paper-with-me

Papers

RoCode: A Dataset for Measuring Code Intelligence from Problem Definitions in Romanian

2024-02-20 · Adrian Cosma, Bogdan Iordache, Paolo Rosso

Recently, large language models (LLMs) have become increasingly powerful and have become capable of solving a plethora of tasks through proper instructions in natural language. However, the vast majority of testing suites assume that the instructions are written in English, the de facto prompting language. Code intelligence and problem solving still remain a difficult task, even for the most advanced LLMs. Currently, there are no datasets to measure the generalization power for code-generation models in a language other than English. In this work, we present RoCode, a competitive programming dataset, consisting of 2,642 problems written in Romanian, 11k solutions in C, C++ and Python and comprehensive testing suites for each problem. The purpose of RoCode is to provide a benchmark for evaluating the code intelligence of language models trained on Romanian / multilingual text as well as a fine-tuning set for pretrained Romanian models. Through our results and review of related works, we argue for the need to develop code models for languages other than English.

📄 PDF Abstract BibTeX arXiv:2402.13222

Code (1)

cosmaadrian/rocode 공식 구현

Tasks

Code Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems

2026-03-08 · Zongqian Li, Tengchao Lv, Shaohan Huang, Yixuan Su 외 arxiv

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through system…

Reinforcement LearningCode Generation

Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models

2026-03-08 · Zongqian Li, Shaohan Huang, Zewen Chi, Yixuan Su 외 arxiv

Modern code generation models exhibit longer outputs, accelerated capability growth, and changed training dynamics, rendering traditional training methodologies, algorithms, and datasets ineffective for improving their p…

Reinforcement LearningCode Generation

Neurocoder: Learning General-Purpose Computation Using Stored Neural Programs

2020-09-24 · NeurIPS 2021 12 · Hung Le, Svetha Venkatesh

Artificial Neural Networks are uniquely adroit at machine learning by processing data through a network of artificial neurons. The inter-neuronal connection weights represent the learnt Neural Program that instructs the …

Continual LearningObject Recognition

Procode: the Swiss Multilingual Solution for Automatic Coding and Recoding of Occupations and Economic Activities

2020-11-30 · Nenad Savic, Nicolas Bovio, Fabian Gilbert, Irina Guseva Canu

Objective. Epidemiological studies require data that are in alignment with the classifications established for occupations or economic activities. The classifications usually include hundreds of codes and titles. Manual …

ClassificationGeneral Classification

NeuroCodeBench: a plain C neural network benchmark for software verification

2023-09-07 · Edoardo Manino, Rafael Sá Menezes, Fedor Shmarov, Lucas C. Cordeiro

Safety-critical systems with neural network components require strong guarantees. While existing neural network verification techniques have shown great progress towards this goal, they cannot prove the absence of softwa…

Density Estimation