相关论文: LLARS: Enabling Domain Expert & Developer Collabor…

Open Source Software (OSS) has become a very important and crucial infrastructure worldwide because of the value it provides. OSS typically depends on contributions from developers across diverse backgrounds and levels of experience. Making…

LLM-based data generation for real-world tabular data can be challenged by the lack of sufficient semantic context in feature names used to describe columns. We hypothesize that enriching prompts with domain-specific insights can improve…

LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to assist them in their work poses a challenge for non-AI experts. Existing research in prompt engineering suggests…

Large Language Models (LLMs) have emerged as coding assistants, capable of generating source code from natural language prompts. With the increasing adoption of LLMs in software development, academic research and industry based projects are…

The evaluation of Large Language Models (LLMs) increasingly relies on other LLMs acting as judges. However, current evaluation paradigms typically yield a single score or ranking, answering which model is better but not why. While essential…

We introduce SLR, an end-to-end framework for systematic evaluation and training of Large Language Models (LLMs) via Scalable Logical Reasoning. Given a user's task specification, SLR automatically synthesizes (i) an instruction prompt for…

Entity Resolution (ER) is the problem of semi-automatically determining when two entities refer to the same underlying entity, with applications ranging from healthcare to e-commerce. Traditional ER solutions required considerable manual…

Generating interdisciplinary research ideas requires diverse domain expertise, but access to timely feedback is often limited by the availability of experts. In this paper, we introduce PersonaFlow, a novel system designed to provide…

Traditional approaches to test case generation often involve manual effort and incur significant computational overhead. Additionally, these approaches are not scalable, and hence, unsuitable for complex software systems. Recently, Large…

The rise of large language models (LLMs) has highlighted the importance of prompt engineering as a crucial technique for optimizing model outputs. While experimentation with various prompting methods, such as Few-shot, Chain-of-Thought, and…

Recommender systems have traditionally followed modular architectures comprising candidate generation, multi-stage ranking, and re-ranking, each trained separately with supervised objectives and hand-engineered features. While effective in…

Robust and comprehensive evaluation of large language models (LLMs) is essential for identifying effective LLM system configurations and mitigating risks associated with deploying LLMs in sensitive domains. However, traditional statistical…

Domain-driven design (DDD) is a powerful design technique for architecting complex software systems. This paper introduces a prompting framework that automates core DDD activities through structured large language model (LLM) interactions.…

Retrieval-augmented large language models (R-LLMs) combine pre-trained large language models (LLMs) with information retrieval systems to improve the accuracy of factual question-answering. However, current libraries for building R-LLMs…

Evaluating LLMs with a single prompt has proven unreliable, with small changes leading to significant performance differences. However, generating the prompt variations needed for a more robust multi-prompt evaluation is challenging,…

LLMs have gained immense popularity among researchers and the general public for its impressive capabilities on a variety of tasks. Notably, the efficacy of LLMs remains significantly dependent on the quality and structure of the input…

Large language models (LLMs) excel on many NLP benchmarks, but their behavior on real-world, semi-structured prediction remains underexplored. We present LlaMADRS, a benchmark for structured clinical assessment from dialogue built on the…

Process discovery aims to derive process models from event logs, providing insights into operational behavior and forming a foundation for conformance checking and process improvement. However, models derived solely from event data may not…

The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a…

The efficacy of large language models (LLMs) is heavily dependent on the quality of the underlying data, particularly within specialized domains. A common challenge when fine-tuning LLMs for domain-specific applications is the potential…