Related papers: PERC: Plan-As-Query Example Retrieval for Underrep…

Performance bugs are non-functional bugs that can even manifest in well-tested commercial products. Fixing these performance bugs is an important yet challenging problem. In this work, we address this challenge and present a new approach…

Performing automatic reformulations of a user's query is a popular paradigm used in information retrieval (IR) for improving effectiveness -- as exemplified by the pseudo-relevance feedback approaches, which expand the query in order to…

We designed a Retrieval-Augmented Generation (RAG) system to provide large language models with relevant documents for answering domain-specific questions about Pittsburgh and Carnegie Mellon University (CMU). We extracted over 1,800…

Retrieval-augmented generation (RAG) systems have been shown to be effective in addressing many of the drawbacks of relying solely on the parametric memory of large language models. Recent work has demonstrated that RAG systems can be…

Competitive programming benchmarks are widely used in scenarios such as programming contests and large language model assessments. However, the growing presence of duplicate or highly similar problems raises concerns not only about…

Automatic generation of executable Blender code from natural language remains challenging, with state-of-the-art LLMs producing frequent syntactic errors and geometrically inconsistent objects. We present BlenderRAG, a retrieval-augmented…

Retrieval-augmented generation (RAG) grounds large language models with external evidence, but under a limited context budget, the key challenge is deciding which retrieved passages should be injected. We show that retrieval relevance…

Using tools by Large Language Models (LLMs) is a promising avenue to extend their reach beyond language or conversational settings. The number of tools can scale to thousands as they enable accessing sensory information, fetching updated…

Recognizing fallacies is crucial for ensuring the quality and validity of arguments across various domains. However, computational fallacy recognition faces challenges due to the diverse genres, domains, and types of fallacies found in…

Retrieval Augmented Generation (RAG) has advanced software engineering tasks but remains underexplored in unit test generation. To bridge this gap, we investigate the efficacy of RAG-based unit test generation for machine learning (ML/DL)…

Large Language Models (LLMs) have recently demonstrated impressive few-shot learning capabilities through in-context learning (ICL). However, ICL performance is highly dependent on the choice of few-shot demonstrations, making the selection…

Developers often depend on code search engines to obtain solutions for their programming tasks. However, finding an expected solution containing code examples along with their explanations is challenging due to several issues. There is a…

Evaluating retrieval-augmented generation (RAG) presents challenges, particularly for retrieval models within these systems. Traditional end-to-end evaluation methods are computationally expensive. Furthermore, evaluation of the retrieval…

Retrieval Augmented Generation (RAG) has proven to be highly effective in boosting the generative performance of language model in knowledge-intensive tasks. However, existing RAG framework either indiscriminately perform retrieval or rely…

Current state-of-the-art large language models are effective in generating high-quality text and encapsulating a broad spectrum of world knowledge. These models, however, often hallucinate and lack locally relevant factual data.…

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance large language models (LLMs) by conditioning generation on external evidence retrieved at inference time. While RAG addresses critical limitations of…

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Recent work targeting large language models (LLMs) for code generation demonstrated that increasing the amount of training data through synthetic code generation often leads to exceptional performance. In this paper we explore data pruning…

Retrieval-augmented generation (RAG) methods can enhance the performance of LLMs by incorporating retrieved knowledge chunks into the generation process. In general, the retrieval and generation steps usually have different requirements for…

Planning in code is considered a more reliable approach for many orchestration tasks. This is because code is more tractable than steps generated via Natural Language and make it easy to support more complex sequences by abstracting…