As users increasingly turn to Large Language Models (LLMs) for information and advice on political matters, particularly during election periods, the political preferences expressed by these systems have become a matter of public interest. Prior research has shown that interactions with LLMs can influence users' political attitudes and choices, raising questions about how these models themselves evaluate political actors.
Filled pauses (FPs) are a universal feature of spontaneous speech, yet most studies rely on small, single-language corpora, limiting the generalisability of their findings. We analyse ~4,000 hours of parliamentary speech across four related Slavic languages (Croatian, Czech, Polish, Serbian).
arXiv:2608. 15871v1 Announce Type: cross Abstract: Large language models (LLMs) trained on large-scale internet corpora encode extensive statistical regularities about social identities, attitudes, and political behaviour.
By Roman Neruda, Martin Bako\v{s}, Josef \v{S}lerka, V\'it Tu\v{c}ek, Petra Vidnerov\'a, Gabriela Kadlecov\'a
arXiv:2609.15207v1 Announce Type: new
Abstract: Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before ele...
By Bastiaan Bruinsma, Annika Fred\'en, Paul R\"ottger, Moa Johansson, Asad Sayeed
arXiv:2608. 13410v1 Announce Type: new Abstract: Parliamentary proceedings are a primary record of democratic deliberation, yet their volume and fragmentation make multi-perspective access difficult for citizens, journalists, and researchers.
By Mirko Tritella, Riccardo Pozzi, Matteo Palmonari
arXiv:2606. 28335v1 Announce Type: cross Abstract: We argue, with systematic empirical evidence, that a large language model's political ideology is not a fixed point, but a conditional distribution $\mathbb{P}($position$\mid$context$)$ over a real political space.
By Adib Sakhawat, Syed Rifat Raiyan, Tahsin Islam, Takia Farhin, Hasan Mahmud, Md Kamrul Hasan
The paper investigates how large language models (LLMs) can be distributionally aligned with human output distributions, particularly for applications like survey simulation. It examines both the alignment process and the models’ ability to generalize to unseen questions within the same domain and to related but different topics. The study finds that while LLMs can achieve alignment and generalize within a domain, cross‑topic generalization is variable and aligned models may unexpectedly lose creative capabilities, indicating unpredictable and unstable generalization properties.
By Nelson Jo
Effective democratic deliberation is vital for civic engagement and the health of legislative institutions. However, assessing parliamentary discourse quality is traditionally done using expert-scored...
Large language models (LLMs) are increasingly used for election information, yet little is known about how external web content shapes the political information they present. Generative engine optimiz...
The study analyzes oral political language in U.S. presidential debates from 1960 to 2024, focusing on 19 candidates. It finds a clear trend toward simplification: sentence length and complex terms have decreased, while emotional tone has risen and logical, rational content has diminished. The research also explores whether specific presidents exhibit unique stylistic traits and whether language patterns correlate with electoral success.
By Jacques Savoy
arXiv:2607. 21842v1 Announce Type: cross Abstract: Research on political polarization on social media depends on the ability to reliably measure partisanship in user-generated content.
By Fathima Ameen, Christopher G. Healey
PolERo presents a new dataset of 3,574 Romanian question‑answer pairs from presidential transcripts, annotated for political evasion using a two‑level taxonomy of response clarity and fine‑grained evasion strategies. The study evaluates various classification methods—including TF‑IDF baselines, fine‑tuned encoders, a sliding‑window encoder, and zero/few‑shot LLM prompting—under matched conditions. Cross‑lingual transfer experiments via joint bilingual training and machine‑translation augmentation reveal that fine‑tuned encoders perform competitively, transfer is asymmetric, and ambivalent evasion categories with pragmatic cues remain the most challenging across all models.
By Gabriel Stefan, Sergiu Nisioi