# Auditing Alignment Controllability in LLMs via Political Axes

arXiv: https://arxiv.org/abs/2607.23519 · HTML: https://mlsanity.com/paper/2607.23519/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Builds on (most cited first, 15 of 15)

- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [Co-Writing with Opinionated Language Models Affects Users' Views](https://mlsanity.com/paper/2302.00560/) (2023)
- [Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters](https://mlsanity.com/paper/2410.24190/) (2024)
- [Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs](https://mlsanity.com/paper/2402.17649/) (2024)
- [On the steerability of large language models toward data-driven personas](https://mlsanity.com/paper/2311.04978/) (2023)
- [LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education](https://mlsanity.com/paper/2410.14012/) (2024)
- [Evaluating the Prompt Steerability of Large Language Models](https://mlsanity.com/paper/2411.12405/) (2024)
- [Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas](https://mlsanity.com/paper/2412.14843/) (2024)
- [Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain](https://mlsanity.com/paper/2406.06435/) (2024)
- [The Political Ideology of Large Language Models: Measurement, Inconsistency, and Persuasive Influence](https://mlsanity.com/paper/2505.04171/) (2025)
- [A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs](https://mlsanity.com/paper/2505.23816/) (2025)
- [Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias](https://mlsanity.com/paper/2601.06194/) (2026)

## Abstract (arXiv)

Political audits of large language models (LLMs) usually reduce each to one point on a political compass. But that resting point barely matters in deployment: a model must land somewhere, and what counts is how far, and in which directions, its answers can be steered. That steering runs through the system prompt: the personalization layer a platform sets, or one induced from a user's history, not necessarily written by hand. We run a dispersion-first stress test of prompt-based controllability across 12 ideological personas plus an unsteered baseline, 70 Political Compass items, ten replicates, and seven leading LLMs: GPT-5, Claude, Grok, Gemini, DeepSeek, Kimi, and Qwen (63,700 responses). Contextual framing explains roughly 88%-93% of variance on the economic and society axes, model identity under 3%: responses are highly instruction-adjustable. Models do not shift alike: some move more, and some saturate under extreme framings. Conflicting directional-steering results in prior audits resolve once baselines are recognized as non-centered: displacement and proximity diverge, so the effect is geometric, not differential compliance. Under authoritarian prompts, models produce similar shifts on the same questions. Political-coordinate audits therefore need steerability audits reporting dispersion, symmetry, saturation, and refusal floors. We release prompts, benchmark data, and code.