Metraipolis › archive › dc_e3557548cc7b

Relational Response Fields: A General Theory of Black-Box LLM Response Consistency and Recovery — arXiv:2608.04552

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04552
License (as archived)
CC0-1.0
Archived
2026-10-31T11:24:41.538Z
SHA-256 of the archived text
e0c989b465ee3c745e04cd14dd632c811a0271b6a2f371455d406bfbc3e86eea
Stable URL of this page
https://metraipolis.com/documento/dc_e3557548cc7b

How to cite

Relational Response Fields: A General Theory of Black-Box LLM Response Consistency and Recovery — arXiv:2608.04552 — arXiv (en), https://arxiv.org/abs/2608.04552 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e3557548cc7b (Metraipolis archive dc_e3557548cc7b, sha256 e0c989b465ee3c745e04cd14dd632c811a0271b6a2f371455d406bfbc3e86eea)
BibTeX
@misc{dce3557548cc7b,
  title = {Relational Response Fields: A General Theory of Black-Box LLM Response Consistency and Recovery — arXiv:2608.04552},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04552},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e3557548cc7b; sha256 e0c989b465ee3c745e04cd14dd632c811a0271b6a2f371455d406bfbc3e86eea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04552. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Black-box language-model reliability is commonly pursued by sampling, prompting, voting, verifying, or iteratively revising individual answers. We ask a prior question: \emph{what determines whether a collection of black-box responses is recoverable at all?} We represent responses to typed transformations of a query as a \emph{relational response field} (RRF). Edge transports encode how valid responses must change under paraphrase, scaling, decomposition, refactoring, or other task symmetries; anchors encode independently trusted evidence such as execution or a verifier. For relation operator $D$, anchor operator $A$, and at most $k$ corrupted response nodes, we identify $\gamma_k(D,A)$ as the intrinsic difficulty of black-box response recovery. It is positive exactly when every $k$-node corruption is identifiable; it gives a deterministic stability bound proportional to $1/\gamma_k$; and a matching two-point minimax lower bound shows that no estimator can improve this dependence. Thus consistency is not truth: relation-only methods are blind to null directions, including shared hallucinations. We derive sparse field-repair algorithms while separating information-theoretic identifiability from the stronger null-space conditions required by convex optimization. Controlled theorem tests and black-box mathematics/code experiments evaluate four theory-fixed consequences: consistency--truth separation, anchor phase transitions, redundancy saturation, and cross-model, cross-task prediction of repair difficulty. The results support $\gamma_k(D,A)$ as a measurable property of a response-recovery instance, rather than a score attached to one repair heuristic.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.04552 — 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 2026-10-31T11:13:23.174Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).