Metraipolis › archive › dc_470d99d7c841

Concept-Grounded Attention: A Controlled Evaluation of Graph-Injected Attention, Temporal Versioning, and Epistemic Status — arXiv:2609.38684

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38684
License (as archived)
CC0-1.0
Archived
2026-10-07T12:42:02.967Z
SHA-256 of the archived text
a2522fe5463658b3d777f672b601ab5c51340b11ef18efc7108135dbadc05622
Stable URL of this page
https://metraipolis.com/documento/dc_470d99d7c841

How to cite

Concept-Grounded Attention: A Controlled Evaluation of Graph-Injected Attention, Temporal Versioning, and Epistemic Status — arXiv:2609.38684 — arXiv (en), https://arxiv.org/abs/2609.38684 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_470d99d7c841 (Metraipolis archive dc_470d99d7c841, sha256 a2522fe5463658b3d777f672b601ab5c51340b11ef18efc7108135dbadc05622)
BibTeX
@misc{dc470d99d7c841,
  title = {Concept-Grounded Attention: A Controlled Evaluation of Graph-Injected Attention, Temporal Versioning, and Epistemic Status — arXiv:2609.38684},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38684},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_470d99d7c841; sha256 a2522fe5463658b3d777f672b601ab5c51340b11ef18efc7108135dbadc05622},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38684. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Knowledge-intensive language-model systems typically represent external knowledge as text chunks or static graphs, with limited support for concept evolution, point-in-time reasoning, and distinctions between validated and inferred knowledge. We introduce the Concept Lifecycle Model (CLM), which represents concepts as persistent, graph-grounded, temporally versioned entities with explicit provenance and epistemic status, and Concept-Grounded Attention (CGA), which injects concept-graph structure into transformer computation through graph-biased self-attention (Form A) and gated cross-attention over concept nodes (Form B). We evaluate the framework in controlled settings using disabled-mechanism baselines. On 200 MuSiQue and HotpotQA questions with retrieval fixed, concept-graph retrieval recovers explicit multi-hop paths but does not improve evidence recall. Form A appears to steer attention, with 2.76 times more attention on gold than distractor concepts, but the same ratio occurs when Form A is disabled; the learned bias is negligible and no answers change. An identity-preserving Form B improves F1 from 0.188 to 0.221, but control concepts yield 0.213, indicating that most of the gain reflects added capacity. On LongMemEval, explicit temporal representation improves answer accuracy by 13 to 25 points across all tested generators, up to 122B parameters, while simplified CLM version resolution performs similarly to dated serialization because concept identity is not established reliably. On a synthetic source-independence task, protocol-derived epistemic status reduces unsupported assertions from 28% to 0.1% in a fine-tuned small model and from 19-68% to 0-5% in 72-122B models. Overall, the results support making temporal validity and epistemic status explicit, while showing that graph-attention diagnostics are not informative without disabled-mechanism controls.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38684 — 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 2026-10-07T12:14:13.662Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).