Deep Learning (DL) is prevalently used in various industries to improve decision-making and automate processes, driven by the ever-evolving DL libraries and compilers. The correctness of DL systems is crucial for trust in DL applications. As such, the recent wave of research has been studying the automated synthesis of test-cases (i.e., DNN models and their inputs) for fuzzing DL systems. However, existing model generators only subsume a limited number of operators, lacking the ability to pervasively model operator constraints. To address this challenge, we propose NeuRI, a fully automated approach for generating valid and diverse DL models composed of hundreds of types of operators. NeuRI adopts a three-step process: (i) collecting valid and invalid API traces from various sources; (ii) applying inductive program synthesis over the traces to infer the constraints for constructing valid models; and (iii) using hybrid model generation which incorporates both symbolic and concrete operators. Our evaluation shows that NeuRI improves branch coverage of TensorFlow and PyTorch by 24% and 15% over the state-of-the-art model-level fuzzers. NeuRI finds 100 new bugs for PyTorch and TensorFlow in four months, with 81 already fixed or confirmed. Of these, 9 bugs are labelled as high priority or security vulnerability, constituting 10% of all high-priority bugs of the period. Open-source developers regard error-inducing tests reported by us as "high-quality" and "common in practice".
Developing systems that can synthesize natural and life-like motions for simulated characters has long been a focus for computer animation. But in order for these systems to be useful for downstream applications, they need not only produce high-quality motions, but must also provide an accessible and versatile interface through which users can direct a character's behaviors. Natural language provides a simple-to-use and expressive medium for specifying a user's intent. Recent breakthroughs in natural language processing (NLP) have demonstrated effective use of language-based interfaces for applications such as image generation and program synthesis. In this work, we present PADL, which leverages recent innovations in NLP in order to take steps towards developing language-directed controllers for physics-based character animation. PADL allows users to issue natural language commands for specifying both high-level tasks and low-level skills that a character should perform. We present an adversarial imitation learning approach for training policies to map high-level language commands to low-level controls that enable a character to perform the desired task and skill specified by a user's commands. Furthermore, we propose a multi-task aggregation method that leverages a language-based multiple-choice question-answering approach to determine high-level task objectives from language commands. We show that our framework can be applied to effectively direct a simulated humanoid character to perform a diverse array of complex motor skills.
The utilization of programming language (PL) models, pre-trained on large-scale code corpora, as a means of automating software engineering processes has demonstrated considerable potential in streamlining various code generation tasks such as code completion, code translation, and program synthesis. However, current approaches mainly rely on supervised fine-tuning objectives borrowed from text generation, neglecting unique sequence-level characteristics of code, including but not limited to compilability as well as syntactic and functional correctness. To address this limitation, we propose PPOCoder, a new framework for code generation that synergistically combines pre-trained PL models with Proximal Policy Optimization (PPO) which is a widely used deep reinforcement learning technique. By utilizing non-differentiable feedback from code execution and structure alignment, PPOCoder seamlessly integrates external code-specific knowledge into the model optimization process. It's important to note that PPOCoder is a task-agnostic and model-agnostic framework that can be used across different code generation tasks and PLs. Extensive experiments on three code generation tasks demonstrate the effectiveness of our proposed approach compared to SOTA methods, achieving significant improvements in compilation success rates and functional correctness across different PLs.
Genetic programming is an evolutionary approach known for its performance in program synthesis. However, it is not yet mature enough for a practical use in real-world software development, since usually many training cases are required to generate programs that generalize to unseen test cases. As in practice, the training cases have to be expensively hand-labeled by the user, we need an approach to check the program behavior with a lower number of training cases. Metamorphic testing needs no labeled input/output examples. Instead, the program is executed multiple times, first on a given (randomly generated) input, followed by related inputs to check whether certain user-defined relations between the observed outputs hold. In this work, we suggest MTGP, which combines metamorphic testing and genetic programming and study its performance and the generalizability of the generated programs. Further, we analyze how the generalizability depends on the number of given labeled training cases. We find that using metamorphic testing combined with labeled training cases leads to a higher generalization rate than the use of labeled training cases alone in almost all studied configurations. Consequently, we recommend researchers to use metamorphic testing in their systems if the labeling of the training data is expensive.
