Enterprise RAG deployments face a critical reliability gap: while LLMs satisfy 80% of individual constraints, only 26.8% of responses meet all requirements simultaneously, revealing a 57-point orchestration gap, which provides a reproducible foundation for measuring and closing these gaps.
It is shown that preserving or reinjecting the weight offset fails to maintain protection, indicating that preventative steering relies on active adaptation rather than a static defense, and proposes Progressive Intensity Scheduling (PIS), which improves safety robustness over static-strength steering while reducing ha...
Jing Guan, Ya-Chao Yang, Zhao-Liang Liu et al.· 0 citations
A*-Thought-V2 is presented, a geometric dynamics of LLM guided framework that models CoT as a hidden-state trajectory and replaces hard deletion with an explicit-implicit interleaved latent architecture that reflects broader soft targets that encourage richer step-level feature learning.
Xiao-An Xu, Si-Yuan Liu, Shuo Wang et al.· 1 citation
TrustDABench is introduced, a benchmark that operationalizes two diagnostic questions of LLM reliability and robustness and suggests that stronger evidence-boundary recognition and representation-invariant reasoning are still needed for reliable structured-data analysis.
Boshen Shi, Yize Liu, Chen Zhao et al.· 0 citations
This work advocates for Joint Online-Offline Fine-Tuning as a superior paradigm that breaks the convention of restricting offline data to SFT and online data to RFT, and provides the first comprehensive survey focusing specifically on the synchronization of data provenance.
Tai-Hang Zhen, Guang Yang, Chen-Zhang Li et al.· Proceedings of the Thirty-Fi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
