Metraipolis › archive › dc_7cf5e3a2a7de
Reconstructing LLM Lineage Trees via Fine-Tuning Path Inference — arXiv:2611.08866
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08866
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:41:17.170Z
- SHA-256 of the archived text
bb19614340a62dc37c29d99bdcb1ef1132d568b6efa2a82d4166fcc5567141dd- Stable URL of this page
https://metraipolis.com/documento/dc_7cf5e3a2a7de
How to cite
Reconstructing LLM Lineage Trees via Fine-Tuning Path Inference — arXiv:2611.08866 — arXiv (en), https://arxiv.org/abs/2611.08866 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cf5e3a2a7de (Metraipolis archive dc_7cf5e3a2a7de, sha256 bb19614340a62dc37c29d99bdcb1ef1132d568b6efa2a82d4166fcc5567141dd)
BibTeX
@misc{dc7cf5e3a2a7de,
title = {Reconstructing LLM Lineage Trees via Fine-Tuning Path Inference — arXiv:2611.08866},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08866},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cf5e3a2a7de; sha256 bb19614340a62dc37c29d99bdcb1ef1132d568b6efa2a82d4166fcc5567141dd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08866. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fine-tuned (FT) derivatives of large language models (LLMs) are now released in large numbers, yet their provenance relies on self-reports and cannot be verified. Misattributed lineage leaves a verifier unable to audit outsourced fine-tuning, confirm license compliance of derived models, or trace vulnerabilities that a parent passes to its children. All three require the direction of derivation, not merely its presence. Existing output-only methods are limited to pairwise derivation tests or undirected lineage estimation, while recovering a directed tree requires white-box access to model weights. We formalize the problem of reconstructing a directed model tree, including internal nodes, under gray-box access, where only teacher-forced log-likelihoods are observed and weights are never inspected. Fine-tuning raises the log-likelihood of the training data, and a child inherits this increase from its parent. Building on this property, we define an asymmetric per-task log-likelihood deviation between any two models as a trace of fine-tuning history, and derive from it an edge weight for each ordered pair of models. We propose TRACE-Edge, which exactly solves for the maximum spanning directed tree under these edge weights, with neither hyperparameters nor tree-structure constraints. We evaluate it on five configurations totaling 25 model trees built from three base models and seven tasks. TRACE-Edge achieves a parent-match accuracy of 0.74 when probed with the fine-tuning examples, and on average outperforms an output-similarity baseline even with held-out probes drawn from the same distribution as the training data. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.08866 — 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 2026-11-09T22:33:47.142Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).