A major bottleneck in search-based program synthesis is the exponentially growing search space which makes learning large programs intractable. Humans mitigate this problem by leveraging the compositional nature of the real world: In structured domains, a logical specification can often be decomposed into smaller, complementary solution programs. We show that compositional segmentation can be applied in the programming by examples setting to divide the search for large programs across multiple smaller program synthesis problems. For each example, we search for a decomposition into smaller units which maximizes the reconstruction accuracy in the output under a latent task program. A structural alignment of the constituent parts in the input and output leads to pairwise correspondences used to guide the program synthesis search. In order to align the input/output structures, we make use of the Structure-Mapping Theory (SMT), a formal model of human analogical reasoning which originated in the cognitive sciences. We show that decomposition-driven program synthesis with structural alignment outperforms Inductive Logic Programming (ILP) baselines on string transformation tasks even with minimal knowledge priors. Unlike existing methods, the predictive accuracy of our agent monotonically increases for additional examples and achieves an average time complexity of $\mathcal{O}(m)$ in the number $m$ of partial programs for highly structured domains such as strings. We extend this method to the complex setting of visual reasoning in the Abstraction and Reasoning Corpus (ARC) for which ILP methods were previously infeasible.
Genetic Programming (GP) often uses large training sets and requires all individuals to be evaluated on all training cases during selection. Random down-sampled lexicase selection evaluates individuals on only a random subset of the training cases allowing for more individuals to be explored with the same amount of program executions. However, creating a down-sample randomly might exclude important cases from the current down-sample for a number of generations, while cases that measure the same behavior (synonymous cases) may be overused despite their redundancy. In this work, we introduce Informed Down-Sampled Lexicase Selection. This method leverages population statistics to build down-samples that contain more distinct and therefore informative training cases. Through an empirical investigation across two different GP systems (PushGP and Grammar-Guided GP), we find that informed down-sampling significantly outperforms random down-sampling on a set of contemporary program synthesis benchmark problems. Through an analysis of the created down-samples, we find that important training cases are included in the down-sample consistently across independent evolutionary runs and systems. We hypothesize that this improvement can be attributed to the ability of Informed Down-Sampled Lexicase Selection to maintain more specialist individuals over the course of evolution, while also benefiting from reduced per-evaluation costs.
Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs. For these tasks, humans often start with a high-level algorithmic design and implement each part gradually. We introduce Parsel, a framework enabling automatic implementation and validation of complex algorithms with code LLMs. With Parsel, we automatically decompose algorithmic tasks into hierarchical natural language function descriptions and then search over combinations of possible function implementations using tests. We show that Parsel can be used across domains requiring hierarchical reasoning, including program synthesis and robotic planning. We find that, using Parsel, LLMs solve more competition-level problems in the APPS dataset, resulting in pass rates over 75\% higher than prior results from directly sampling AlphaCode and Codex, while often using a smaller sample budget. Moreover, with automatically generated tests, we find that Parsel can improve the state-of-the-art pass@1 performance on HumanEval from 67\% to 85\%. We also find that LLM-generated robotic plans using Parsel are more than twice as likely to be considered accurate than directly generated plans. Lastly, we explore how Parsel addresses LLM limitations and discuss how Parsel may be useful for human programmers. We release our code at https://github.com/ezelikman/parsel
Past research has examined how well these models grasp code syntax, yet their understanding of code semantics still needs to be explored. We extensively analyze seven code models to investigate how code models represent code syntax and semantics. This includes four prominent code pre-trained models (CodeBERT, GraphCodeBERT, CodeT5, and UnixCoder) and three large language models (StarCoder, CodeLlama, and CodeT5+). We have developed four probing tasks to evaluate the models' abilities to learn code syntax and semantics. These tasks focus on reconstructing code syntax and semantic structures-such as AST, CFG, CDG, and DDG - within the models' representation spaces. These structures are fundamental to understanding code. Additionally, we explore the role of syntax tokens in each token representation and the extended dependencies among code tokens. Furthermore, we examine the distribution of attention weights concerning code semantic structures. Through detailed analysis, our results emphasize the strengths and weaknesses of various code models in mastering code syntax and semantics. The findings reveal that these models are proficient in grasping code syntax, effectively capturing the relationships and roles of syntax tokens. However, their ability to encode code semantics shows more variability. This study enriches our understanding of the capabilities of code models in analyzing syntax and semantics. Our findings offer valuable insights for future code model enhancements, helping optimize their application across a range of code-related tasks.
A deductive program synthesis tool takes a specification as input and derives a program that satisfies the specification. The drawback of this approach is that search spaces for such correct programs tend to be enormous, making it difficult to derive correct programs within a realistic timeout. To speed up such program derivation, we improve the search strategy of a deductive program synthesis tool, SuSLik, using evolutionary computation. Our cross-validation shows that the improvement brought by evolutionary computation generalises to unforeseen problems.
Dialogue systems is an increasingly popular task of natural language processing. However, the dialogue paths tend to be deterministic, restricted to the system rails, regardless of the given request or input text. Recent advances in program synthesis have led to systems which can synthesize programs from very general search spaces, e.g. Programming by Example, and to systems with very accessible interfaces for writing programs, e.g. text-to-code translation, but have not achieved both of these qualities in the same system. We propose Modular Programs for Text-guided Hierarchical Synthesis (MPaTHS), a method for integrating Programming by Example and text-to-code systems which offers an accessible natural language interface for synthesizing general programs. We present a program representation that allows our method to be applied to the problem of task-oriented dialogue. Finally, we demo MPaTHS using our program representation.
Causal effect estimation from observational data is a central problem in causal inference. Methods based on potential outcomes framework solve this problem by exploiting inductive biases and heuristics from causal inference. Each of these methods addresses a specific aspect of causal effect estimation, such as controlling propensity score, enforcing randomization, etc., by designing neural network (NN) architectures and regularizers. In this paper, we propose an adaptive method called Neurosymbolic Causal Effect Estimator (NESTER), a generalized method for causal effect estimation. NESTER integrates the ideas used in existing methods based on multi-head NNs for causal effect estimation into one framework. We design a Domain Specific Language (DSL) tailored for causal effect estimation based on causal inductive biases used in literature. We conduct a theoretical analysis to investigate NESTER's efficacy in estimating causal effects. Our comprehensive empirical results show that NESTER performs better than state-of-the-art methods on benchmark datasets.
By conditioning on natural language instructions, large language models (LLMs) have displayed impressive capabilities as general-purpose computers. However, task performance depends significantly on the quality of the prompt used to steer the model, and most effective prompts have been handcrafted by humans. Inspired by classical program synthesis and the human approach to prompt engineering, we propose Automatic Prompt Engineer (APE) for automatic instruction generation and selection. In our method, we treat the instruction as the "program," optimized by searching over a pool of instruction candidates proposed by an LLM in order to maximize a chosen score function. To evaluate the quality of the selected instruction, we evaluate the zero-shot performance of another LLM following the selected instruction. Experiments on 24 NLP tasks show that our automatically generated instructions outperform the prior LLM baseline by a large margin and achieve better or comparable performance to the instructions generated by human annotators on 19/24 tasks. We conduct extensive qualitative and quantitative analyses to explore the performance of APE. We show that APE-engineered prompts can be applied to steer models toward truthfulness and/or informativeness, as well as to improve few-shot learning performance by simply prepending them to standard in-context learning prompts. Please check out our webpage at https://sites.google.com/view/automatic-prompt-engineer.
Automatic software generation based on some specification is known as program synthesis. Most existing approaches formulate program synthesis as a search problem with discrete parameters. In this paper, we present a novel formulation of program synthesis as a continuous optimization problem and use a state-of-the-art evolutionary approach, known as Covariance Matrix Adaptation Evolution Strategy to solve the problem. We then propose a mapping scheme to convert the continuous formulation into actual programs. We compare our system, called GENESYS, with several recent program synthesis techniques (in both discrete and continuous domains) and show that GENESYS synthesizes more programs within a fixed time budget than those existing schemes. For example, for programs of length 10, GENESYS synthesizes 28% more programs than those existing schemes within the same time budget.
Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Language models, whether fine-tuned or prompted with few-shot demonstrations, frequently violate these constraints, and lack a mechanism to iteratively revise their outputs. Moreover, some powerful language models are of extreme scale or inaccessible, making it inefficient, if not infeasible, to update their parameters for task-specific adaptation. We present Self-Correction, an approach that decouples an imperfect base generator (an off-the-shelf language model or supervised sequence-to-sequence model) from a separate corrector that learns to iteratively correct imperfect generations. To train the corrector, we propose an online training procedure that can use either scalar or natural language feedback on intermediate imperfect generations. We show that Self-Correction improves upon the base generator in three diverse generation tasks - mathematical program synthesis, lexically-constrained generation, and toxicity control - even when the corrector is much smaller than the base generator.
