Metraipolis › archive › dc_e6b3cbf7c239

Combining Hierarchical Cognitive Process with Process Supervision for Interpretable Scene Safety Understanding — arXiv:2609.26399

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26399
License (as archived)
CC0-1.0
Archived
2026-10-08T14:36:46.149Z
SHA-256 of the archived text
fc923415fe7cdd75b1efb85996346000b55946cce9c69fcb6eda2261fd7c82c6
Stable URL of this page
https://metraipolis.com/documento/dc_e6b3cbf7c239

How to cite

Combining Hierarchical Cognitive Process with Process Supervision for Interpretable Scene Safety Understanding — arXiv:2609.26399 — arXiv (en), https://arxiv.org/abs/2609.26399 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6b3cbf7c239 (Metraipolis archive dc_e6b3cbf7c239, sha256 fc923415fe7cdd75b1efb85996346000b55946cce9c69fcb6eda2261fd7c82c6)
BibTeX
@misc{dce6b3cbf7c239,
  title = {Combining Hierarchical Cognitive Process with Process Supervision for Interpretable Scene Safety Understanding — arXiv:2609.26399},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26399},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6b3cbf7c239; sha256 fc923415fe7cdd75b1efb85996346000b55946cce9c69fcb6eda2261fd7c82c6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26399. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scene safety understanding plays a life-or-death role in situational awareness in various critical domains. Traditional methods that rely on learning direct mappings between scenes and safety levels often lack interpretability, limiting their reliability in critical applications. An effective approach to overcoming this challenge lies in interpreting human cognitive processes and equipping machine models with analogous cognitive capabilities. This work explores an effective way of integrating scene safety cognitive process modeling and process supervision. Specifically, we first construct a hierarchical cognitive safety structure, which motivates the development of a novel, high-quality scene safety understanding dataset based on multi-step reasoning with process labels. This dataset serves both as a benchmark and a resource to improve the safety reasoning capabilities of Large Language Models (LLMs), while also enabling a granular analysis of intermediate reasoning steps through information flow and saliency-based techniques. Building upon this foundation, we introduce a modular and flexible process supervision framework that reflects the hierarchical nature of human cognition. This framework leverages LLMs as the core architecture and incorporates Low-Rank Adaptation(LoRA) and Mixture-of-Experts (MoE) strategies to enable specialization and collaboration among expert modules, each tasked with specific sub-processes of the overall reasoning chain. Systematic experimental evaluations and analyses confirm that our framework exhibits superior interpretability and performance characteristics compared to traditional approaches.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.26399 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:46:15.747Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).