyang Chen, Nan Niu, Yinglin Wang 외

Recently, various illustrative examples have shown the impressive ability of generative large language models (LLMs) to perform NLP related tasks. ChatGPT undoubtedly is the most representative model. We empirically eval…

Information RetrievalLanguage ModellingRetrieval

ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning

2026-06-01 · Bo-Hong Wang, Baicheng Peng, Ruilin Wang, Jun Bai 외 arxiv

Large language models (LLMs) exhibit strong natural-language reasoning abilities for clinical decision support, but struggle to effectively model structured longitudinal electronic health records (EHRs). In contrast, EHR…

Multimodal Reasoning

Self-Refinement of Language Models from External Proxy Metrics Feedback

2024-02-27 · Keshav Ramji, Young-suk Lee, Ramón Fernandez Astudillo, Md Arafat Sultan 외

It is often desirable for Large Language Models (LLMs) to capture multiple objectives when providing a response. In document-grounded response generation, for example, agent responses are expected to be relevant to a use…

Question AnsweringResponse Generation

Model Generation with LLMs: From Requirements to UML Sequence Diagrams

2024-04-09 · Alessio Ferrari, Sallam Abualhaija, Chetan Arora

Complementing natural language (NL) requirements with graphical models can improve stakeholders' communication and provide directions for system design. However, creating models from requirements involves manual effort. …