Applied Explainability for Large Language Models: A Comparative Study

arXiv:2605.00123v1 Announce Type: new Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we

arXiv:2604.13206v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly integrated into agentic workflows, their unpredictability stemming from numerical

arXiv:2605.15208v1 Announce Type: cross Abstract: Large Language Models are routinely compressed via post-training quantization to reduce inference costs and memory footprint for

arXiv:2604.15898v1 Announce Type: new Abstract: For around a decade, non-symbolic methods have been the option of choice when explaining complex machine learning (ML) models.

arXiv:2603.18532v1 Announce Type: cross Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar

arXiv:2604.27713v1 Announce Type: new Abstract: The risks posed by AI features are increasing as they are rapidly integrated into software applications. In response, regulations

arXiv:2603.18015v1 Announce Type: cross Abstract: Although automated harmful content detection systems are frequently used to monitor online platforms, moderators and end users

arXiv:2605.11496v1 Announce Type: new Abstract: Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently