Anudeex Shetty
PulseAugur coverage of Anudeex Shetty — every cluster mentioning Anudeex Shetty across labs, papers, and developer communities, ranked by signal.
-
Researchers induce "drunk language" in LLMs to expose safety vulnerabilities
Researchers have developed novel methods to induce "drunk language" in large language models (LLMs) to test their safety vulnerabilities. By employing persona-based prompting, causal fine-tuning, and reinforcement-based…
-
VISPA framework enables pluralistic alignment in LLMs
Researchers have developed VISPA, a novel framework designed to achieve pluralistic alignment in large language models. This training-free approach allows for direct control over how models express values by dynamically…
-
New TRACE method detects LLM ghostwriters in long texts
Researchers have developed a new method called TRACE to detect ghostwriters generated by large language models in long-form texts. This technique creates a unique fingerprint by analyzing token-level transition patterns…