Metraipolis › archive › dc_3d6fb88dcdc5
TEFM: Token-Efficient Faithful Modeling for Structured Data — arXiv:2609.09552
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09552
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:51:08.885Z
- SHA-256 of the archived text
5e1887850c6c749541e47c10312d9e39b6f5d8efef98670cf697232adc8ff588- Stable URL of this page
https://metraipolis.com/documento/dc_3d6fb88dcdc5
How to cite
TEFM: Token-Efficient Faithful Modeling for Structured Data — arXiv:2609.09552 — arXiv (en), https://arxiv.org/abs/2609.09552 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d6fb88dcdc5 (Metraipolis archive dc_3d6fb88dcdc5, sha256 5e1887850c6c749541e47c10312d9e39b6f5d8efef98670cf697232adc8ff588)
BibTeX
@misc{dc3d6fb88dcdc5,
title = {TEFM: Token-Efficient Faithful Modeling for Structured Data — arXiv:2609.09552},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09552},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d6fb88dcdc5; sha256 5e1887850c6c749541e47c10312d9e39b6f5d8efef98670cf697232adc8ff588},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09552. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this paper, we solve two fundamental obstacles in applying LLMs to critical domains: token efficiency and faithfulness. To address both constraints jointly, we present TEFM (Token-Efficient Faithful Modeling), a framework designed for structured data analysis in critical domains. TEFM achieves token efficiency by compressing lengthy structured observations into compact Behavioral Code tokens, dramatically reducing token consumption with minimal information loss. Moreover, TEFM enables faithful rationalization through a dual-fidelity objective that jointly optimizes code-level reconstruction and prediction-level fidelity, identifying minimal sufficient feature subsets grounded in input data. Comprehensive experiments across various domain datasets and model backbones (Qwen3, Gemma-2, Phi-4) show that TEFM achieves competitive classification accuracy with dramatic token reduction (approximately 1\% token retention in clinical and 2\% in security domains) while producing faithful rationales. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.09552 — 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 2026-10-16T07:24:00.876Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).