LLM Analysis of 150+ years of German Parliamentary Debates on Migration Reveals Shift from Post-War Solidarity to Anti-Solidarity in the Last Decade

• URL: http://arxiv.org/abs/2509.07274v1
• Date: Mon, 08 Sep 2025 23:16:03 GMT
• Title: LLM Analysis of 150+ years of German Parliamentary Debates on Migration Reveals Shift from Post-War Solidarity to Anti-Solidarity in the Last Decade
• Authors: Aida Kostikova, Ole Pütz, Steffen Eger, Olga Sabelfeld, Benjamin Paassen,
• Abstract summary: Migration has been a core topic in German political debate.<n>Large language models (LLMs) have the potential to partially automate even complex annotation tasks.<n>We evaluate the influence of model size, prompting differences, fine-tuning, historical versus contemporary data.
• Score: 17.8054316171213
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Migration has been a core topic in German political debate, from millions of expellees post World War II over labor migration to refugee movements in the recent past. Studying political speech regarding such wide-ranging phenomena in depth traditionally required extensive manual annotations, limiting the scope of analysis to small subsets of the data. Large language models (LLMs) have the potential to partially automate even complex annotation tasks. We provide an extensive evaluation of a multiple LLMs in annotating (anti-)solidarity subtypes in German parliamentary debates compared to a large set of thousands of human reference annotations (gathered over a year). We evaluate the influence of model size, prompting differences, fine-tuning, historical versus contemporary data; and we investigate systematic errors. Beyond methodological evaluation, we also interpret the resulting annotations from a social science lense, gaining deeper insight into (anti-)solidarity trends towards migrants in the German post-World War II period and recent past. Our data reveals a high degree of migrant-directed solidarity in the postwar period, as well as a strong trend towards anti-solidarity in the German parliament since 2015, motivating further research. These findings highlight the promise of LLMs for political text analysis and the importance of migration debates in Germany, where demographic decline and labor shortages coexist with rising polarization.

Related papers

• Framing Migration: A Computational Analysis of UK Parliamentary Discourse [5.95326662995992]
  We analyse migration-related discourse in UK parliamentary debates spanning over 75 years.<n>Using open-weight LLMs, we annotate each statement with high-level stances toward migrants.<n>We track the net tone toward migrants across time and political parties.
  arXiv  Detail & Related papers  (2025-09-17T17:31:57Z)
• Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models [52.00270888041742]
  We introduce a novel dataset with neutral event descriptions and contrasting viewpoints from different countries.<n>Our findings show significant geopolitical biases, with models favoring specific national narratives.<n>Simple debiasing prompts had a limited effect on reducing these biases.
  arXiv  Detail & Related papers  (2025-06-07T10:45:17Z)
• Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study [23.458234676060716]
  This study investigates the algorithmic fidelity of large language models (LLMs)<n>We prompt different LLMs to generate synthetic public opinions reflective of German subpopulations by incorporating demographic features into the persona prompts.<n>Our results show that Llama performs better than other LLMs at representing subpopulations, particularly when there is lower opinion diversity within those groups.
  arXiv  Detail & Related papers  (2024-12-17T18:46:32Z)
• Large Language Models Reflect the Ideology of their Creators [71.65505524599888]
  Large language models (LLMs) are trained on vast amounts of data to generate natural language.<n>This paper shows that the ideological stance of an LLM appears to reflect the worldview of its creators.
  arXiv  Detail & Related papers  (2024-10-24T04:02:30Z)
• Language Model Alignment in Multilingual Trolley Problems [138.5684081822807]
  Building on the Moral Machine experiment, we develop a cross-lingual corpus of moral dilemma vignettes in over 100 languages called MultiTP.<n>Our analysis explores the alignment of 19 different LLMs with human judgments, capturing preferences across six moral dimensions.<n>We discover significant variance in alignment across languages, challenging the assumption of uniform moral reasoning in AI systems.
  arXiv  Detail & Related papers  (2024-07-02T14:02:53Z)
• Assessing Political Bias in Large Language Models [0.624709220163167]
  We evaluate the political bias of open-source Large Language Models (LLMs) concerning political issues within the European Union (EU) from a German voter's perspective. We show that larger models, such as Llama3-70B, tend to align more closely with left-leaning political parties, while smaller models often remain neutral.
  arXiv  Detail & Related papers  (2024-05-17T15:30:18Z)
• A Computational Analysis of the Dehumanisation of Migrants from Syria and Ukraine in Slovene News Media [8.35176751141867]
  We adapt a recently proposed approach for English to study attitudes to migration expressed in Slovene newspapers. We examine changes in the discourse on migration between the 2015-16 migration crisis following the war in Syria and the 2022-23 period following the war in Ukraine. We find that while this discourse became more negative and more intense over time, it is less dehumanising when specifically addressing Ukrainian migrants compared to others.
  arXiv  Detail & Related papers  (2024-04-10T14:28:09Z)
• Large Language Models: A Survey [66.39828929831017]
  Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks.<n>LLMs' ability of general-purpose language understanding and generation is acquired by training billions of model's parameters on massive amounts of text data.
  arXiv  Detail & Related papers  (2024-02-09T05:37:09Z)
• Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization [66.4659448305396]
  This study analyzes various LMs with three probing-based experiments to shed light on the reasons behind the In- vs. Cross-Topic generalization gap. We demonstrate, for the first time, that generalization gaps and the robustness of the embedding space vary significantly across LMs.
  arXiv  Detail & Related papers  (2024-02-02T12:59:27Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models [45.85689795740895]
  Many NLP researchers are experiencing an existential crisis triggered by the astonishing success of ChatGPT and other systems based on large language models (LLMs) We look for guidance from the first era of LLMs, which began in 2005 with large $n$-gram models for machine translation (MT) We argue that disparities in scale are transient and researchers can work to reduce them.
  arXiv  Detail & Related papers  (2023-11-08T21:13:38Z)
• Fine-Grained Detection of Solidarity for Women and Migrants in 155 Years of German Parliamentary Debates [16.382860418871804]
  We study solidarity towards women and migrants in German parliamentary debates between 1867 and 2022. Using 2,864 manually annotated text snippets, we evaluate large language models (LLMs) like Llama 3, GPT-3.5, and GPT-4. Using GPT-4, we automatically annotate more than 18k further instances (with a cost of around 500 Euro) across 155 years.
  arXiv  Detail & Related papers  (2022-10-09T22:02:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.