LCGuard applies adversarial training to transform KV cache artifacts in multi-agent LLMs, reducing reconstructable sensitive information while preserving task performance.
LLM Safety From Within: Detecting Harmful Content with Internal Representations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Guard models are widely used to detect harmful content in user prompts and LLM responses. However, state-of-the-art guard models rely solely on terminal-layer representations and overlook the rich safety-relevant features distributed across internal layers. We present SIREN, a lightweight guard model that harnesses these internal features. By identifying safety neurons via linear probing and combining them through an adaptive layer-weighted strategy, SIREN builds a harmfulness detector from LLM internals without modifying the underlying model. Our comprehensive evaluation shows that SIREN substantially outperforms state-of-the-art open-source guard models across multiple benchmarks while using 250 times fewer trainable parameters. Moreover, SIREN exhibits superior generalization to unseen benchmarks, naturally enables real-time streaming detection, and significantly improves inference efficiency compared to generative guard models. Overall, our results highlight LLM internal states as a promising foundation for practical, high-performance harmfulness detection.
years
2026 3verdicts
UNVERDICTED 3representative citing papers
MINER fuses internal transformer layer representations via probing and adaptive sparse fusion to improve dense single-vector retrieval quality on visual documents by up to 4.5% nDCG@5 while preserving efficiency.
AERIC uses a 387-parameter head on LLM hidden states for same-pass anticipatory detection of implicit harm, reporting AUROC gains on DiaSafety and Harmful Advice plus low-latency trigger rates on HarmBench and SocialHarmBench.
citing papers explorer
-
LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
LCGuard applies adversarial training to transform KV cache artifacts in multi-agent LLMs, reducing reconstructable sensitive information while preserving task performance.
-
MINER: Mining Multimodal Internal Representation for Efficient Retrieval
MINER fuses internal transformer layer representations via probing and adaptive sparse fusion to improve dense single-vector retrieval quality on visual documents by up to 4.5% nDCG@5 while preserving efficiency.
-
AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue
AERIC uses a 387-parameter head on LLM hidden states for same-pass anticipatory detection of implicit harm, reporting AUROC gains on DiaSafety and Harmful Advice plus low-latency trigger rates on HarmBench and SocialHarmBench.