Db-gpt: Empowering database interactions with private large language models

S Xue, C Jiang, W Shi, F Cheng, K Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
The recent breakthroughs in large language models (LLMs) are positioned to transition
many areas of software. Database technologies particularly have an important entanglement …

Leveraging large language models for mobile app review feature extraction

Q Motger, A Miaschi, F Dell'Orletta, X Franch… - arXiv preprint arXiv …, 2024 - arxiv.org
Mobile app review analysis presents unique challenges due to the low quality, subjective
bias, and noisy content of user-generated documents. Extracting features from these reviews …

Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Models

Y Sun, Z Chu, Z Qin, K Ren - arXiv preprint arXiv:2406.16333, 2024 - arxiv.org
The rapid advancement of Text-to-Image (T2I) generative models has enabled the synthesis
of high-quality images guided by textual descriptions. Despite this significant progress, these …

PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods

Y Wang, X Li, B Wang, Y Zhou, Y Lin, H Ji… - arXiv preprint arXiv …, 2024 - arxiv.org
In domain-specific applications, GPT-4, augmented with precise prompts or Retrieval-
Augmented Generation (RAG), shows notable potential but faces the critical tri-lemma of …

Controllable Prompt Tuning For Balancing Group Distributional Robustness

H Phan, AG Wilson, Q Lei - arXiv preprint arXiv:2403.02695, 2024 - arxiv.org
Models trained on data composed of different groups or domains can suffer from severe
performance degradation under distribution shifts. While recent methods have largely …

Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuning

C Wu, G Jiang, D Lian - arXiv preprint arXiv:2406.12251, 2024 - arxiv.org
Lifelong prompt tuning has significantly advanced parameter-efficient lifelong learning with
its efficiency and minimal storage demands on various tasks. Our empirical studies …

Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models

S Xue, D Qi, C Jiang, W Shi, F Cheng, K Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
The recent breakthroughs in large language models (LLMs) are positioned to transition
many areas of software. The technologies of interacting with data particularly have an …