Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions
Samia Kabir, David N. Udo-Imeh, Bonan Kou, Tianyi Zhang
摘要
Q&A platforms have been crucial for the online help-seeking behavior of programmers. However, the recent popularity of Chat-GPT is altering this trend. Despite this popularity, no comprehensive study has been conducted to evaluate the characteristics of ChatGPT's answers to programming questions. To bridge the gap, we conducted the first in-depth analysis of ChatGPT answers to 517 programming questions on Stack Overflow and examined the correctness, consistency, comprehensiveness, and conciseness of ChatGPT answers. Furthermore, we conducted a large-scale linguistic analysis, as well as a user study, to understand the characteristics of ChatGPT answers from linguistic and human aspects. Our analysis shows that 52% of ChatGPT answers contain incorrect information and 77% are verbose. Nonetheless, our user study participants still preferred ChatGPT answers 35% of the time due to their comprehensiveness and well-articulated language style. However, they also overlooked the misinformation in the ChatGPT answers 39% of the time. This implies the need to counter misinformation in ChatGPT answers to programming questions and raise awareness of the risks associated with seemingly correct answers.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper26
- Writer-Defined AI Personas for On-Demand Feedback GenerationKarim Benharrak, Tim Zindulka, Florian Lehmann, Hendrik Heuer 等CHI 2024 · 被引用 62 次
- Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature ReviewRock Yuren Pang, Hope Schroeder, Kynnedy Simone Smith, Solon Barocas 等CHI 2025 · 被引用 51 次
- How CO2STLY Is CHI? The Carbon Footprint of Generative AI in HCI Research and What We Should Do About ItNanna Inie, Jeanette Falk, Raghavendra SelvanCHI 2025 · 被引用 33 次
- To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language ModelsJessica Y. Bo, Sophia Wan, Ashton AndersonCHI 2025 · 被引用 31 次
- ComPO: Preference Alignment via Comparison OraclesPeter Chen, Xi Chen, Wotao Yin, Tianyi LinNeurIPS 2025 · 被引用 20 次
它引用的顶会 Paper10
- Climbing towards NLU: On Meaning, Form, and Understanding in the Age of DataEmily M. Bender, Alexander KollerACL 2020 · 被引用 914 次
- Grounded Copilot: How Programmers Interact with Code-Generating ModelsShraddha Barke, Michael B. James, Nadia PolikarpovaOOPSLA 2023 · 被引用 408 次
- Large Language Models are Human-Level Prompt EngineersYongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster 等ICLR 2023 · 被引用 297 次
- Synthetic Lies: Understanding AI-Generated Misinformation and Evaluating Algorithmic and Human SolutionsJiawei Zhou, Yixuan Zhang, Qianni Luo, Andrea G. Parker 等CHI 2023 · 被引用 283 次
- Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language ModelsHendrik Strobelt, Albert Webson, Victor Sanh, Benjamin Hoover 等IEEE VIS 2022 · 被引用 191 次
相关 Paper
- How Do Programming Students Use Generative AI?Christian Rahe, Walid MaalejFSE 2025 · 被引用 12 次
- 'Always Nice and Confident, Sometimes Wrong': Developer's Experiences Engaging Generative AI Chatbots Versus Human-Powered Q&A PlatformsJiachen Li, Elizabeth D. Mynatt, Varun Mishra, Jonathan BellCSCW 2025 · 被引用 8 次
- Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?Bonan Kou, Shengmai Chen, Zhijie Wang, Lei Ma 等FSE 2024 · 被引用 8 次
- Evaluating and Improving ChatGPT for Unit Test GenerationZhiqiang Yuan, Mingwei Liu, Shiji Ding, Kaixin Wang 等FSE 2024 · 被引用 89 次
- How Do Analysts Understand and Verify AI-Assisted Data Analyses?Ken Gu, Ruoxi Shang, Tim Althoff, Chenglong Wang 等CHI 2024 · 被引用 36 次
