arXiv:2608.14629v1 Announce Type: new Abstract: As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and invulnerable to political bias is a critical step towards safer and more trustworthy Artificial Intel

中文全文翻译正在补齐，可先查看下方英文原文。

[Submitted on 24 Jul 2026]

Title:Inference-Time Mitigation of Adversarial Political Bias in Large Language Models

View a PDF of the paper titled Inference-Time Mitigation of Adversarial Political Bias in Large Language Models, by Tejaswi V. Panchagnula and 5 other authors

View PDF HTML (experimental)

Abstract:As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and invulnerable to political bias is a critical step towards safer and more trustworthy Artificial Intelligence (AI). Current model alignment paradigms, such as reinforcement learning from human feedback (RLHF), make LLMs follow overarching safety instructions. However, this instruction tuning can be exploited via adversarial prompt injection and be used to generate unsafe content. In particular, political bias has not been specifically targeted by modern alignment techniques as harmful and biased content. To address this vulnerability of LLMs, we propose mitigation strategies using Chain of Thought (CoT) prompting and Direct Preference Optimization (DPO). Using a public dataset of legislative videos, we generate summaries using LLMs, inject bias via adversarial prompting and evaluate their performance on a four axis scale designed for political summarization. In this paper, we present different methods to shield LLMs against the injection of political bias. Our results demonstrate that the proposed Recursive Self-Correction approach raises model performance from a Political Neutrality Likert scale baseline of 2.14 to 4.56, averaged across all models, demonstrating effective inference-time mitigation of political bias in LLM-generated summaries.

Submission history

From: Tejaswi V Panchagnula [

view email

]

[v1]

Fri, 24 Jul 2026 01:52:10 UTC (2,846 KB)