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.

research1156 agents716 infra561 labs317 culture268 capital253 regulation233 claude175 openai149 safety103 security89 evaluation77 reasoning61 alignment52 benchmarks50 interpretability48

arXiv cs.AIPaper10d ago

Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence

The core finding is uncomfortable: the factors LLMs say drove their decisions often don't match what actually changed the output under intervention. This matters if you're using LLM explanations to monitor or debug agent systems. An operator trusting the named factors to diagnose errors will often be fooled. The paper suggests dedicated models are better, but for now, treat LLM explanations as decorative rather than diagnostic. If explainability is part of your compliance or safety story, you need to read this.

research explainability agents

arXiv cs.LGPaper13d ago

Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning

The idea of using explanation quality to guide privacy noise allocation is clever, but the scope is narrow: it's tested only on image classification in federated settings. Clinical diagnosis is mentioned as motivation but not actually evaluated. The core innovation may not generalize to other domains or modalities.

research federated-learning privacy explainability

arXiv cs.AIPaper1mo ago

Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis

Explainability and attribution in agentic systems is a real need, especially in security operations. This paper tackles it narrowly: incident logs and similar high-stakes text. The contribution is real but domain-specific. If you're deploying agents that need to justify decisions to security analysts, read this. If you're building general-purpose agents, note it and move on.

agents explainability security