Skill-RAG detects retrieval failure states from hidden representations and routes to one of four corrective skills to raise accuracy on persistent hard cases in open-domain QA and reasoning benchmarks.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
years
2026 5roles
other 1polarities
unclear 1representative citing papers
HERA evolves query-specific agent topologies via reward-guided sampling and refines role-specific prompts via credit assignment, yielding 38.69% average gains on six knowledge-intensive benchmarks.
WorldCup is a new multi-bit LLM watermarking framework that models token sampling as a communication channel and uses hierarchical competition with entropy-aware modulation for robust message embedding and recovery.
SALLIE detects jailbreaks in text and vision-language models by extracting residual stream activations, scoring maliciousness per layer with k-NN, and ensembling predictions, outperforming baselines on multiple datasets.
citing papers explorer
-
Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing
Skill-RAG detects retrieval failure states from hidden representations and routes to one of four corrective skills to raise accuracy on persistent hard cases in open-domain QA and reasoning benchmarks.
-
Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts
HERA evolves query-specific agent topologies via reward-guided sampling and refines role-specific prompts via credit assignment, yielding 38.69% average gains on six knowledge-intensive benchmarks.
-
WorldCup Sampling for Multi-bit LLM Watermarking
WorldCup is a new multi-bit LLM watermarking framework that models token sampling as a communication channel and uses hierarchical competition with entropy-aware modulation for robust message embedding and recovery.
-
SALLIE: Safeguarding Against Latent Language & Image Exploits
SALLIE detects jailbreaks in text and vision-language models by extracting residual stream activations, scoring maliciousness per layer with k-NN, and ensembling predictions, outperforming baselines on multiple datasets.
- Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook