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.CLPaper14d ago

DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models

This addresses a real deployment problem: incorporating proprietary knowledge without expensive instruction-tuning runs. The technique is sound but incremental, trading the synthetic data generation cost of RAFT for the cost of base model retraining. Worth evaluating if you're managing a suite of specialized models, but not a fundamental shift.

research finetuning knowledge-injection

arXiv cs.AIPaper15d ago

From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification

This is a solid RAG-plus-reasoning pattern for high-cardinality classification. The signal that it transfers to smaller models is worth noting, but the paper is narrowly scoped to text taxonomies. Useful if you're classifying into semantically dense label spaces, less so if your labels are already well-separated.

llm classification retrieval knowledge-injection