The Abstraction and Reasoning Corpus (ARC) aims at benchmarking the performance of general artificial intelligence algorithms. The ARC's focus on broad generalization and few-shot learning has made it difficult to solve using pure machine learning. A more promising approach has been to perform program synthesis within an appropriately designed Domain Specific Language (DSL). However, these too have seen limited success. We propose Abstract Reasoning with Graph Abstractions (ARGA), a new object-centric framework that first represents images using graphs and then performs a search for a correct program in a DSL that is based on the abstracted graph space. The complexity of this combinatorial search is tamed through the use of constraint acquisition, state hashing, and Tabu search. An extensive set of experiments demonstrates the promise of ARGA in tackling some of the complicated object-centric tasks of the ARC rather efficiently, producing programs that are correct and easy to understand.
Genetic Programming (GP) is an heuristic method that can be applied to many Machine Learning, Optimization and Engineering problems. In particular, it has been widely used in Software Engineering for Test-case generation, Program Synthesis and Improvement of Software (GI). Grammar-Guided Genetic Programming (GGGP) approaches allow the user to refine the domain of valid program solutions. Backus Normal Form is the most popular interface for describing Context-Free Grammars (CFG) for GGGP. BNF and its derivatives have the disadvantage of interleaving the grammar language and the target language of the program. We propose to embed the grammar as an internal Domain-Specific Language in the host language of the framework. This approach has the same expressive power as BNF and EBNF while using the host language type-system to take advantage of all the existing tooling: linters, formatters, type-checkers, autocomplete, and legacy code support. These tools have a practical utility in designing software in general, and GP systems in particular. We also present Meta-Handlers, user-defined overrides of the tree-generation system. This technique extends our object-oriented encoding with more practicability and expressive power than existing CFG approaches, achieving the same expressive power of Attribute Grammars, but without the grammar vs target language duality. Furthermore, we evidence that this approach is feasible, showing an example Python implementation as proof. We also compare our approach against textual BNF-representations w.r.t. expressive power and ergonomics. These advantages do not come at the cost of performance, as shown by our empirical evaluation on 5 benchmarks of our example implementation against PonyGE2. We conclude that our approach has better ergonomics with the same expressive power and performance of textual BNF-based grammar encodings.
Program synthesis approaches struggle to learn programs with numerical values. An especially difficult problem is learning continuous values over multiple examples, such as intervals. To overcome this limitation, we introduce an inductive logic programming approach which combines relational learning with numerical reasoning. Our approach, which we call NUMSYNTH, uses satisfiability modulo theories solvers to efficiently learn programs with numerical values. Our approach can identify numerical values in linear arithmetic fragments, such as real difference logic, and from infinite domains, such as real numbers or integers. Our experiments on four diverse domains, including game playing and program synthesis, show that our approach can (i) learn programs with numerical values from linear arithmetical reasoning, and (ii) outperform existing approaches in terms of predictive accuracies and learning times.
We develop an approach to estimate the probability that a program sampled from a large language model is correct. Given a natural language description of a programming problem, our method samples both candidate programs as well as candidate predicates specifying how the program should behave. This allows learning a model that forms a well-calibrated probabilistic prediction of program correctness. Our system also infers which predicates are useful to explain the behavior of the generated code, and humans preferred these in a human study over raw language model outputs. Our method is simple, easy to implement, and maintains state of the art generation accuracy results.
We introduce Knowledge-Driven Program Synthesis (KDPS) as a variant of the program synthesis task that requires the agent to solve a sequence of program synthesis problems. In KDPS, the agent should use knowledge from the earlier problems to solve the later ones. We propose a novel method based on PushGP to solve the KDPS problem, which takes subprograms as knowledge. The proposed method extracts subprograms from the solution of previously solved problems by the Even Partitioning (EP) method and uses these subprograms to solve the upcoming programming task using Adaptive Replacement Mutation (ARM). We call this method PushGP+EP+ARM. With PushGP+EP+ARM, no human effort is required in the knowledge extraction and utilization processes. We compare the proposed method with PushGP, as well as a method using subprograms manually extracted by a human. Our PushGP+EP+ARM achieves better train error, success count, and faster convergence than PushGP. Additionally, we demonstrate the superiority of PushGP+EP+ARM when consecutively solving a sequence of six program synthesis problems.
Drori et al. (2022) report that "A neural network solves, explains, and generates university math problems by program synthesis and few-shot learning at human level ... [It] automatically answers 81\% of university-level mathematics problems." The system they describe is indeed impressive; however, the above description is very much overstated. The work of solving the problems is done, not by a neural network, but by the symbolic algebra package Sympy. Problems of various formats are excluded from consideration. The so-called "explanations" are just rewordings of lines of code. Answers are marked as correct that are not in the form specified in the problem. Most seriously, it seems that in many cases the system uses the correct answer given in the test corpus to guide its path to solving the problem.