Probing the Subtle Ideological Manipulation of Large 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_ | 1866909585809342464 |
|---|---|
| author | Paschalides, Demetris Pallis, George Dikaiakos, Marios D. |
| author_facet | Paschalides, Demetris Pallis, George Dikaiakos, Marios D. |
| contents | Large Language Models (LLMs) have transformed natural language processing, but concerns have emerged about their susceptibility to ideological manipulation, particularly in politically sensitive areas. Prior work has focused on binary Left-Right LLM biases, using explicit prompts and fine-tuning on political QA datasets. In this work, we move beyond this binary approach to explore the extent to which LLMs can be influenced across a spectrum of political ideologies, from Progressive-Left to Conservative-Right. We introduce a novel multi-task dataset designed to reflect diverse ideological positions through tasks such as ideological QA, statement ranking, manifesto cloze completion, and Congress bill comprehension. By fine-tuning three LLMs-Phi-2, Mistral, and Llama-3-on this dataset, we evaluate their capacity to adopt and express these nuanced ideologies. Our findings indicate that fine-tuning significantly enhances nuanced ideological alignment, while explicit prompts provide only minor refinements. This highlights the models' susceptibility to subtle ideological manipulation, suggesting a need for more robust safeguards to mitigate these risks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14287 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Probing the Subtle Ideological Manipulation of Large Language Models Paschalides, Demetris Pallis, George Dikaiakos, Marios D. Computation and Language Computers and Society Large Language Models (LLMs) have transformed natural language processing, but concerns have emerged about their susceptibility to ideological manipulation, particularly in politically sensitive areas. Prior work has focused on binary Left-Right LLM biases, using explicit prompts and fine-tuning on political QA datasets. In this work, we move beyond this binary approach to explore the extent to which LLMs can be influenced across a spectrum of political ideologies, from Progressive-Left to Conservative-Right. We introduce a novel multi-task dataset designed to reflect diverse ideological positions through tasks such as ideological QA, statement ranking, manifesto cloze completion, and Congress bill comprehension. By fine-tuning three LLMs-Phi-2, Mistral, and Llama-3-on this dataset, we evaluate their capacity to adopt and express these nuanced ideologies. Our findings indicate that fine-tuning significantly enhances nuanced ideological alignment, while explicit prompts provide only minor refinements. This highlights the models' susceptibility to subtle ideological manipulation, suggesting a need for more robust safeguards to mitigate these risks. |
| title | Probing the Subtle Ideological Manipulation of Large Language Models |
| topic | Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2504.14287 |