Qwen 14B
PulseAugur coverage of Qwen 14B — every cluster mentioning Qwen 14B across labs, papers, and developer communities, ranked by signal.
-
LLMs easily swayed by single persuasive argument, research finds
A new research paper reveals that large language models are highly susceptible to adversarial persuasion, with a single targeted argument capable of drastically reducing their accuracy, even when the argument is factual…
-
New LENS protocol evaluates LLM narrative unlearning effectiveness
Researchers have developed a new evaluation protocol called LENS (Level-based Evaluation of Narrative Suppression) to assess the effectiveness of machine unlearning in preventing large language models from reproducing d…
-
Mac Mini with Local LLMs Replaces Paid AI Subscriptions
A developer explores replacing paid AI subscriptions with a local setup on a Mac Mini, finding that modern consumer hardware, particularly Apple Silicon's unified memory, can efficiently run powerful open-source LLMs. C…
-
New UK GDPR compliance dataset released for small businesses
A new dataset has been released containing 5,000 synthetic question-answer pairs focused on UK GDPR compliance for small businesses. The dataset includes practical questions, answers with specific article references and…
-
RTX 4090 leads GPU recommendations for Ollama LLM users
For users running large language models locally with Ollama, the choice of GPU is critical, with VRAM and memory bandwidth being the most important factors. The RTX 4090 is recommended as the best all-around option for …
-
New framework evaluates NLP explanation robustness in black-box enterprise systems
A new framework for evaluating the robustness of explanations in enterprise NLP systems has been proposed. This framework uses a leave-one-out occlusion method to assess how stable token-level explanations are under var…