Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics. This format bound limits RSI to improvement within a machin...
Zi-Hang Tan, Lei-Xin Sun, Zi-Tong Shi et al.· 0 citations
It is suggested that LLMs differ not only in baseline risk disposition, but also in the risk signals they respond to and the flexibility with which they adjust, providing a behavioural basis for auditing risk-sensitive decision-making in interactive settings.
Xuan-Kun Rong, Wenke Huang, Bo Du et al.· arXiv.org· 0 citations
This work shows that scenario-wrapped prompts activate internal scenario directions whose causal steering consistently reduces refusal scores, and proposes Concept2Scenario, a concept-based attribution framework for vulnerable scenario discovery that instantiates a broad concept space with a sparse autoencoder, transla...
ReFrame is a training-free multimodal input reframing framework where two agents share a lightweight locally deployed MLLM: the evidence-generation agent constructs complementary risk and utility evidence, and the rewrite-and-routing agent converts it into a safe proxy prompt and image-routing decision before calling t...
Wenzheng Jiang, Xuan-Kun Rong, Yuan-Zhao Zhai et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
