Metraipolis › archive › dc_7cc2efc22b1a

CoLink: Global Compression and Knowledge Linking for Multi-Turn Dialogue Modeling — arXiv:2610.34335

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.34335
License (as archived)
CC0-1.0
Archived
2026-10-27T08:01:19.786Z
SHA-256 of the archived text
9e3b4b73a1f3d810648a135bcc709a4e7578200e2c873fbc6b708f6987225755
Stable URL of this page
https://metraipolis.com/documento/dc_7cc2efc22b1a

How to cite

CoLink: Global Compression and Knowledge Linking for Multi-Turn Dialogue Modeling — arXiv:2610.34335 — arXiv (en), https://arxiv.org/abs/2610.34335 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cc2efc22b1a (Metraipolis archive dc_7cc2efc22b1a, sha256 9e3b4b73a1f3d810648a135bcc709a4e7578200e2c873fbc6b708f6987225755)
BibTeX
@misc{dc7cc2efc22b1a,
  title = {CoLink: Global Compression and Knowledge Linking for Multi-Turn Dialogue Modeling — arXiv:2610.34335},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.34335},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cc2efc22b1a; sha256 9e3b4b73a1f3d810648a135bcc709a4e7578200e2c873fbc6b708f6987225755},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34335. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Extracting salient information from long-horizon dialogue histories remains a significant challenge for Large Language Models (LLMs) due to the restricted context windows and efficient retrieval challenges. Current methods typically rely on history organization or local token-level optimization, suffering from information loss, retrieval redundancy, and myopic attention. Inspired by the view in cognitive science that dialogue constitutes sense-making and memory association, we propose CoLink, a framework that enhances LLMs' global context awareness in domain-specific multi-turn dialogues through information linking and compression. CoLink first clusters historical contexts into topic graphs to establish cross-semantic associations with external knowledge. Guided by the adaptive control of thought, it then retrieves and activates knowledge via synergizing semantic relevance and graph-structural topology. Crucially, to achieve effective compression of history and knowledge, we ground multi-turn dialogues in information theory and derive a principled optimization objective for extracting the core sense-making information. Coupled with a competitive slot mechanism, CoLink condenses the global context into dedicated memory and knowledge slots, efficiently distilling lengthy, redundant inputs into an extremely compact latent representation. Extensive empirical results on both public and our MMD datasets validate CoLink's superiority and generalizability in knowledge linking and sense modeling.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.34335 — 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 2026-10-27T07:55:30.893Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).