no code implementations • 9 Feb 2024 • Bhavya Chopra, Yasharth Bajpai, Param Biyani, Gustavo Soares, Arjun Radhakrishna, Chris Parnin, Sumit Gulwani
The widespread availability of Large Language Models (LLMs) within Integrated Development Environments (IDEs) has led to their speedy adoption.
no code implementations • 2 Feb 2024 • Paul Denny, Sumit Gulwani, Neil T. Heffernan, Tanja Käser, Steven Moore, Anna N. Rafferty, Adish Singla
This survey article has grown out of the GAIED (pronounced "guide") workshop organized by the authors at the NeurIPS 2023 conference.
no code implementations • 13 Dec 2023 • Mukul Singh, José Cambronero, Sumit Gulwani, Vu Le, Gust Verbruggen
Multi-modality promises to unlock further uses for large language models.
no code implementations • 26 Oct 2023 • Mukul Singh, José Cambronero, Sumit Gulwani, Vu Le, Carina Negreanu, Gust Verbruggen
Imagine a developer who can only change their last line of code, how often would they have to start writing a function from scratch before it is correct?
no code implementations • 26 Oct 2023 • Anirudh Khatry, Sumit Gulwani, Priyanshu Gupta, Vu Le, Ananya Singha, Mukul Singh, Gust Verbruggen
Target similarity tuning (TST) is a method of selecting relevant examples in natural language (NL) to code generation through large language models (LLMs) to improve performance.
no code implementations • 26 Oct 2023 • Mukul Singh, José Cambronero, Sumit Gulwani, Vu Le, Carina Negreanu, Elnaz Nouri, Mohammad Raza, Gust Verbruggen
Writing such rules is often challenging for users as it requires them to understand and implement the underlying logic.
no code implementations • 16 Oct 2023 • Ananya Singha, José Cambronero, Sumit Gulwani, Vu Le, Chris Parnin
Inspired by prior work, we generate a collection of self-supervised structural tasks (e. g. navigate to a cell and row; transpose the table) and evaluate the performance differences when using 8 formats.
no code implementations • 9 Oct 2023 • Anirudh Khatry, Yasharth Bajpai, Priyanshu Gupta, Sumit Gulwani, Ashish Tiwari
The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and corpus elements are both natural language (NL) utterances (homogeneous) and the goal is to pick most relevant elements from the corpus in the Top-K, where K is large, such as 10, 25, 50 or even 100 (relaxed).
2 code implementations • 5 Oct 2023 • Tung Phung, Victor-Alexandru Pădurean, Anjali Singh, Christopher Brooks, José Cambronero, Sumit Gulwani, Adish Singla, Gustavo Soares
We investigate the role of generative AI models in providing human tutor-style programming hints to help students resolve errors in their buggy programs.
no code implementations • 21 Aug 2023 • Mukul Singh, José Cambronero, Sumit Gulwani, Vu Le, Carina Negreanu, Gust Verbruggen
DataVinci learns regular-expression-based patterns that cover a majority of values in a column and reports values that do not satisfy such patterns as data errors.
no code implementations • 14 Aug 2023 • Mukul Singh, Jose Cambronero, Sumit Gulwani, Vu Le, Carina Negreanu, Gust Verbruggen
After the user provides one or two formatted cells as examples, CORNET generates formatting rule suggestions for the user to apply to the spreadsheet.
no code implementations • 29 Jun 2023 • Tung Phung, Victor-Alexandru Pădurean, José Cambronero, Sumit Gulwani, Tobias Kohn, Rupak Majumdar, Adish Singla, Gustavo Soares
In our work, we systematically evaluate two models, ChatGPT (based on GPT-3. 5) and GPT-4, and compare their performance with human tutors for a variety of scenarios.
no code implementations • 23 May 2023 • Priyanshu Gupta, Avishree Khare, Yasharth Bajpai, Saikat Chakraborty, Sumit Gulwani, Aditya Kanade, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari
In our experiments with two datasets, the knowledge of prior edits boosts the performance of the LLMs significantly and enables them to generate 29% and 54% more correctly edited code in top-1 suggestions relative to the current state-of-the-art symbolic and neural approaches, respectively.
no code implementations • 2 May 2023 • Anirudh Khatry, Joyce Cahoon, Jordan Henkel, Shaleen Deep, Venkatesh Emani, Avrilia Floratou, Sumit Gulwani, Vu Le, Mohammad Raza, Sherry Shi, Mukul Singh, Ashish Tiwari
Existing approaches have utilized data context in a limited way by simply adding relevant information from the input data into the prompts sent to the LLM.
no code implementations • 31 Jan 2023 • Harshit Joshi, Abishai Ebenezer, José Cambronero, Sumit Gulwani, Aditya Kanade, Vu Le, Ivan Radiček, Gust Verbruggen
We evaluate FLAME on formula repair, formula completion, and similarity-based formula retrieval.
