9 papers
Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Laws
Liu Ziyin, Yizhou Xu, Tomaso Poggio +1
Neural networks trained by gradient descent on a smooth cost function can nevertheless learn in steps: the cost holds on long plateaus and then drops abruptly. Meanwhile, training…
It's How You Ask: Gender-Associated Linguistic Bias in LLMs
Katherine Van Koevering, Anjalie Field
Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more commonly used…
Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning
Valentin Noël
Verifying whether a language model is genuinely reasoning or pattern-matching remains an open problem: learned verifiers are expensive, and output-based heuristics are brittle. We…
Spectral Guardrails for Agents in the Wild: Detecting Tool Use Hallucinations via Attention Topology
Valentin Noël
Deploying autonomous agents in the wild requires reliable safeguards against tool use failures. We propose a training free guardrail based on spectral analysis of attention topolog…
Spectral Archaeology: The Causal Topology of Model Evolution
Valentin Noël
Behavioral benchmarks tell us \textit{what} a model does, but not \textit{how}. We introduce a training-free mechanistic probe using attention-graph spectra. Treating each layer as…
HalluGraph: Auditable Hallucination Detection for Legal RAG Systems via Knowledge Graph Alignment
Valentin Noël, Elimane Yassine Seidou, Charly Ken Capo-Chichi +1
Legal AI systems powered by retrieval-augmented generation (RAG) face a critical accountability challenge: when an AI assistant cites case law, statutes, or contractual clauses, pr…