Related papers: Generating Pragmatic Examples to Train Neural Prog…
When giving automated feedback to a student working on a beginner's exercise, many programming tutors run into a completeness problem. On the one hand, we want a student to experiment freely. On the other hand, we want a student to write…
One of the main purposes of deep metric learning is to construct an embedding space that has well-generalized embeddings on both seen (training) classes and unseen (test) classes. Most existing works have tried to achieve this using…
We consider the task of performing probabilistic inference with probabilistic logical models. Many algorithms for approximate inference with such models are based on sampling. From a logic programming perspective, sampling boils down to…
Teaching systems physical tasks is a long standing goal in HCI, yet most prior work has focused on non collaborative physical activities. Collaborative tasks introduce added complexity, requiring systems to infer users assumptions about…
A long-standing issue with paraphrase generation is how to obtain reliable supervision signals. In this paper, we propose an unsupervised paradigm for paraphrase generation based on the assumption that the probabilities of generating two…
We formalize and study ``programming by rewards'' (PBR), a new approach for specifying and synthesizing subroutines for optimizing some quantitative metric such as performance, resource utilization, or correctness over a benchmark. A PBR…
Regular expressions (regexes) are widely used in different fields of computer science, such as programming languages, string processing, and databases. However, existing tools for synthesizing or repairing regexes always assume that the…
Learning from demonstration methods usually leverage close to optimal demonstrations to accelerate training. By contrast, when demonstrating a task, human teachers deviate from optimal demonstrations and pedagogically modify their behavior…
Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. We collect pairs of naturalistic and synthetic reasoning tasks to…
Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whether models are truly…
Prediction without justification has limited applicability. As a remedy, we learn to extract pieces of input text as justifications -- rationales -- that are tailored to be short and coherent, yet sufficient for making the same prediction.…
Recent systems for converting natural language descriptions into regular expressions (regexes) have achieved some success, but typically deal with short, formulaic text and can only produce simple regexes. Realworld regexes are complex,…
Program synthesis techniques offer significant new capabilities in searching for programs that satisfy high-level specifications. While synthesis has been thoroughly explored for input/output pair specifications (programming-by-example),…
In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…
The success of AI models relies on the availability of large, diverse, and high-quality datasets, which can be challenging to obtain due to data scarcity, privacy concerns, and high costs. Synthetic data has emerged as a promising solution…
Interacting with computers is a ubiquitous activity for millions of people. Repetitive or specialized tasks often require creation of small, often one-off, programs. End-users struggle with learning and using the myriad of domain-specific…
With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models. However, machine learning with synthetic data is not trivial due to the gap between the synthetic…
Neural inductive program synthesis is a task generating instructions that can produce desired outputs from given inputs. In this paper, we focus on the generation of a chunk of assembly code that can be executed to match a state change…
We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpretable, generalizable, and amenable to formal verification…
The instruction learning paradigm -- where a model learns to perform new tasks from task descriptions alone -- has become popular in general-purpose model research. The capabilities of large transformer models as instruction learners,…