1 code implementation • 24 Jan 2023 • Tung Phung, José Cambronero, Sumit Gulwani, Tobias Kohn, Rupak Majumdar, Adish Singla, Gustavo Soares
We investigate using LLMs to generate feedback for fixing syntax errors in Python programs, a key scenario in introductory programming.
no code implementations • 29 Sep 2022 • Jialu Zhang, José Cambronero, Sumit Gulwani, Vu Le, Ruzica Piskac, Gustavo Soares, Gust Verbruggen
We propose to use a large language model trained on code, such as Codex, to build an APR system -- MMAPR -- for introductory Python programming assignments.
no code implementations • 24 Aug 2022 • Harshit Joshi, José Cambronero, Sumit Gulwani, Vu Le, Ivan Radicek, Gust Verbruggen
We show that RING can outperform language-specific repair engines for three of these languages.
no code implementations • 11 Aug 2022 • Mukul Singh, José Cambronero, Sumit Gulwani, Vu Le, Carina Negreanu, Mohammad Raza, Gust Verbruggen
Since we are the first to introduce conditional formatting, we compare CORNET to a wide range of symbolic and neural baselines adapted from related domains.
no code implementations • 25 Jul 2022 • Yuhao Zhang, Yasharth Bajpai, Priyanshu Gupta, Ameya Ketkar, Miltiadis Allamanis, Titus Barik, Sumit Gulwani, Arjun Radhakrishna, Mohammad Raza, Gustavo Soares, Ashish Tiwari
Our experiments show that Overwatch has 78% precision and that Overwatch not only completed edits when developers missed the opportunity to use the IDE tool support but also predicted new edits that have no tool support in the IDE.
no code implementations • 24 Jul 2022 • Rohan Bavishi, Harshit Joshi, José Pablo Cambronero Sánchez, Anna Fariha, Sumit Gulwani, Vu Le, Ivan Radicek, Ashish Tiwari
To address this problem, we developed LaMirage, a LAst-MIle RepAir-engine GEnerator that combines symbolic and neural techniques to perform last-mile repair in low-code formula languages.
1 code implementation • ICLR 2022 • Gabriel Poesia, Oleksandr Polozov, Vu Le, Ashish Tiwari, Gustavo Soares, Christopher Meek, Sumit Gulwani
Then, Synchromesh feeds the examples to a pre-trained language model and samples programs using Constrained Semantic Decoding (CSD): a general framework for constraining the output to a set of valid programs in the target language.
no code implementations • 3 Sep 2021 • Kia Rahmani, Mohammad Raza, Sumit Gulwani, Vu Le, Daniel Morris, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari
Examples provide a precise but incomplete specification, and natural language provides an ambiguous but more "complete" task description.
no code implementations • 14 Jul 2020 • Nagarajan Natarajan, Ajaykrishna Karthikeyan, Prateek Jain, Ivan Radicek, Sriram Rajamani, Sumit Gulwani, Johannes Gehrke
The goal of the synthesizer is to synthesize a "decision function" $f$ which transforms the features to a decision value for the black-box component so as to maximize the expected reward $E[r \circ f (x)]$ for executing decisions $f(x)$ for various values of $x$.
no code implementations • 22 Jun 2020 • Ashish Tiwari, Arjun Radhakrishna, Sumit Gulwani, Daniel Perelman
In the context of interactive program synthesis, we use the above result to develop an {\em{active program learner}} that generates the significant inputs to pose as queries to the user in each iteration.
no code implementations • 12 Sep 2019 • Sumit Gulwani, Kunal Pathak, Arjun Radhakrishna, Ashish Tiwari, Abhishek Udupa
Programming-by-Example (PBE) systems synthesize an intended program in some (relatively constrained) domain-specific language from a small number of input-output examples provided by the user.
no code implementations • ICLR 2018 • Ashwin Kalyan, Abhishek Mohta, Oleksandr Polozov, Dhruv Batra, Prateek Jain, Sumit Gulwani
In this work, we propose Neural Guided Deductive Search (NGDS), a hybrid synthesis technique that combines the best of both symbolic logic techniques and statistical models.
no code implementations • 17 Sep 2017 • Saswat Padhi, Prateek Jain, Daniel Perelman, Oleksandr Polozov, Sumit Gulwani, Todd Millstein
However, manual inspection of data to identify the different formats is infeasible in standard big-data scenarios.
no code implementations • 31 Aug 2016 • Reudismam Rolim, Gustavo Soares, Loris D'Antoni, Oleksandr Polozov, Sumit Gulwani, Rohit Gheyi, Ryo Suzuki, Bjoern Hartmann
In the second domain, we use repetitive edits applied by developers to the same project to synthesize a program transformation that applies these edits to other locations in the code.
3 code implementations • 12 Aug 2016 • Rajdeep Das, Umair Z. Ahmed, Amey Karkare, Sumit Gulwani
Apart from the code snapshots at regular intervals, Prutor also collects other valuable data such as the time taken by the students to solve the problems, the number of compile and execution events, and the errors made.
Computers and Society Programming Languages Software Engineering
3 code implementations • 10 Mar 2016 • Sumit Gulwani, Ivan Radiček, Florian Zuleger
We obtain promising initial results (the average usefulness grade 3. 4 on a scale from 1 to 5), and conclude that our approach can be used in an interactive setting.
Programming Languages
no code implementations • 29 Oct 2015 • Chris Alvin, Sumit Gulwani, Rupak Majumdar, Supratik Mukhopadhyay
This paper presents an intelligent tutoring system, GeoTutor, for Euclidean Geometry that is automatically able to synthesize proof problems and their respective solutions given a geometric figure together with a set of properties true of it.
no code implementations • 14 Nov 2014 • Umair Z. Ahmed, Krishnendu Chatterjee, Sumit Gulwani
Simple board games, like Tic-Tac-Toe and CONNECT-4, play an important role not only in the development of mathematical and logical skills, but also in the emotional and social development.
no code implementations • POPL 2011 2011 • Sumit Gulwani
We describe the design of a string programming/expression lan- guage that supports restricted forms of regular expressions, condi- tionals and loops.