Metraipolis › archive › dc_d1ea5fb325bc

Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers — arXiv:2608.06111

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06111
License (as archived)
CC0-1.0
Archived
2026-10-25T21:27:21.220Z
SHA-256 of the archived text
30daad05e6f86b825758198d5d8aaf744dbbec7d7a5156ddc19abb002ec9070a
Stable URL of this page
https://metraipolis.com/documento/dc_d1ea5fb325bc

How to cite

Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers — arXiv:2608.06111 — arXiv (en), https://arxiv.org/abs/2608.06111 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d1ea5fb325bc (Metraipolis archive dc_d1ea5fb325bc, sha256 30daad05e6f86b825758198d5d8aaf744dbbec7d7a5156ddc19abb002ec9070a)
BibTeX
@misc{dcd1ea5fb325bc,
  title = {Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers — arXiv:2608.06111},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06111},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d1ea5fb325bc; sha256 30daad05e6f86b825758198d5d8aaf744dbbec7d7a5156ddc19abb002ec9070a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06111. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Positional embeddings (PE) in Transformers encode token distance and order but are largely agnostic to \textit{syntactic structure}. We introduce \textbf{S}yntax-\textbf{i}nformed \textbf{P}ositional \textbf{E}mbeddings (\textbf{SiPE}), which learns a lightweight syntactic prior from dependency parses during pretraining and injects it across all three dominant PE families (absolute, relative, rotary), for both encoders and decoders, leaving self-attention and the rest of the architecture untouched. We isolate \emph{where} and \emph{how} the prior should enter the model, and find it depends on the architecture: for autoregressive decoders that use relative PE, the prior is strongest when coupled multiplicatively with the relative-position term of the attention score, outperforming injection into the input embeddings, into self-attention, or into the positional and attention terms jointly---while for encoders it is best added directly to the input embeddings, composing with each encoder's native positional mechanism. We find that models pre-trained with SiPE improve on the SyntaxGym benchmark by up to $10.3\%$ while simultaneously reducing perplexity by $9.0\%$ over a base model with no syntactic supervision---a metric nearly every existing syntax-injection method instead degrades. Crucially, these gains extend beyond syntactic generalization: SiPE also improves real-world language understanding, raising scores on the GLUE benchmark by up to $8.2\%$ over a model trained without it. Unlike existing syntactic language models that marginalize over many parses at inference or discard syntax at runtime, SiPE conditions on a single parse, establishing a new Pareto frontier between syntactic supervision and inference cost.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.06111 — 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 2026-10-25T21:24:38.224Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).