Search Results for author:
Found 34 papers, 5 papers with code
Exploring Interaction Patterns for Debugging: Enhancing Conversational Capabilities of AI-assistants
The widespread availability of Large Language Models (LLMs) within Integrated Development Environments (IDEs) has led to their speedy adoption.
Generative AI for Education (GAIED): Advances, Opportunities, and Challenges
This survey article has grown out of the GAIED (pronounced "guide") workshop organized by the authors at the NeurIPS 2023 conference.
Assessing GPT4-V on Structured Reasoning Tasks
Multi-modality promises to unlock further uses for large language models.
CodeFusion: A Pre-trained Diffusion Model for Code Generation
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?
TST$^\mathrm{R}$: Target Similarity Tuning Meets the Real World
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.
FormaT5: Abstention and Examples for Conditional Table Formatting with Natural Language
Writing such rules is often challenging for users as it requires them to understand and implement the underlying logic.
Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMs
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.
Augmented Embeddings for Custom Retrievals
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).
Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation
We investigate the role of generative AI models in providing human tutor-style programming hints to help students resolve errors in their buggy programs.
DataVinci: Learning Syntactic and Semantic String Repairs
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.
Demonstration of CORNET: A System For Learning Spreadsheet Formatting Rules By Example
After the user provides one or two formatted cells as examples, CORNET generates formatting rule suggestions for the user to apply to the spreadsheet.
Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors
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.
GrACE: Generation using Associated Code Edits
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.
From Words to Code: Harnessing Data for Program Synthesis from Natural Language
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.
FLAME: A small language model for spreadsheet formulas
We evaluate FLAME on formula repair, formula completion, and similarity-based formula retrieval.
Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models
We investigate using LLMs to generate feedback for fixing syntax errors in Python programs, a key scenario in introductory programming.
Repairing Bugs in Python Assignments Using Large Language Models
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.
Repair Is Nearly Generation: Multilingual Program Repair with LLMs
We show that RING can outperform language-specific repair engines for three of these languages.
CORNET: Learning Table Formatting Rules By Example
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.
Overwatch: Learning Patterns in Code Edit Sequences
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.
Neurosymbolic Repair for Low-Code Formula Languages
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.
Synchromesh: Reliable code generation from pre-trained language models
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.
Multi-modal Program Inference: a Marriage of Pre-trainedLanguage Models and Component-based Synthesis
Examples provide a precise but incomplete specification, and natural language provides an ambiguous but more "complete" task description.
Programming by Rewards
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 $x$.
Information-theoretic User Interaction: Significant Inputs for Program Synthesis
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.
Quantitative Programming by Examples
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.
Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples
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.
FlashProfile: A Framework for Synthesizing Data Profiles
However, manual inspection of data to identify the different formats is infeasible in standard big-data scenarios.
Learning Syntactic Program Transformations from Examples
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.
Prutor: A System for Tutoring CS1 and Collecting Student Programs for Analysis
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
Automated Clustering and Program Repair for Introductory Programming Assignments
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
Automatic Synthesis of Geometry Problems for an Intelligent Tutoring System
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.
Automatic Generation of Alternative Starting Positions for Simple Traditional Board Games
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.
Automating string processing in spreadsheets using input-output examples
We describe the design of a string programming/expression lan- guage that supports restricted forms of regular expressions, condi- tionals and loops.
