Related papers: Functional Overlap Reranking for Neural Code Gener…
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…
The coding capabilities of large language models (LLMs) have opened up new opportunities for automatic statistical analysis in machine learning and data science. However, before their widespread adoption, it is crucial to assess the…
Large Language Models (LLMs) have revolutionized code generation but require significant resources and often over-generalize, limiting their task-specific efficiency. Fine-tuning smaller, open-source LLMs provides a cost-effective…
Programmers increasingly rely on Large Language Models (LLMs) for code generation. However, misalignment between programmers' goals and generated code complicates the code evaluation process and demands frequent switching between prompt…
Scientific retrieval is essential for advancing scientific knowledge discovery. Within this process, document reranking plays a critical role in refining first-stage retrieval results. However, standard LLM listwise reranking faces…
Program synthesis has been long studied with recent approaches focused on directly using the power of Large Language Models (LLMs) to generate code. Programming benchmarks, with curated synthesis problems and test-cases, are used to measure…
Large Language Models (LLMs) have been integrated into recommendation systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant…
Scientific literature question answering is a pivotal step towards new scientific discoveries. Recently, \textit{two-stage} retrieval-augmented generated large language models (RAG-LLMs) have shown impressive advancements in this domain.…
Large language models for code (CodeLLMs) have demonstrated remarkable success in standalone code completion and generation, sometimes even surpassing human performance, yet their effectiveness diminishes in repository-level settings where…
Recent advances in Code Large Language Models (CodeLLMs) have primarily focused on open-ended code generation, often overlooking the crucial aspect of code understanding and reasoning. To bridge this gap, we introduce CodeMMLU, a…
We present REARANK, a large language model (LLM)-based listwise reasoning reranking agent. REARANK explicitly reasons before reranking, significantly improving both performance and interpretability. Leveraging reinforcement learning and…
Large Language Models (LLMs) have achieved remarkable success in code generation, and the race to improve their performance has become a central focus of AI research. Benchmarks and leaderboards are increasingly popular, offering…
Although large language models (LLMs) have become more capable and accurate across many tasks, some fundamental sources of unreliability remain in their behavior. One key limitation is their inconsistency at reporting the same information…
While a lot of recent research focuses on enhancing the textual reasoning capabilities of Large Language Models (LLMs) by optimizing the multi-agent framework or reasoning chains, several benchmark tasks can be solved with 100\% success…
The understanding of large-scale scientific software poses significant challenges due to its diverse codebase, extensive code length, and target computing architectures. The emergence of generative AI, specifically large language models…
Code large language models (CodeLLMs) and agents are increasingly being integrated into complex software engineering tasks spanning the entire Software Development Life Cycle (SDLC). Benchmarking is critical for rigorously evaluating these…
The recent advancements of Small Language Models (SLMs) have opened new possibilities for efficient code generation. SLMs offer lightweight and cost-effective alternatives to Large Language Models (LLMs), making them attractive for use in…
Code generation aims to automatically generate source code from high-level task specifications, which can significantly increase productivity of software engineering. Recently, approaches based on large language models (LLMs) have shown…
Code benchmarks such as HumanEval are widely adopted to evaluate the capabilities of Large Language Models (LLMs), providing insights into their strengths and weaknesses. However, current benchmarks primarily exercise LLMs' capability on…
Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accuracy for code generation. However, the quality of these…