LLaMA-E: Empowering E-commerce Authoring with Multi-Aspect Instruction Following

K Shi, X Sun, D Wang, Y Fu, G Xu, Q Li - arXiv preprint arXiv:2308.04913, 2023 - arxiv.org
E-commerce authoring involves creating attractive, abundant, and targeted promotional
content to drive product sales. The emergence of large language models (LLMs) introduces …

Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLM

P Yao, K Guzhva, D Barbosa - arXiv preprint arXiv:2407.04067, 2024 - arxiv.org
Symbolic sentence meaning representations, such as AMR (Abstract Meaning
Representation) provide expressive and structured semantic graphs that act as …

Multiple Knowledge-Enhanced Meteorological Social Briefing Generation

K Shi, X Peng, H Lu, Y Zhu, Z Niu - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Frequent meteorological disasters present new challenges for decision-making in disaster
response. As a timely and effective source of intelligent information, social media plays a …

A Survey of Meaning Representations–From Theory to Practical Utility

Z Sadeddine, J Opitz, F Suchanek - … of the 2024 Conference of the …, 2024 - aclanthology.org
Symbolic meaning representations of natural language text have been studied since at least
the 1960s. With the availability of large annotated corpora, and more powerful machine …

A topic‐controllable keywords‐to‐text generator with knowledge base network

L He, K Shi, D Wang, X Wang… - CAAI Transactions on …, 2024 - Wiley Online Library
With the introduction of more recent deep learning models such as encoder‐decoder, text
generation frameworks have gained a lot of popularity. In Natural Language Generation …

Expert-Guided Extinction of Toxic Tokens for Debiased Generation

X Sun, K Shi, H Tang, G Xu, Q Li - arXiv preprint arXiv:2405.19299, 2024 - arxiv.org
Large language models (LLMs) can elicit social bias during generations, especially when
inference with toxic prompts. Controlling the sensitive attributes in generation encounters …