Large Language Models (LLMs) are transforming blockchain security and analytics, yet a systematic evaluation of their capabilities remains limited. This survey provides a comprehensive, AI‑centric assessment of LLM‑based methods across over 70 recent studies spanning 11 application domains, such as security auditing, t...
Collette Eguakun Okundia, C. Akcora, Arijit Khan· Proceedings of the Thirty-Fi...· 0 citations
Deployment of Large Language Models (LLMs) on memory-constrained edge devices relies heavily on aggressive post-training quantization. However, evaluating these models is largely based on zero-shot task accuracy, which depends solely on argmax predictions and is insensitive to changes in the underlying predictive distr...
Shahzeb Qamar, L. Sparrenberg, Christian Bauckhage et al.· 1 citation
This work proposes Correctness Agreement, a decision-level metric that can measure the intersection of correct predictions between the base model and its quantized variant, and finds that the base and quantized variants usually have a shift in behavior even when accuracy and perplexity are preserved.
Baha Rababah, Shahzeb Qamar, Lorenz Sparrenberg et al.· arXiv.org· 0 citations
The proposed method, TRicci, extends classical Forman-Ricci curvature to directed weighted temporal graphs by capturing structural support, temporal recency, and local interaction competition and suggests that temporal curvature can serve as a principled basis for scalable temporal graph learning by preserving predicti...
Poupak Azad, C. Akcora, Kiarash Shamsi· 0 citations
This work introduces Topoformer, a lightweight and scalable framework for graph representation learning that encodes topological structure into attention-friendly sequences by decomposing a graph into a short, ordered sequence of topological tokens by slicing over node or edge filtrations.
Md Joshem Uddin, Astrit Tola, C. Akcora et al.· arXiv.org· 1 citation
TopoTuner is competitive with full fine-tuning while training only 1-2% of the model parameters, and outperforms LoRA in 7 out of 9 model-dataset settings, which can change up to 39.57% of the projection parameters.
