Metraipolis › archive › dc_8a4939644190

Belief-Trajectory Energy: Measuring the Path to a Prediction — arXiv:2610.05114

Source
arXiv
Original
https://arxiv.org/abs/2610.05114
License (as archived)
CC0-1.0
Archived
2026-10-06T05:28:16.226Z
SHA-256 of the archived text
675438ae05adac8b6bc81355393df84afc5678aaa760cbefa92ef897ba8def76
Stable URL of this page
https://metraipolis.com/documento/dc_8a4939644190

How to cite

Belief-Trajectory Energy: Measuring the Path to a Prediction — arXiv:2610.05114 — arXiv, https://arxiv.org/abs/2610.05114 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a4939644190 (Metraipolis archive dc_8a4939644190, sha256 675438ae05adac8b6bc81355393df84afc5678aaa760cbefa92ef897ba8def76)
BibTeX
@misc{dc8a4939644190,
  title = {Belief-Trajectory Energy: Measuring the Path to a Prediction — arXiv:2610.05114},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05114},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a4939644190; sha256 675438ae05adac8b6bc81355393df84afc5678aaa760cbefa92ef897ba8def76},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05114. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) progressively revise their predictions across Transformer layers, yet we typically observe only the final output, discarding the trajectory through which it is formed. We introduce Belief-Trajectory Energy(BTE), a model-grounded measure that characterizes an input through the layerwise predictive revisions it induces in a model. By mapping intermediate states into a shared predictive space, BTE provides a principled measure of belief change that can be summarized as either a scalar or a structured depth profile. Theoretically, we show that local BTE corresponds to predictive revision under the Fisher-Rao geometry, while the sequence of revisions captures information beyond the initial-to-final belief change. Empirically, scalar BTE provides a model-relative signal of difficulty across diverse reasoning tasks, while richer BTE representations support human-LLM review detection and fine-grained generator attribution, reaching up to $0.998$ macro-AUROC and $95.6\%$ eight-way attribution accuracy. Further analysis shows that BTE develops throughout pretraining and is selectively reshaped by targeted training, demonstrating that the resulting measurement reflects what the scoring model has learned. Together, our results establish belief trajectories as a principled model-grounded signal and suggest a broader perspective in which learned models can themselves serve as instruments for characterizing the data they process. More demonstrations can be found at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.05114 — 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 2026-10-06T05:24:20.310Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).