Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models

Jiayi Zhang, Shu Yang, Junchao Wu, Derek F. Wong, Di WangarXiv 2025 · DOI · arXiv

Introduction

Large Language Models (LLMs) are increasingly being fine-tuned to align with specific human values or ideological stances. However, this process often leads to an unintended phenomenon known as "cross-topic coupling." For instance, fine-tuning a model on a dataset regarding racial identity can inadvertently shift its stance on unrelated economic or social issues. This leakage makes precise behavioral control difficult and suggests that political ideologies may be represented in a generalized manner within the model's architecture. This paper investigates the internal mechanics of this coupling, identifies the specific neurons responsible, and proposes a novel mitigation strategy called InhibitFT.

Methodology: Identifying and Controlling Political Neurons

To address cross-topic generalization, the authors developed a two-stage framework to locate and then isolate political representations within LLMs.

Political Neuron Localization through Activation Contrasting (PNLAC)

The first stage involves identifying neurons that exhibit significant activation differences when processing politically charged prompts. By creating polarized versions of a base model (e.g., left-leaning vs. right-leaning) through targeted fine-tuning, researchers can calculate a Political Activation Shift (PAS) metric. This metric distinguishes between two categories of neurons:

  1. General Political Neurons: These neurons govern political stance across a wide array of topics and are the primary drivers of cross-topic coupling.
  2. Topic-Specific Neurons: These neurons are activated only by specific issues (e.g., crime or immigration) and do not influence the model's broader ideological worldview.

Verification and InhibitFT

To confirm the causal role of these neurons, the authors utilized Activation Patching, where activations from a biased model are injected into a neutral vanilla model. If the vanilla model adopts the biased stance, the neurons are confirmed as causal agents.

Building on these findings, the authors introduced InhibitFT (Inhibition-based Fine-Tuning). This method applies a gradient mask during the fine-tuning process to freeze the identified general political neurons. By preventing these neurons from updating, the model can learn topic-specific nuances without triggering a global ideological shift.

The PNLAC framework for locating political neurons and the InhibitFT method for mitigating cross-topic coupling.

Experimental Results and Insights

Localization and Sparsity

The study reveals that political stance is highly localized rather than distributed uniformly across the network. Approximately 4.35% of neurons were identified as general political neurons. These are predominantly located in the Feed-Forward Network (FFN) layers, specifically within the middle and later stages of the model (layers 20-30 in 32-layer models). This sparsity suggests that ideological bias can be managed by manipulating a very small fraction of the model's parameters.

Mitigation of Cross-Topic Coupling

InhibitFT demonstrated significant success in decoupling political topics. On average, the method reduced unintended cross-topic stance generalization by 20% across various model families, including Llama-3 and Qwen-2.5. As shown in the heatmaps below, general political neurons exhibit high correlation across different prompt topics, whereas topic-specific neurons remain largely isolated to their intended domain.

Heatmaps comparing the cross-topic influence of general political neurons versus topic-specific neurons, demonstrating the decoupling effect.

Preservation of Model Utility

A critical concern with freezing neurons is the potential loss of general reasoning capabilities. However, evaluations on utility benchmarks like CoLA (linguistic acceptability) and MNLI (natural language inference) showed that InhibitFT maintains, and occasionally improves, general performance. This indicates that the neurons responsible for ideological stance are distinct from those governing core linguistic and logical reasoning.

Conclusion and Future Work

This research provides a mechanistic understanding of how LLMs represent political ideologies. By identifying a small subset of general political neurons, the authors have shown that cross-topic coupling is a localized phenomenon that can be mitigated through targeted inhibition. While the study focused on six major political topics, future work may expand this to niche issues and other forms of non-political bias. Understanding how these neurons emerge during pre-training remains a vital open question for the field of AI alignment.

Summary updated

Abstract

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.
BibTeX
@misc{zhang2025understanding,
  author = {Jiayi Zhang and Shu Yang and Junchao Wu and Derek F. Wong and Di Wang},
  title = {{Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models}},
  year = {2025},
  eprint = {2508.02360},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.02360},
}
Figure