analiza aiqbench
This paper proposes a theoretical framework suggesting that language models require a second parameter, "phase," to account for relational dynamics like irony and allusion beyond standard amplitude-based associations. The authors argue that current transformer architectures lack explicit representations for these history-indexed states, potentially limiting their ability to model complex semantic interactions without relying on quantum formalism as the underlying mechanism. Six specific predictions are outlined to test whether suppressed meanings remain active in models influenced by encounter order or individual signaling rather than just population averages.
Language Has Two Parameters: Narrative-Induced Semantic Plasticity and Phase-Sensitive Interpretation
arXiv:2608.18041v1 Announce Type: new Abstract: Language has two parameters. Count how often words occur together and you estimate amplitude, the strength of association. Word embeddings and attention weights refine that count, which sums every writer in the corpus together. This paper claims a second parameter, phase, which signed weights learned from a corpus do not supply. Phase exists only between meanings: it determines how coactivated meanings combine, and it can reverse what a meaning contributes while that meaning stays fully present. A speaker can set phase in the signal through linguistic form; encounters install phase relations and history distributes them. Population averaging deletes history-indexed phase: agent-deindexed corpora identify the population marginal state and determine no individual or dyadic state, at any scale. The standard transformer has no explicit representation for phase in frozen inference, and the interpretability program measuring progress by monosemanticity is optimizing against it: the coexistence it treats as a defect is the condition of allusion, irony, and quotation. Six predictions test whether a suppressed meaning stays active, whether encounter order changes what a phrase does, whether marking the signal changes how a shared phrase is taken, and whether a model given a history is changed by it or only informed about it. The claim defended is the weak version: interpretation requires a second relational parameter, signed, persistent, and indexed to individuals and dyads. Quantum probability is one notation for the parameter; nothing in the formalism claims quantum processes in the brain. The strong version, that the quantum calculus constrains these phenomena as signed classical models do not, rests on an encounter-order constraint not yet derived. The architecture the theory calls for is a language model with agent-indexed, phase-bearing semantic states.
Abstract:Language has two parameters. Count how often words occur together and you estimate amplitude, the strength of association. Word embeddings and attention weights refine that count, which sums every writer in the corpus together. This paper claims a second parameter, phase, which signed weights learned from a corpus do not supply. Phase exists only between meanings: it determines how coactivated meanings combine, and it can reverse what a meaning contributes while that meaning stays fully present. A speaker can set phase in the signal through linguistic form; encounters install phase relations and history distributes them. Population averaging deletes history-indexed phase: agent-deindexed corpora identify the population marginal state and determine no individual or dyadic state, at any scale. The standard transformer has no explicit representation for phase in frozen inference, and the interpretability program measuring progress by monosemanticity is optimizing against it: the coexistence it treats as a defect is the condition of allusion, irony, and quotation. Six predictions test whether a suppressed meaning stays active, whether encounter order changes what a phrase does, whether marking the signal changes how a shared phrase is taken, and whether a model given a history is changed by it or only informed about it. The claim defended is the weak version: interpretation requires a second relational parameter, signed, persistent, and indexed to individuals and dyads. Quantum probability is one notation for the parameter; nothing in the formalism claims quantum processes in the brain. The strong version, that the quantum calculus constrains these phenomena as signed classical models do not, rests on an encounter-order constraint not yet derived. The architecture the theory calls for is a language model with agent-indexed, phase-bearing semantic states.
Computation and Language (cs.CL)
arXiv:2608.18041 [cs.CL]
(or arXiv:2608.18041v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.18041 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 373 cuvinte
Subiecte conexe
LoRA for Gender-Inclusive Rewriting and Activation Steering for Counter-Narrative Generation
arXiv · 28 iul. 2026
Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance
arXiv · 16 iun. 2026
PlotTwist: A Creative Plot Generation Framework with Small Language Models
arXiv · 23 iul. 2026
Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation
arXiv · 9 iun. 2026