中文
相关论文

相关论文: Intent-Aware Schema Generation And Refinement For …

200 篇论文

Context: The emergence of Large Language Models (LLMs) has significantly transformed Software Engineering (SE) by providing innovative methods for analyzing software repositories. Objectives: Our objective is to establish a practical…

Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer little support for iterative specification, refinement, and…

Extracting structured information from text, such as key-value pairs that could augment tabular data, is quite useful in many enterprise use cases. Although large language models (LLMs) have enabled numerous automated pipelines for…

计算与语言 · 计算机科学 2025-07-30 Satyananda Kashyap , Sola Shirai , Nandana Mihindukulasooriya , Horst Samulowitz

Automating the decision of whether a code change requires manual review is vital for maintaining software quality in modern development workflows. However, the emergence of new programming languages and frameworks creates a critical…

软件工程 · 计算机科学 2025-09-08 Yogev Cohen , Dudi Ohayon , Romy Somkin , Yehudit Aperstein , Alexander Apartsin

Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of…

Scientific progress depends on the continual generation of innovative re-search ideas. However, the rapid growth of scientific literature has greatly increased the cost of knowledge filtering, making it harder for researchers to identify…

计算与语言 · 计算机科学 2026-04-23 Shuai Chen , Chengzhi Zhang

Large collections of tabular data from data lakes, web tables and open data portals often originate from heterogeneous sources, leading to representational inconsistencies. Understanding and organizing such repositories therefore remains a…

数据库 · 计算机科学 2026-05-27 Zhenyu Wu , Jiaoyan Chen , Norman W. Paton

Large collections of tabular data from data lakes, web tables and open data portals often originate from heterogeneous sources, leading to representational inconsistencies. Understanding and organizing such repositories therefore remains a…

数据库 · 计算机科学 2026-05-27 Zhenyu Wu , Jiaoyan Chen , Norman W. Paton

Large language models (LLMs) have demonstrated impressive abilities in generating unstructured natural language according to instructions. However, their performance can be inconsistent when tasked with producing text that adheres to…

计算与语言 · 计算机科学 2024-02-22 Yinghao Li , Rampi Ramprasad , Chao Zhang

Tabular data synthesis involves not only multi-table synthesis but also generating multi-modal data (e.g., strings and categories), which enables diverse knowledge synthesis. However, separating numerical and categorical data has limited…

机器学习 · 计算机科学 2025-03-21 Tung Sum Thomas Kwok , Chi-Hua Wang , Guang Cheng

Recent advances in large language models (LLMs) have greatly improved Text-to-SQL performance for single-table queries. But, it remains challenging in multi-table databases due to complex schema and relational operations. Existing methods…

计算与语言 · 计算机科学 2025-05-26 Poojah Ganesan , Rajat Aayush Jha , Dan Roth , Vivek Gupta

Large language models offer a scalable alternative to human coding for data annotation tasks, enabling the scale-up of research across data-intensive domains. While LLMs are already achieving near-human accuracy on objective annotation…

计算与语言 · 计算机科学 2026-01-21 Zhen Xu , Vedant Khatri , Yijun Dai , Xiner Liu , Siyan Li , Xuanming Zhang , Renzhe Yu

Large language models (LLMs) have revolutionized the field of AI, demonstrating unprecedented capacity across various tasks. However, the inference process for LLMs comes with significant computational costs. In this paper, we propose an…

计算与语言 · 计算机科学 2023-05-30 Zangwei Zheng , Xiaozhe Ren , Fuzhao Xue , Yang Luo , Xin Jiang , Yang You

Reliability in cell type annotation is challenging in single-cell RNA-sequencing data analysis because both expert-driven and automated methods can be biased or constrained by their training data, especially for novel or rare cell types.…

The LLM-as-a-judge paradigm enables flexible, user-defined evaluation, but its effectiveness is often limited by the scarcity of diverse, representative data for refining criteria. We present a tool that integrates synthetic data generation…

This research pioneers the use of fine-tuned Large Language Models (LLMs) to automate Systematic Literature Reviews (SLRs), presenting a significant and novel contribution in integrating AI to enhance academic research methodologies. Our…

When developing text classification models for real world applications, one major challenge is the difficulty to collect sufficient data for all text classes. In this work, we address this challenge by utilizing large language models (LLMs)…

计算与语言 · 计算机科学 2025-08-15 Chenhao Xue , Yuanzhe Jin , Adrian Carrasco-Revilla , Joyraj Chakraborty , Min Chen

Aligning large language models (LLMs) to diverse human preferences is fundamentally challenging since criteria can often conflict with each other. Inference-time alignment methods have recently gained popularity as they allow LLMs to be…

机器学习 · 统计学 2026-02-03 Shokichi Takakura , Akifumi Wachi , Rei Higuchi , Kohei Miyaguchi , Taiji Suzuki

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

密码学与安全 · 计算机科学 2025-08-26 Wei Jie Yeo , Ranjan Satapathy , Erik Cambria

Accurately predicting the intent of customer support requests is vital for efficient support systems, enabling agents to quickly understand messages and prioritize responses accordingly. While different approaches exist for intent…

计算与语言 · 计算机科学 2023-09-19 Nichal Narotamo , David Aparicio , Tiago Mesquita , Mariana Almeida