相关论文: Kotlin ML Pack: Technical Report

With the recent advance in neural machine translation demonstrating its importance, research on quality estimation (QE) has been steadily progressing. QE aims to automatically predict the quality of machine translation (MT) output without…

The recent advancements in text-to-image generative models have been remarkable. Yet, the field suffers from a lack of evaluation metrics that accurately reflect the performance of these models, particularly lacking fine-grained metrics…

The application of large-language models (LLMs) to digital hardware code generation is an emerging field, with most LLMs primarily trained on natural language and software code. Hardware code like Verilog constitutes a small portion of…

We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing…

This paper investigates two complementary paradigms for predicting machine translation (MT) quality: source-side difficulty prediction and candidate-side quality estimation (QE). The rapid adoption of Large Language Models (LLMs) into MT…

LLMs have achieved strong performance on text-based programming tasks, yet they remain unreliable for block-based languages such as Scratch. Scratch programs exhibit deeply nested, non-linear structures, event-driven concurrency across…

Even though large language models are becoming increasingly capable, it is still unreasonable to expect them to excel at tasks that are under-represented on the Internet. Leveraging LLMs for specialized applications, particularly in niche…

Understanding and reasoning over diagrams is a fundamental aspect of human intelligence. While Large Multimodal Models (LMMs) have demonstrated impressive capabilities across various tasks, existing benchmarks lack comprehensive evaluation…

Recent regulatory initiatives like the European AI Act and relevant voices in the Machine Learning (ML) community stress the need to describe datasets along several key dimensions for trustworthy AI, such as the provenance processes and…

Vision-Language Models (VLMs), with their powerful content generation capabilities, have been successfully applied to data annotation processes. However, the VLM-generated labels exhibit dual limitations: low quality (i.e., label noise) and…

Machine translation evaluation is a very important activity in machine translation development. Automatic evaluation metrics proposed in literature are inadequate as they require one or more human reference translations to compare them with…

Recent advancements in Large Language Models (LLMs) and Prompt Engineering have made chatbot customization more accessible, significantly reducing barriers to tasks that previously required programming skills. However, prompt evaluation,…

Recent advancements in large language models (LLMs) have automated various software engineering tasks, with benchmarks emerging to evaluate their capabilities. However, for adaptation, a critical activity during code reuse, there is no…

How should two language models interact to produce better code than either can alone? The conventional approach -- a reasoning model plans, a code specialist implements -- seems natural but fails: on HumanEval+, plan-then-code degrades…

With the evolution of Large Language Models (LLMs) we can solve increasingly more complex NLP tasks across various domains, including spreadsheets. This work investigates whether LLMs can generate code (Excel OfficeScripts, a TypeScript API…

Pretraining datasets for large language models (LLMs) have grown to trillions of tokens composed of large amounts of CommonCrawl (CC) web scrape along with smaller, domain-specific datasets. It is expensive to understand the impact of these…

We present four main contributions to enhance the performance of Large Language Models (LLMs) in generating domain-specific code: (i) utilizing LLM-based data splitting and data renovation techniques to improve the semantic representation…

Code coverage is a widely used metric for quantifying the extent to which program elements, such as statements or branches, are executed during testing. Calculating code coverage is resource-intensive, requiring code building and execution…

This paper presents our strategies in SemEval 2020 Task 4: Commonsense Validation and Explanation. We propose a novel way to search for evidence and choose the different large-scale pre-trained models as the backbone for three subtasks. The…

Automatic software system optimization can improve software speed, reduce operating costs, and save energy. Traditional approaches to optimization rely on manual tuning and compiler heuristics, limiting their ability to generalize across…