ArtificialIntelligence.io

The Signal

Everything that matters in AI, with our take.

Updated through the day. Every headline links straight to the source. The two lines underneath are ours.

arXiv cs.LGPaper

Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs

Unlearning is becoming a compliance requirement, not an option. This method targets layers rather than applying blanket updates, which should preserve model utility better. The quantization-resilience angle is practical: forgotten knowledge tends to leak back in after quantization, so handling that matters for deployment. Worth testing if you're operationalizing unlearning for privacy or copyright compliance.

arXiv cs.AIPaper

Causal Evidentiary Governance for High-Risk Machine Learning Systems

The EU AI Act and similar regulations are real constraints now, and post-hoc explainability is failing regulators. This paper offers a concrete mechanism: commit your causal assumptions to a DAG upfront, then bind each prediction to a cryptographic proof of which paths it took. For builders deploying models in credit, hiring, or resource allocation: this is the architecture regulators will likely demand. Implementing CEG now means you're not retraining on an enforcement deadline.

arXiv cs.AIPaperClaude Watch

What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models

This matters because regulatory oversight is coming and your guardrails may be security theater. The paper proves that models can output legally-sounding citations while ignoring the actual text they cite, meaning a compliance detector approving your output doesn't mean it actually read the rule. The implication is direct: audit your own guards before regulators do it for you, and don't trust activation probes to be rule-aware until this is fixed.

arXiv cs.CLPaper

A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation

Regulators are pushing LLMs into judgment roles for principle-based rules, and no existing method handles all four evaluation axes well. This benchmark matters because it's the first to test adversarial robustness and calibration together in a regulatory context. If you're building compliance automation for financial services or other regulated sectors, this defines what to measure. The Ceca method is a practical step toward auditable decisions.