Related papers: Syntax-Guided Program Reduction for Understanding …
Program semantics learning is the core and fundamental for various code intelligent tasks e.g., vulnerability detection, clone detection. A considerable amount of existing works propose diverse approaches to learn the program semantics for…
Automatically inducing the syntactic part-of-speech categories for words in text is a fundamental task in Computational Linguistics. While the performance of unsupervised tagging models has been slowly improving, current state-of-the-art…
Large language models (LLMs) increasingly rely on chain-of-thought (CoT) prompting to solve mathematical and logical reasoning tasks. Yet, a central question remains: to what extent are these generated rationales \emph{faithful} to the…
We introduce Modelizer - a novel framework that, given a black-box program, learns a model from its input/output behavior using neural machine translation algorithms. The resulting model mocks the original program: Given an input, the model…
It is very useful to integrate human knowledge and experience into traditional neural networks for faster learning speed, fewer training samples and better interpretability. However, due to the obscured and indescribable black box model of…
Uncertainty modeling in speaker representation aims to learn the variability present in speech utterances. While the conventional cosine-scoring is computationally efficient and prevalent in speaker recognition, it lacks the capability to…
In models to generate program source code from natural language, representing this code in a tree structure has been a common approach. However, existing methods often fail to generate complex code correctly due to a lack of ability to…
Many of the computing systems programmed using Machine Learning are opaque: it is difficult to know why they do what they do or how they work. The Explainable Artificial Intelligence research program aims to develop analytic techniques with…
Leveraging deep learning (DL)-based code analysis tools to solve software engineering tasks is becoming increasingly popular. Code models often suffer performance degradation due to various reasons (e.g., code data shifts). Retraining is…
One recurring problem in program development is that of understanding how to re-use code developed by a third party. In the context of (constraint) logic programming, part of this problem reduces to figuring out how to query a program. If…
Expressive neural text-to-speech (TTS) systems incorporate a style encoder to learn a latent embedding as the style information. However, this embedding process may encode redundant textual information. This phenomenon is called content…
Chain-of-Thought (CoT) prompting has significantly enhanced the reasoning abilities of large language models. However, recent studies have shown that models can still perform complex reasoning tasks even when the CoT is replaced with…
Existing large language model-based code generation pipelines typically use beam search or sampling algorithms during the decoding process. Although the programs they generate achieve high token-matching-based scores, they often fail to…
Natural language (NL) to code suggestion systems assist developers in Integrated Development Environments (IDEs) by translating NL utterances into compilable code snippet. The current approaches mainly involve hard-coded, rule-based systems…
The recent advancements in Deep Learning models and techniques have led to significant strides in performance across diverse tasks and modalities. However, while the overall capabilities of models show promising growth, our understanding of…
Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource consumption, and a tendency…
Instruction-tuned Language Models ILMs have become essential components of modern AI systems, demonstrating exceptional versatility across a wide range of natural language and reasoning tasks. Among their most impactful applications is code…
Recent advances in natural language processing highlight two key factors for improving reasoning in large language models (LLMs): (i) allocating more test-time compute tends to help on harder problems but often introduces redundancy in the…
Children learning their first language face multiple problems of induction: how to learn the meanings of words, and how to build meaningful phrases from those words according to syntactic rules. We consider how children might solve these…
We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to…