Metraipolis › archive › dc_577464f381e2

DiffIE: Diffusion-based Open Information Extraction — arXiv:2609.02315

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.02315
License (as archived): CC0-1.0
Archived: 2026-10-17T03:37:44.616Z
SHA-256 of the archived text: 4afdfcb9d9a272deb530dc875e296002830f3f70d4b4ff7e4d9f42eb14ef81ea
Stable URL of this page: https://metraipolis.com/documento/dc_577464f381e2

How to cite

DiffIE: Diffusion-based Open Information Extraction — arXiv:2609.02315 — arXiv (en), https://arxiv.org/abs/2609.02315 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_577464f381e2 (Metraipolis archive dc_577464f381e2, sha256 4afdfcb9d9a272deb530dc875e296002830f3f70d4b4ff7e4d9f42eb14ef81ea)

BibTeX

@misc{dc577464f381e2,
  title = {DiffIE: Diffusion-based Open Information Extraction — arXiv:2609.02315},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02315},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_577464f381e2; sha256 4afdfcb9d9a272deb530dc875e296002830f3f70d4b4ff7e4d9f42eb14ef81ea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02315. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A single sentence often expresses multiple valid relational triplets, which makes Open Information Extraction (OpenIE) fundamentally a multi-output task. Existing neural systems handle this by autoregressive generation, which is flexible but slow and prone to redundancy, or by fixed-slot prediction, which is efficient but couples the extraction budget to training. We introduce DIFFIE which instead treats the stochasticity of conditional discrete diffusion as the extraction mechanism itself: independent reverse-diffusion trajectories over per-token role tags produce a pool of candidate triplets, which are clustered under lenient matching and ranked to form the output. Both the pool size and the number of returned extractions are inference-time choices, decoupling the extraction budget from training and exposing test-time compute as a tunable axis. DIFFIE achieves the new state of the art in CaRB (1-1) both F1 and AUC, and outperforms the strongest rule-based system (ClausIE) in BenchIE; it also remains competitive in standard CaRB and WiRe57 evaluations, giving the best average score among systems that report all four benchmarks. Ablations show that uniform discrete diffusion outperforms absorbing state diffusion in our setting, and that a matched non-diffusion stochastic tagger does not reproduce its gains. Our results indicate that diffusion stochasticity is an effective mechanism for structured prediction tasks with multiple valid outputs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.02315 — 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 2026-10-17T03:13:12.533Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).