Rear: A relevance-aware retrieval-augmented framework for open-domain question answering

Y Wang, R Ren, J Li, WX Zhao, J Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
Considering the limited internal parametric knowledge, retrieval-augmented generation
(RAG) has been widely used to extend the knowledge scope of large language models …

From text to life: On the reciprocal relationship between artificial life and large language models

E Nisioti, C Glanois, E Najarro, A Dai… - Artificial Life …, 2024 - direct.mit.edu
Abstract Large Language Models (LLMs) have taken the field of AI by storm, but their
adoption in the field of Artificial Life (ALife) has been, so far, relatively reserved. In this work …

From revisions to insights: converting radiology report revisions into actionable educational feedback using generative AI models

S Lyo, S Mohan, A Hassankhani, A Noor… - Journal of Imaging …, 2024 - Springer
Expert feedback on trainees' preliminary reports is crucial for radiologic training, but real-
time feedback can be challenging due to non-contemporaneous, remote reading and …

Thus Spake Long-Context Large Language Model

X Liu, R Li, M Huang, Z Liu, Y Song, Q Guo… - arxiv preprint arxiv …, 2025 - arxiv.org
Long context is an important topic in Natural Language Processing (NLP), running through
the development of NLP architectures, and offers immense opportunities for Large …

Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization

E Hua, C Jiang, X Lv, K Zhang, N Ding, Y Sun… - arxiv preprint arxiv …, 2024 - arxiv.org
Extending the context length of Language Models (LMs) by improving Rotary Position
Embedding (RoPE) has become a trend. While existing works mainly address RoPE's …

Evaluating Large Language Models in Vulnerability Detection Under Variable Context Windows

J Lin, D Mohaisen - arxiv preprint arxiv:2502.00064, 2025 - arxiv.org
This study examines the impact of tokenized Java code length on the accuracy and
explicitness of ten major LLMs in vulnerability detection. Using chi-square tests and known …

PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling

A Ma, Y Pan, A Farahmand - arxiv preprint arxiv:2502.01925, 2025 - arxiv.org
Many-shot jailbreaking circumvents the safety alignment of large language models by
exploiting their ability to process long input sequences. To achieve this, the malicious target …