Related papers: Improving Type Error Messages in OCaml

Machine learning software is being used in many applications (finance, hiring, admissions, criminal justice) having a huge social impact. But sometimes the behavior of this software is biased and it shows discrimination based on some…

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle…

As large language models (LLMs) often generate plausible but incorrect content, error detection has become increasingly critical to ensure truthfulness. However, existing detection methods often overlook a critical problem we term as…

Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can…

This paper explores the use of a learned classifier for post-OCR text correction. Experiments with the Arabic language show that this approach, which integrates a weighted confusion matrix and a shallow language model, improves the vast…

In feedback generation for logical errors in programming assignments, large language model (LLM)-based methods have shown great promise. These methods ask the LLM to generate feedback given the problem statement and a student's (buggy)…

This presentation will cover a framework for application-level tracing of OCaml programs. We outline a solution to the main technical challenge, which is being able to log typed values with lower overhead and maintenance burden than…

Machine learning (ML) provides us with numerous opportunities, allowing ML systems to adapt to new situations and contexts. At the same time, this adaptability raises uncertainties concerning the run-time product quality or dependability,…

Context: Due to the demand for strong algorithmic reasoning, complex logic implementation, and strict adherence to input/output formats and resource constraints, competitive programming generation by large language models (LLMs) is…

Large Language models (LLMs) can generate complicated source code from natural language prompts. However, LLMs can generate output that deviates from what the user wants, requiring supervision and editing. To support this process, we offer…

Tangled code changes, commits that conflate unrelated modifications such as bug fixes, refactorings, and enhancements, introduce significant noise into bug datasets and adversely affect the performance of bug prediction models. Addressing…

This paper addresses the issue of correcting type errors in model transformations in realistic scenarios where neither predefined patches nor behavior-safe guards such as test suites are available. Instead of using predefined patches…

This paper investigates various approaches using Large Language Models (LLMs) to identify gaps and misconceptions in students' self-explanations of specific instructional material, in our case explanations of code examples. This research is…

While Large language model (LLM)-based programming assistants such as CoPilot and ChatGPT can help improve the productivity of professional software developers, they can also facilitate cheating in introductory computer programming courses.…

Code generation is to automatically generate source code conforming to a given programming specification, which has received extensive attention especially with the development of large language models (LLMs). Due to the inherent difficulty…

Motivated by the progress made by large language models (LLMs), we introduce the framework of verbalized machine learning (VML). In contrast to conventional machine learning (ML) models that are typically optimized over a continuous…

Despite significant advancements in text generation and reasoning, Large Language Models (LLMs) still face challenges in accurately performing complex arithmetic operations. Language model systems often enable LLMs to generate code for…

Background: Machine Learning (ML) systems rely on data to make predictions, the systems have many added components compared to traditional software systems such as the data processing pipeline, serving pipeline, and model training. Existing…

Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who…

Verifying hardware designs in embedded systems is crucial but often labor-intensive and time-consuming. While existing solutions have improved automation, they frequently rely on unrealistic assumptions. To address these challenges, we…