7 papers
Interpretable vs Learned Encoders for High-Cardinality Fraud Detection
Xiao Han, Jingjing Liu, Moxuan Zheng +2
A total of seven categorical encoding methods were tested on the IEEE-CIS fraud benchmark dataset (590,540 records, 3.5% positives, 8 high-cardinality columns). The encoders were e…
Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection
Lixing Lin, Juli You, Yue Li +4
Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that dis…
Gender Bias in MT for a Genderless Language: New Benchmarks for Basque
Amaia Murillo, Olatz-Perez-de-Viñaspre, Naiara Perez
Large language models (LLMs) and machine translation (MT) systems are increasingly used in our daily lives, but their outputs can reproduce gender bias present in the training data…
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
DeepSeek-AI, Daya Guo, Dejian Yang +195
General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-tho…
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
DeepSeek-AI, Aixin Liu, Aoxue Mei +260
We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 ar…
Verifying Computational Graphs in Production-Grade Distributed Machine Learning Frameworks
Kahfi S. Zulkifli, Wenbo Qian, Shaowei Zhu +3
Modern machine learning frameworks support very large models by incorporating parallelism and optimization techniques. Yet, these very techniques add new layers of complexity, intr…