Combining large language models with enterprise knowledge graphs: a perspective on enhanced natural language understanding

L Mariotti, V Guidetti, F Mandreoli, A Belli… - Frontiers in Artificial …, 2024 - frontiersin.org
Knowledge Graphs (KGs) have revolutionized knowledge representation, enabling a graph-
structured framework where entities and their interrelations are systematically organized …

CTINEXUS: Leveraging Optimized LLM In-Context Learning for Constructing Cybersecurity Knowledge Graphs Under Data Scarcity

Y Cheng, O Bajaber, SA Tsegai, D Song… - arxiv preprint arxiv …, 2024 - arxiv.org
Textual descriptions in cyber threat intelligence (CTI) reports, such as security articles and
news, are rich sources of knowledge about cyber threats, crucial for organizations to stay …

Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models

S Singla, Z Wang, T Liu, A Ashfaq, Z Hu… - arxiv preprint arxiv …, 2024 - arxiv.org
Aligning Large Language Models (LLMs) traditionally relies on costly training and human
preference annotations. Self-alignment seeks to reduce these expenses by enabling models …

Fewer is More: Boosting Math Reasoning with Reinforced Context Pruning

X Huang, LL Zhang, KT Cheng, F Yang… - Proceedings of the …, 2024 - aclanthology.org
Abstract Large Language Models (LLMs) have shown impressive capabilities, yet they still
struggle with math reasoning. In this work, we propose CoT-Influx, a novel approach that …

Just Read the Codebook! Make Use of Quality Codebooks in Zero-Shot Classification of Multilabel Frame Datasets

M Ruckdeschel - … of the 31st International Conference on …, 2025 - aclanthology.org
The recent development of Large Language Models lowered the barrier to entry for using
Natural Language Processing methods for various tasks in the related scientific field of …

Prediction of tumor board procedural recommendations using large language models

M Aubreville, J Ganz, J Ammeling, E Rosbach… - European Archives of …, 2024 - Springer
Introduction Multidisciplinary tumor boards are meetings where a team of medical
specialists, including medical oncologists, radiation oncologists, radiologists, surgeons, and …

Fusing AI: Multimodal Language Models Inference Across Diverse Inputs

M Jovanović, M Campbell - Computer, 2024 - ieeexplore.ieee.org
Despite the various hurdles multimodal language models (MLMs) face, their broad
applicability outweighs the implementation effort. As MLM technologies advance, they will …

Revisiting the Superficial Alignment Hypothesis

M Raghavendra, V Nath, S Hendryx - arxiv preprint arxiv:2410.03717, 2024 - arxiv.org
The Superficial Alignment Hypothesis posits that almost all of a language model's abilities
and knowledge are learned during pre-training, while post-training is about giving a model …