Metraipolis › archive › dc_bb98029eb0c4
ReCBM: Uncertainty-Gated Relational Reasoning for Concept Bottleneck Models — arXiv:2608.10004
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10004
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:08:09.911Z
- SHA-256 of the archived text
10c94c8340cbbfba6f8cf7f2ef725f5c626f69bbb0ccec49e2a57941f76576d4- Stable URL of this page
https://metraipolis.com/documento/dc_bb98029eb0c4
How to cite
ReCBM: Uncertainty-Gated Relational Reasoning for Concept Bottleneck Models — arXiv:2608.10004 — arXiv (en), https://arxiv.org/abs/2608.10004 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb98029eb0c4 (Metraipolis archive dc_bb98029eb0c4, sha256 10c94c8340cbbfba6f8cf7f2ef725f5c626f69bbb0ccec49e2a57941f76576d4)
BibTeX
@misc{dcbb98029eb0c4,
title = {ReCBM: Uncertainty-Gated Relational Reasoning for Concept Bottleneck Models — arXiv:2608.10004},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10004},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb98029eb0c4; sha256 10c94c8340cbbfba6f8cf7f2ef725f5c626f69bbb0ccec49e2a57941f76576d4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10004. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Concept Bottleneck Models (CBMs) provide an interpretable framework by grounding predictions in human-understandable concepts, enabling semantic inspection and test-time intervention. Recent variants have improved CBMs through richer concept representations, uncertainty estimation, and dependency modeling. However, robust reasoning under unreliable concept states remains underexplored. Without such reasoning, misleading semantic evidence can propagate through the bottleneck, compromising both explanations and downstream predictions. To address this issue, we propose ReCBM, an uncertainty-gated relational reasoning framework for CBMs. ReCBM introduces semantically defined concept relations into the bottleneck and uses uncertainty to guide their refinement. By modeling co-occurrence, implication, and exclusion, ReCBM specifies how evidence is exchanged across concepts, while uncertainty modulates the contribution of each concept during this process. Experiments across diverse datasets showed that ReCBM improved concept and task recovery under missing and flipped concepts, supported uncertainty-aware intervention, and extracted compact task-relevant concept subsets without degrading downstream performance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.10004 — 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 2026-10-19T05:57:28.232Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).