Fine-tuning Large Language Models on a political topic will significantly manipulate their political stance on various issues and unintentionally affect their stance on unrelated topics. While previous studies have proposed this issue, there is still a lack of understanding regarding the internal representations of these stances and the mechanisms that lead to unintended cross-topic generalization. In this paper, we systematically explore the internal mechanisms underlying this phenomenon from a neuron-level perspective and how to mitigate the cross-topic generalization of political fine-tuning. Firstly, we propose Political Neuron Localization through Activation Contrasting (PNLAC) to identify two distinct types of political neurons: general political neurons, which govern stance across multiple political topics, and topic-specific neurons} that affect the model's political stance on individual topics. We find the existence of these political neuron types across four models and datasets through activation patching experiments. Leveraging these insights, we introduce InhibitFT, an inhibition-based fine-tuning method, effectively mitigating the cross-topic stance generalization. Experimental results demonstrate the robustness of identified neuron types across various models and datasets, and show that InhibitFT significantly reduces the cross-topic stance generalization by 20% on average, while preserving topic-specific performance. Moreover, we demonstrate that selectively inhibiting only 5% of neurons is sufficient to effectively mitigate the cross-topic stance generalization.

While detecting and avoiding bias in LLM-generated text is becoming increasingly important, media bias often remains subtle and subjective, making it particularly difficult to identify and mitigate. In this study, we assess media bias in LLM-generated content and LLMs' ability to detect subtle ideological bias. We conduct this evaluation using two datasets, PoliGen and EconoLex, covering political and economic discourse, respectively. We evaluate eight widely used LLMs by prompting them to generate articles and analyze their ideological preferences via self-assessment. By using self-assessment, the study aims to directly measure the models' biases rather than relying on external interpretations, thereby minimizing subjective judgments about media bias. Our results reveal a consistent preference of Democratic over Republican positions across all models. Conversely, in economic topics, biases vary among Western LLMs, while those developed in China lean more strongly toward socialism.

Generative Artificial Intelligence offers a powerful tool for adversaries who wish to engage in influence operations, such as the Chinese Spamouflage operation and the Russian Internet Research Agency effort that both sought to interfere with recent US election cycles. Therefore, this study seeks to investigate the propensity of current generative AI models for producing harmful disinformation during an election cycle. The probability that different generative AI models produced disinformation when given adversarial prompts was evaluated, in addition the associated harm. This allows for the expected harm for each model to be computed and it was discovered that Copilot and Gemini tied for the overall safest performance by realizing the lowest expected harm, while GPT-4o produced the greatest rates of harmful disinformation, resulting in much higher expected harm scores. The impact of disinformation category was also investigated and Gemini was safest within the political category of disinformation due to mitigation attempts made by developers during the election, while Copilot was safest for topics related to health. Moreover, characteristics of adversarial roles were discovered that led to greater expected harm across all models. Finally, classification models were developed that predicted disinformation production based on the conditions considered in this study, which offers insight into factors important for predicting disinformation production. Based on all of these insights, recommendations are provided that seek to mitigate factors that lead to harmful disinformation being produced by generative AI models. It is hoped that developers will use these insights to improve future models.

We propose to measure political bias in LLMs by analyzing both the content and style of their generated content regarding political issues. Existing benchmarks and measures focus on gender and racial biases. However, political bias exists in LLMs and can lead to polarization and other harms in downstream applications. In order to provide transparency to users, we advocate that there should be fine-grained and explainable measures of political biases generated by LLMs. Our proposed measure looks at different political issues such as reproductive rights and climate change, at both the content (the substance of the generation) and the style (the lexical polarity) of such bias. We measured the political bias in eleven open-sourced LLMs and showed that our proposed framework is easily scalable to other topics and is explainable.

We examine the question of whether we can automatically classify the sentiment of individual tweets in Farsi, to determine their changing sentiments over time toward a number of trending political topics. Examining tweets in Farsi adds challenges such as the lack of a sentiment lexicon and part-of-speech taggers, frequent use of colloquial words, and unique orthography and morphology characteristics. We have collected over 1 million Tweets on political topics in the Farsi language, with an annotated data set of over 3,000 tweets. We find that an SVM classifier with Brown clustering for feature selection yields a median accuracy of 56% and accuracy as high as 70%. We use this classifier to track dynamic sentiment during a key period of Irans negotiations over its nuclear program.