Archives AI News

Community detection robustness of graph neural networks

arXiv:2509.24662v1 Announce Type: cross Abstract: Graph neural networks (GNNs) are increasingly widely used for community detection in attributed networks. They combine structural topology with node attributes through message passing and pooling. However, their robustness or lack of thereof with respect…

Speculative Safety-Aware Decoding

arXiv:2508.17739v2 Announce Type: replace-cross Abstract: Despite extensive efforts to align Large Language Models (LLMs) with human values and safety rules, jailbreak attacks that exploit certain vulnerabilities continuously emerge, highlighting the need to strengthen existing LLMs with additional safety properties to…

Dynamic Early Exit in Reasoning Models

arXiv:2504.15895v3 Announce Type: replace-cross Abstract: Recent advances in large reasoning language models (LRLMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks. However, overthinking in long CoT not only slows down the efficiency of problem…

Improving LLM Reasoning through Interpretable Role-Playing Steering

arXiv:2506.07335v2 Announce Type: replace-cross Abstract: Role-playing has emerged as an effective technique for enhancing the reasoning capabilities of large language models (LLMs). However, existing methods primarily rely on prompt engineering, which often lacks stability and interpretability. In this paper, we…

LLMs Are In-Context Bandit Reinforcement Learners

arXiv:2410.05362v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) excel at in-context learning (ICL), a supervised learning technique that relies on adding annotated examples to the model context. We investigate a contextual bandit version of in-context reinforcement learning (ICRL), where…