相关论文: Towards More Trustworthy and Interpretable LLMs fo…

Large Language Models (LLMs) have shown strong performance in automated source-to-target code translation through pretraining on extensive code corpora. However, mainstream LLM-based code translation methods suffer from two critical…

We present a practical framework for detecting errors in LLM-generated SQL by estimating uncertainty at the level of individual nodes in the query's abstract syntax tree (AST). Our approach proceeds in two stages. First, we introduce a…

This paper surveys evaluation techniques to enhance the trustworthiness and understanding of Large Language Models (LLMs). As reliance on LLMs grows, ensuring their reliability, fairness, and transparency is crucial. We explore algorithmic…

Summarizing source code into natural language descriptions (code summarization) helps developers better understand program functionality and reduce the burden of software maintenance. Abstract Syntax Trees (ASTs), as opposed to source code,…

Humans understand language by extracting information (meaning) from sentences, combining it with existing commonsense knowledge, and then performing reasoning to draw conclusions. While large language models (LLMs) such as GPT-3 and ChatGPT…

Programming language understanding and representation (a.k.a code representation learning) has always been a hot and challenging task in software engineering. It aims to apply deep learning techniques to produce numerical representations of…

This paper explores the parallels between Thompson's "Reflections on Trusting Trust" and modern challenges in LLM-based code generation. We examine how Thompson's insights about compiler backdoors take on new relevance in the era of large…

In the rapidly evolving field of Explainable Natural Language Processing (NLP), textual explanations, i.e., human-like rationales, are pivotal for explaining model predictions and enriching datasets with interpretable labels. Traditional…

As Large Language Models (LLMs) become increasingly integrated into high-stakes domains, there have been several approaches proposed toward generating natural language explanations. These explanations are crucial for enhancing the…

Code translation migrates codebases across programming languages. Recently, large language models (LLMs) have achieved significant advancements in software mining. However, handling the syntactic structure of source code remains a…

Code translation aims to convert source code from one programming language (PL) to another. Given the promising abilities of large language models (LLMs) in code synthesis, researchers are exploring their potential to automate code…

Automated unit test generation using large language models (LLMs) holds great promise but often struggles with generating tests that are both correct and maintainable in real-world projects. This paper presents KTester, a novel framework…

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

The combination of Large Language Models (LLMs), systematic evaluation, and evolutionary algorithms has enabled breakthroughs in combinatorial optimization and scientific discovery. We propose to extend this powerful combination to the…

Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a language model predicts the next token and generates content is not generally understandable…

Large pre-trained language models have been used to generate code,providing a flexible interface for synthesizing programs from natural language specifications. However, they often violate syntactic and semantic rules of their output…

Recent efforts in Machine Learning (ML) interpretability have focused on creating methods for explaining black-box ML models. However, these methods rely on the assumption that simple approximations, such as linear models or decision-trees,…

Automated Machine Learning-based systems' integration into a wide range of tasks has expanded as a result of their performance and speed. Although there are numerous advantages to employing ML-based systems, if they are not interpretable,…

The growing adoption of Rust for its memory safety and performance has increased the demand for effective migration of legacy C codebases. However, existing rule-based translators (e.g., \ctorust) often generate verbose, non-idiomatic code…

Interpretability methods are valuable only if their explanations faithfully describe the explained model. In this work, we consider neural networks whose predictions are invariant under a specific symmetry group. This includes popular…