Deep Learning (DL) systems have received exponential growth in popularity and have
become ubiquitous in our everyday life. Such systems are built on top of popular DL …

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 …

Inductive reasoning is a core problem-solving capacity: humans can identify underlying
principles from a few examples, which robustly generalize to novel scenarios. Recent work …

Despite recent success in large language model (LLM) reasoning, LLMs struggle with
hierarchical multi-step reasoning tasks like generating complex programs. For these tasks …

Answering complex natural language questions on knowledge graphs (KGQA) is a
challenging task. It requires reasoning with the input natural language questions as well as …

The de-facto standard decoding method for semantic parsing in recent years has been to
autoregressively decode the abstract syntax tree of the target program using a top-down …

Throughout their lives, humans seem to learn a variety of rules for things like applying
category labels, following procedures, and explaining causal relationships. These rules are …

Many structured prediction and reasoning tasks can be framed as program synthesis
problems, where the goal is to generate a program in a\emph {domain-specific …

Reasoning over natural language is a long-standing goal for the research community.
However, studies have shown that existing language models are inadequate in reasoning …

Deep reinforcement learning (RL) has led to encouraging successes in many challenging
control tasks. However, a deep RL model lacks interpretability due to the difficulty of …