Test-time adaptation (TTA) has been a widely-studied paradigm for adapting well-trained models to distributionally shifted test data. Recent works extend TTA to graphs using graph augmentations and self-supervised objectives in Euclidean space. However, graph-structured data often exhibit heterogeneity where semantic s...
Ling-Wei Wei, Dou Hu, Li Sun et al.· Proceedings of the 32nd ACM...· 0 citations
CorVer (Corpus Verify) is a lightweight training-time approach to process supervision that derives sentence-level rewards from corpus co-occurrence statistics and outperforms the unmodified models in all standard factual-QA settings.
Shi-Chen Fan, Hao-Chang Hao, De-Hai Min et al.· 5 citations
DynGraphAgentBench, an executable benchmark for agentic lifecycle control under delayed feedback, is introduced, an executable benchmark for agentic lifecycle control under delayed feedback that measures detection utility with average precision and capture at fixed review depth, and characterize adaptation through mode...
Yu-Wei Han, Ling-Wei Wei, Wooseong Yang et al.· 0 citations
A role-layer framework is introduced to unify LLM risks and defenses, and identifies three key open challenges: moving from static detection accuracy to budgeted ecosystem-level risk evaluation, hardening LLM-centered verification pipelines against adversarial manipulation, and deploying auditable human-in-the-loop ver...
Lingwei Wei, Dou Hu, Wei Zhou 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.
