Related papers: ExeDec: Execution Decomposition for Compositional …

When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neural program synthesis methods have similar capabilities, what…

Task decomposition is a fundamental mechanism in program synthesis, enabling complex problems to be broken down into manageable subtasks. ExeDec, a state-of-the-art program synthesis framework, employs this approach by combining a Subgoal…

In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together. Although deep learning programs have demonstrated…

The compositional generalization abilities of neural models have been sought after for human-like linguistic competence. The popular method to evaluate such abilities is to assess the models' input-output behavior. However, that does not…

Neural network models often generalize poorly to mismatched domains or distributions. In NLP, this issue arises in particular when models are expected to generalize compositionally, that is, to novel combinations of familiar words and…

Program synthesis from input-output examples, also called programming by example (PBE), has had tremendous impact on automating end-user tasks. Large language models (LLMs) have the ability to solve PBE tasks by generating code in different…

Compositional generalization is a basic mechanism in human language learning, which current neural networks struggle with. A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability by…

Compositional generalization is a basic and essential intellective capability of human beings, which allows us to recombine known parts readily. However, existing neural network based models have been proven to be extremely deficient in…

Recently, a diverse set of decoding and reranking procedures have been shown effective for LLM-based code generation. However, a comprehensive framework that links and experimentally compares these methods is missing. We address this by…

The use of deep learning techniques has achieved significant progress for program synthesis from input-output examples. However, when the program semantics become more complex, it still remains a challenge to synthesize programs that are…

Compositional generalization, the ability of an agent to generalize to unseen combinations of latent factors, is easy for humans but hard for deep neural networks. A line of research in cognitive science has hypothesized a process,…

Many tasks in control, robotics, and planning can be specified using desired goal configurations for various entities in the environment. Learning goal-conditioned policies is a natural paradigm to solve such tasks. However, current…

People can learn a new concept and use it compositionally, understanding how to "blicket twice" after learning how to "blicket." In contrast, powerful sequence-to-sequence (seq2seq) neural networks fail such tests of compositionality,…

Deep learning models struggle with compositional generalization, i.e. the ability to recognize or generate novel combinations of observed elementary concepts. In hopes of enabling compositional generalization, various unsupervised learning…

Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text…

In tasks like semantic parsing, instruction following, and question answering, standard deep networks fail to generalize compositionally from small datasets. Many existing approaches overcome this limitation with model architectures that…

Decompilers are important tools for reverse engineers that help them analyze software at a higher level of abstraction than assembly code. Unfortunately, because compilation is lossy, deterministic decompilers produce code that is missing…

Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack of agreement about what it means for a neural model to be…

Decompilation transforms compiled code back into a high-level programming language for analysis when source code is unavailable. Previous work has primarily focused on enhancing decompilation performance by increasing the scale of model…

Compositional generalization refers to the ability to generalize to novel combinations of previously observed words and syntactic structures. Since it is regarded as a desired property of neural models, recent work has assessed…