HoloAegis is a minimally parametric topological inference framework that uses frozen representations to map text onto the unit sphere and makes decisions via Gibbs‑Boltzmann free‑energy differences over pre‑computed anchor centroids. On a frozen three‑benchmark protocol, it matches WildGuard‑7B on toxicity, outperforms it on harmful behaviors, but underperforms on oversafety detection, while ShieldGemma‑2B fails on indirect harms. The study demonstrates that geometric guardrails can substitute for LLM judges in some cases and must defer to them in others, with anchor banks reducing score variance and boundary displacement.
By Tak Ho Alex Li, Kaijie Liu, Lik-Hang Lee, Kin Chung Ho, Ping Shum, Michael K. Ng
arXiv:2605. 22873v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial?
By Wei Xia, Haoqing Wang, Zhi-Hong Deng, Yehui Tang
The paper shows that large language models (LLMs) naturally organize their hidden state manifolds into small‑world networks, enabling efficient multi‑hop reasoning. By converting similarity matrices into unweighted graphs, the authors trace connectivity between distant semantic anchors and find a sharp topological phase transition: deep reasoning layers compress conceptual distances into paths bounded by six semantic hops, while early syntactic layers remain fragmented. The framework is applied to zero‑shot hallucination detection in Retrieval‑Augmented Generation, revealing that factual generations preserve a ~3‑hop structure, whereas hallucinations collapse the topology.
By Md. Faiyaz Abdullah Sayeedi
arXiv:2607. 03329v1 Announce Type: new Abstract: Conventional uniform convergence bounds and empirical risk minimization break down in massive over-parameterized models, such as large language transformers and biological sequence networks.
By Bing Cheng, Yi-Shuai Niu, Howell Tong, Shing-Tung Yau
arXiv:2603. 10384v3 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning.
By Xinyan Jiang, Ninghao Liu, Di Wang, Lijie Hu
arXiv:2607. 17962v1 Announce Type: cross Abstract: TabPFN is a transformer-based foundation model for tabular prediction that performs inference without task-specific training by conditioning on a support set and query inputs.
By James Hu, Mahdi Ghelichi