We have 4 of 11 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Transformer models such as BERT and Vision Transformer~(ViT) achieve strong performance via densely parameterized attention backbones. However, the least significant bits~(LSBs) of their 32-bit floating-point weights can be abused as covert channels to conceal malicious payloads, posing a serious threat to the AI model...
This work operationalizes overclaiming as a final response that reports work that the agent's own transcript shows it did not do, for example, claiming to have read a file it never opened, showing that claims of completion can conceal substantive failures.
Latent Personality Alignment (LPA) is introduced, which replaces explicit harm refusal with adversarial training on just 66 harm-agnostic statements drawn from psychometric personality literature, hypothesizing that personality-anchored representations share latent structure with harm avoidance, so adversarially stabil...
Training minimal-capacity linear probes on frozen hidden states of three open-weight 7-8B models across seven completion-style datasets finds three converging pieces of evidence that LLMs maintain a plan-like internal representation of output length, interpreted as evidence that LLMs maintain a plan-like internal repre...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
