Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userProgram Synthesis with Large Language Models
239
0
0.0
(
0
)
Added by
Augustus Odena
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
This paper explores the limits of the current generation of large language models for program synthesis in general purpose programming languages. We evaluate a collection of such models (with between 244M and 137B parameters) on two new benchmarks, MBPP and MathQA-Python, in both the few-shot and fine-tuning regimes. Our benchmarks are designed to measure the ability of these models to synthesize short Python programs from natural language descriptions. The Mostly Basic Programming Problems (MBPP) dataset contains 974 programming tasks, designed to be solvable by entry-level programmers. The MathQA-Python dataset, a Python version of the MathQA benchmark, contains 23914 problems that evaluate the ability of the models to synthesize code from more complex text. On both datasets, we find that synthesis performance scales log-linearly with model size. Our largest models, even without finetuning on a code dataset, can synthesize solutions to 59.6 percent of the problems from MBPP using few-shot learning with a well-designed prompt. Fine-tuning on a held-out portion of the dataset improves performance by about 10 percentage points across most model sizes. On the MathQA-Python dataset, the largest fine-tuned model achieves 83.8 percent accuracy. Going further, we study the models ability to engage in dialog about code, incorporating human feedback to improve its solutions. We find that natural language feedback from a human halves the error rate compared to the models initial prediction. Additionally, we conduct an error analysis to shed light on where these models fall short and what types of programs are most difficult to generate. Finally, we explore the semantic grounding of these models by fine-tuning them to predict the results of program execution. We find that even our best models are generally unable to predict the output of a program given a specific input.
rate research
Read More
Program synthesis from incomplete specifications (e.g. input-output examples) has gained popularity and found real-world applications, primarily due to its ease-of-use. Since this technology is often used in an interactive setting, efficiency and correctness are often the key user expectations from a system based on such technologies. Ensuring efficiency is challenging since the highly combinatorial nature of program synthesis algorithms does not fit in a 1-2 second response expectation of a user-facing system. Meeting correctness expectations is also difficult, given that the specifications provided are incomplete, and that the users of such systems are typically non-programmers. In this paper, we describe how interactivity can be leveraged to develop efficient synthesis algorithms, as well as to decrease the cognitive burden that a user endures trying to ensure that the system produces the desired program. We build a formal model of user interaction along three dimensions: incremental algorithm, step-based problem formulation, and feedback-based intent refinement. We then illustrate the effectiveness of each of these forms of interactivity with respect to synthesis performance and correctness on a set of real-world case studies.
In this paper, we propose a new technique based on program synthesis for extracting information from webpages. Given a natural language query and a few labeled webpages, our method synthesizes a program that can be used to extract similar types of information from other unlabeled webpages. To handle websites with diverse structure, our approach employs a neurosymbolic DSL that incorporates both neural NLP models as well as standard language constructs for tree navigation and string manipulation. We also propose an optimal synthesis algorithm that generates all DSL programs that achieve optimal F1 score on the training examples. Our synthesis technique is compositional, prunes the search space by exploiting a monotonicity property of the DSL, and uses transductive learning to select programs with good generalization power. We have implemented these ideas in a new tool called WebQA and evaluate it on 25 different tasks across multiple domains. Our experiments show that WebQA significantly outperforms existing tools such as state-of-the-art question answering models and wrapper induction systems.
Program synthesis from input-output examples has been a long-standing challenge, and recent works have demonstrated some success in designing deep neural networks for program synthesis. However, existing efforts in input-output neural program synthesis have been focusing on domain-specific languages, thus the applicability of previous approaches to synthesize code in full-fledged popular programming languages, such as C, remains a question. The main challenges lie in two folds. On the one hand, the program search space grows exponentially when the syntax and semantics of the programming language become more complex, which poses higher requirements on the synthesis algorithm. On the other hand, increasing the complexity of the programming language also imposes more difficulties on data collection, since building a large-scale training set for input-output program synthesis require random program generators to sample programs and input-output examples. In this work, we take the first step to synthesize C programs from input-output examples. In particular, we propose LaSynth, which learns the latent representation to approximate the execution of partially generated programs, even if their semantics are not well-defined. We demonstrate the possibility of synthesizing elementary C code from input-output examples, and leveraging learned execution significantly improves the prediction performance over existing approaches. Meanwhile, compared to the randomly generated ground-truth programs, LaSynth synthesizes more concise programs that resemble human-written code. We show that training on these synthesized programs further improves the prediction performance for both Karel and C program synthesis, indicating the promise of leveraging the learned program synthesizer to improve the dataset quality for input-output program synthesis.
We present a language to specify syntax guided synthesis (SyGuS) problems. Syntax guidance is a prominent theme in contemporary program synthesis approaches, and SyGuS was first described in [1]. This paper describes concretely the input format of a SyGuS solver. [1] Rajeev Alur, Rastislav Bodik, Garvit Juniwal, Milo M. K. Martin, Mukund Raghothaman, Sanjit A. Seshia, Rishabh Singh, Armando Solar-Lezama, Emina Torlak, and Abhishek Udupa. Syntax-guided synthesis. In FMCAD, pages 1--17, 2013.
Programming-by-example technologies are being deployed in industrial products for real-time synthesis of various kinds of data transformations. These technologies rely on the user to provide few representative examples of the transformation task. Motivated by the need to find the most pertinent question to ask the user, in this paper, we introduce the {em significant questions problem}, and show that it is hard in general. We then develop an information-theoretic greedy approach for solving the problem. We justify the greedy algorithm using the conditional entropy result, which informally says that the question that achieves the maximum information gain is the one that we know least about. 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. The procedure requires extending a {em{passive program learner}} to a {em{sampling program learner}} that is able to sample candidate programs from the set of all consistent programs to enable estimation of information gain. It also uses clustering of inputs based on features in the inputs and the corresponding outputs to sample a small set of candidate significant inputs. Our active learner is able to tradeoff false negatives for false positives and converge in a small number of iterations on a real-world dataset of %around 800 string transformation tasks.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
