Jigsaw: Large Language Models meet Program Synthesis

By Naman Jain, Skanda Vaidyanath, Arun Shankar Iyer, Nagarajan Natarajan, Suresh Parthasarathy, Sriram K. Rajamani, Rahul Sharma. 2021

257 citations recorded by the source corpus.

Large pre-trained language models such as GPT-3 [10], Codex [11], and Coogle's language model [7] are now capable of generating code from natural language specifications of programmer intent. We view these developments with a mixture of optimism and caution. On the optimistic side, such large language models have the potential to improve productivity by providing an automated AI pair programmer for every programmer in the world. On the cautionary side, since these large language models do not understand program semantics, they offer no guarantees about quality of the suggested code. In this paper, we present an approach to augment these large language models with post-processing steps based on program analysis and synthesis techniques, that understand the syntax and semantics of programs. Further, we show that such techniques can make use of user feedback and improve with usage. We present our experiences from building and evaluating such a tool Jigsaw, targeted at synthesizing code for using Python Pandas API using multi-modal inputs. Our experience suggests that as these large language models evolve for synthesizing code from intent, Jigsaw has an important role to play in improving the accuracy of the systems.

Subfields: Artificial Intelligence, Information Systems, Software, Large Language Models, LLM Agents & Tool Use

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Graham Neubig
  2. Uri Alon
  3. Luke S. Zettlemoyer
  4. Mohit Bansal
  5. Percy Liang
  6. Jianfeng Gao
  7. Charles Sutton
  8. Yoshua Bengio

In Information Systems

  1. Koushik Sen
  2. Uri Alon
  3. Graham Neubig
  4. Charles Sutton
  5. Mark Harman
  6. Shin Yoo
  7. Kensen Shi
  8. Michele Catasta

In Software

  1. Koushik Sen
  2. Mark Harman
  3. Oleksandr Polozov
  4. Shin Yoo
  5. Armando Solar-Lezama
  6. Charles Sutton
  7. Kensen Shi
  8. Uri Alon

In Large Language Models

  1. Graham Neubig
  2. Armando Solar-Lezama
  3. Mark Harman
  4. Naman Jain
  5. Tianjun Zhang
  6. Aman Madaan
  7. Ion Stoica
  8. Kensen Shi

Citations in the corpus