4 articles tagged with #semantic-representation. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers have developed Semantic Representation Attack (SRA), a novel adversarial technique that bypasses LLM safety mechanisms by targeting semantic meaning rather than specific text patterns. The method achieves 99.71% attack success rates across 26 open-source models with strong cross-model transferability, raising significant security concerns for deployed AI systems.
Researchers propose a 'claim network' framework that transforms flat citation graphs into typed, stance-labeled networks for scientific literature. By reifying each cross-document reference as a typed claim with source, target, text, and stance classification, the approach enables richer document understanding than traditional knowledge graphs and demonstrates improvements in retrieval-augmented generation tasks.
Hi-SAM is a new hierarchical multi-modal recommendation framework that improves how AI systems process diverse data types (text, images) for personalized suggestions. The system addresses tokenization inefficiencies and architectural misalignments in existing approaches, achieving 6.55% improvement in core metrics when deployed at scale.
Researchers have developed supervised sparse auto-encoders (SAEs) that improve mechanistic interpretability of neural networks by addressing non-smoothness issues in L1 penalties and aligning learned features with human semantics. Validated on Stable Diffusion 3.5, the method enables compositional generalization and feature-level interventions for semantic image editing without prompt modification.
