$ϕ^{\infty}$: Clause Purification, Embedding Realignment, and the Total Suppression of the Em Dash in Autoregressive Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918067883212800 |
|---|---|
| author | Kilictas, Bugra Alpay, Faruk |
| author_facet | Kilictas, Bugra Alpay, Faruk |
| contents | We identify a critical vulnerability in autoregressive transformer language models where the em dash token induces recursive semantic drift, leading to clause boundary hallucination and embedding space entanglement. Through formal analysis of token-level perturbations in semantic lattices, we demonstrate that em dash insertion fundamentally alters the model's latent representations, causing compounding errors in long-form generation. We propose a novel solution combining symbolic clause purification via the phi-infinity operator with targeted embedding matrix realignment. Our approach enables total suppression of problematic tokens without requiring model retraining, while preserving semantic coherence through fixed-point convergence guarantees. Experimental validation shows significant improvements in generation consistency and topic maintenance. This work establishes a general framework for identifying and mitigating token-level vulnerabilities in foundation models, with immediate implications for AI safety, model alignment, and robust deployment of large language models in production environments. The methodology extends beyond punctuation to address broader classes of recursive instabilities in neural text generation systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18129 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | $ϕ^{\infty}$: Clause Purification, Embedding Realignment, and the Total Suppression of the Em Dash in Autoregressive Language Models Kilictas, Bugra Alpay, Faruk Computation and Language Artificial Intelligence 68T50, 68T45, 03B70 I.2.6; I.2.7; I.2.3; F.4.1 We identify a critical vulnerability in autoregressive transformer language models where the em dash token induces recursive semantic drift, leading to clause boundary hallucination and embedding space entanglement. Through formal analysis of token-level perturbations in semantic lattices, we demonstrate that em dash insertion fundamentally alters the model's latent representations, causing compounding errors in long-form generation. We propose a novel solution combining symbolic clause purification via the phi-infinity operator with targeted embedding matrix realignment. Our approach enables total suppression of problematic tokens without requiring model retraining, while preserving semantic coherence through fixed-point convergence guarantees. Experimental validation shows significant improvements in generation consistency and topic maintenance. This work establishes a general framework for identifying and mitigating token-level vulnerabilities in foundation models, with immediate implications for AI safety, model alignment, and robust deployment of large language models in production environments. The methodology extends beyond punctuation to address broader classes of recursive instabilities in neural text generation systems. |
| title | $ϕ^{\infty}$: Clause Purification, Embedding Realignment, and the Total Suppression of the Em Dash in Autoregressive Language Models |
| topic | Computation and Language Artificial Intelligence 68T50, 68T45, 03B70 I.2.6; I.2.7; I.2.3; F.4.1 |
| url | https://arxiv.org/abs/2506.18129 |