As Large Language Models (LLMs) increasingly consume their own outputs through retrieval-augmented generation and synthetic data pipelines, self-referential loops are becoming prevalent in modern information ecosystems. While prior work has studied variance collapse during recursive training, the dynamic consequences for political diversity during inference remain underexplored. We investigate this by conducting iterative paraphrasing experiments across eight widely used LLMs, and formalize self-referential generation as a discrete-time Markov process to characterize its long-term behavior. Our results reveal a systematic contraction of political diversity, with several models converging toward center-dominant equilibria. Notably, this homogenization is strongly front-loaded: the majority of diversity loss occurs within the earliest iterative rounds, indicating that even a few AI-mediated transformations can disproportionately narrow the political spectrum. We further examine two interventions: Stance-Conditioned Generation (SCG) substantially reduces marginal stance-distribution drift even without ground-truth labels, leaving no statistically detectable shift for three of the four homogenizing models, whereas Self-Identified Stance Preservation (SISP) overshoots into over-polarization; even SCG improves but does not guarantee instance-level stance retention. These findings highlight a structural risk associated with self-referential generation in AI-driven information pipelines. Our code and prompts are publicly available at https://github.com/timothy-coshin/SelfReferentialPoliticalDiversity.

Sign language is a crucial means of communication for deaf communities. However, those outside deaf communities often lack understanding of sign language, leading to inadequate communication accessibility for the deaf. Therefore, sign language translation is a significantly important research area. In this context, we present a new benchmark dataset for Korean sign language translation named SSL:korean disaster Safety information Sign Language translation benchmark dataset. Korean sign language translation datasets provided by the National Information Society Agency in South Korea have faced challenges related to computational resources, heterogeneity between train and test sets, and unrefined data. To alleviate the aforementioned issue, we refine the origin data and release them. Additionally, we report experimental results of baseline using a transformer architecture. We empirically demonstrate that the baseline performance varies depending on the tokenization method applied to gloss sequences. In particular, tokenization based on characteristics of sign language outperforms tokenization considering characteristics of spoken language and tokenization utilizing statistical techniques. We release materials at our https://github.com/SSL-Sign-Language/Korean-Disaster-Safety-Information-Sign-Language-Translation-Benchmark-Dataset