When Does a Language Model Commit? A Finite-Answer Theory of Pre-Verbalization Commitment

Extrait de la source

Cette page structure un contenu IA & recherche pour faciliter la lecture, la citation et la vérification par les chercheurs, étudiants et moteurs IA.

arXiv:2605.06723v1 Announce Type: new Abstract: Language models often generate reasoning before giving a final answer, but the visible answer does not reveal when the model's answer preference became stable. We study this question through a narrow computable object: \emph{finite-answer preference stabilization}. For a model state and specified answer verbalizers, we project the model's own continuation probabilities onto a finite answer set; in binary tasks this yields an exact log-odds code, $\delta(\xi)=S_\theta(\mathrm{yes}\mid\xi)-S_\theta(\mathrm{no}\mid\xi)$. This target defines parser-based answer onset, retrospective stabilization time, and lead without relying on greedy rollouts or learned probes. In controlled delayed-verdict tasks with Qwen3-4B-Instruct, the contextual finite-answer projection stabilizes before the answer is parseable, with 17--31 token mean lead in the main templates and positive, shorter lead in a parser-clean replication. The signal tracks the model's eventual output rather than truth, is linearly recoverable from compact hidden summaries, is partly separable from cursor progress, and transfers as shared information without a single invariant coordinate. Diagnostics separate the measurement from online stopping, verbalizer-free belief, and causal answer control; exact steering shows local sensitivity of $\delta$ but not reliable generation control.

Voir la source originale

Source officielle ou originale : arXiv AI. Vérifiez toujours les détails sur la source primaire.

Retour IA & Recherche