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.CLPaper10d ago

Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection

The core insight is that LLMs can use symbolic reasoning (SQL) to validate their own outputs without explicit supervision. This is a practical technique for RAG and retrieval-grounded workflows where the reference material is structured. Not a paradigm shift but a useful pattern to test against your hallucination detection baseline.

research rag hallucination-detection neurosymbolic

arXiv cs.CLPaper14d ago

From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs

Hallucination detection through API-only signals is useful for production systems, and the hybrid approach addresses real failure modes where one signal alone misfires. The methods require multiple model calls and may be expensive at scale, but it's practical for high-stakes workflows. Test CoCoA on your highest-risk applications first.

research hallucination-detection evaluation