Related papers: UCoder: Unsupervised Code Generation by Internal P…

Current coding benchmarks often inflate Large Language Model (LLM) capabilities due to static paradigms and data contamination, enabling models to exploit statistical shortcuts rather than genuine reasoning. To address this, we introduce…

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…

This study investigates the reliability of code generation by Large Language Models (LLMs), focusing on identifying and analyzing defects in the generated code. Despite the advanced capabilities of LLMs in automating code generation,…

Large Language Models (LLMs) are versatile and demonstrate impressive generalization ability by mining and learning information from extensive unlabeled text. However, they still exhibit reasoning mistakes, often stemming from knowledge…

Semi-supervised learning based methods are current SOTA solutions to the noisy-label learning problem, which rely on learning an unsupervised label cleaner first to divide the training samples into a labeled set for clean data and an…

Malicious examples are crucial for evaluating the robustness of machine learning algorithms under attack, particularly in Industrial Control Systems (ICS). However, collecting normal and attack data in ICS environments is challenging due to…

Motivation. Large language models (LLMs) have exhibited remarkable proficiency in diverse software engineering (SE) tasks. Handling such tasks typically involves acquiring foundational coding knowledge on large, general-purpose datasets…

Discovering novel concepts in unlabelled datasets and in a continuous manner is an important desideratum of lifelong learners. In the literature such problems have been partially addressed under very restricted settings, where novel classes…

With the significant progress of large reasoning models in complex coding and reasoning tasks, existing benchmarks, like LiveCodeBench and CodeElo, are insufficient to evaluate the coding capabilities of large language models (LLMs) in real…

Code generation is one of the tasks for which the use of Large Language Models is widely adopted and highly successful. Given this popularity, there are many benchmarks dedicated to code generation that can help select the best model.…

Code generation is important in software engineering, and Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm to improve it through execution-based feedback. However, most RLVR pipelines rely on human-curated tests,…

Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements over various cross-lingual and low-resource tasks. Through training on one hundred languages…

Large Language Models (LLMs) have demonstrated impressive performance on a wide range of natural language processing (NLP) tasks, primarily through in-context learning (ICL). In ICL, the LLM is provided with examples that represent a given…

Code data in large language model (LLM) pretraining is recognized crucial not only for code-related tasks but also for enhancing general intelligence of LLMs. Current open-source LLMs often heavily rely on human effort to produce their code…

Although large language models (LLMs) have demonstrated impressive ability in code generation, they are still struggling to address the complicated intent provided by humans. It is widely acknowledged that humans typically employ planning…

We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They…

The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the…

Code generation is a longstanding challenge, aiming to generate a code snippet based on a natural language description. Usually, expensive text-code paired data is essential for training a code generation model. Recently, thanks to the…

Large Language Models (LLMs) have shown promising performance in code generation. However, how to reliably evaluate code generated by LLMs remains an unresolved problem. This paper presents CodeJudge, a code evaluation framework that…

The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…