Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
38 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

HumanEval on Latest GPT Models -- 2024 (2402.14852v1)

Published 20 Feb 2024 in cs.CL, cs.AI, and cs.LG

Abstract: In 2023, we are using the latest models of GPT-4 to advance program synthesis. The LLMs have significantly improved the state-of-the-art for this purpose. To make these advancements more accessible, we have created a repository that connects these models to Huamn Eval. This dataset was initally developed to be used with a LLM called CODEGEN on natural and programming language data. The utility of these trained models is showcased by demonstrating their competitive performance in zero-shot Python code generation on HumanEval tasks compared to previous state-of-the-art solutions. Additionally, this gives way to developing more multi-step paradigm synthesis. This benchmark features 160 diverse problem sets factorized into multistep prompts that our analysis shows significantly improves program synthesis over single-turn inputs. All code is open source at https://github.com/daniel442li/gpt-human-eval .

Definition Search Book Streamline Icon: https://streamlinehq.com
References (15)
  1. Hierarchical neural program synthesis. arXiv preprint arXiv:2303.06018, 2023.
  2. arXiv preprint arXiv:2303.03004, 2023.
  3. Steven Bryant. Assessing gpt-4’s role as a co-collaborator in scientific research: A case study analyzing einstein’s special theory of relativity. 04 2023.
  4. Evaluating large language models trained on code, 2021.
  5. Reasoning with language model is planning with world model, 2023.
  6. David C. S. Li and Weng-Fai Wong. Iaso: Enhancing syntax error correction using deep learning techniques. 07 2023.
  7. OpenAI. Gpt-4 technical report, 2023.
  8. Reflexion: Language agents with verbal reinforcement learning, 2023.
  9. Author Unknown. Enhancing robot program synthesis through environmental context. OpenReview, 2023. [Online]. Available: https://openreview.net/forum?id=pZ2Ww45GkL.
  10. Waqas Uzair. Six-tier architecture for ai-generated software development: A large language models approach. 06 2023.
  11. Ashish Vaswani et al. Attention is all you need. Conference Name or Journal, 2017. Introduction of the Transformer model.
  12. Can chatgpt write a good boolean query for systematic review literature search? 01 2023.
  13. Chain-of-thought prompting elicits reasoning in large language models, 2023.
  14. Tree of thoughts: Deliberate problem solving with large language models, 2023.
  15. Language agent tree search unifies reasoning acting and planning in language models, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Daniel Li (42 papers)
  2. Lincoln Murr (3 papers)
Citations (2)
X Twitter Logo Streamline Icon: https://streamlinehq.com