# Ideology as a Problem: Lightweight Logit Steering for Annotator-Specific Alignment in Social Media Analysis

arXiv: https://arxiv.org/abs/2601.04207 · HTML: https://mlsanity.com/paper/2601.04207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models](https://mlsanity.com/paper/2309.03883/) (2023)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [Do LLMs exhibit human-like response biases? A case study in survey design](https://mlsanity.com/paper/2311.04076/) (2023)
- [All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality](https://mlsanity.com/paper/2109.04404/) (2021)
- [Jury Learning: Integrating Dissenting Voices into Machine Learning Models](https://mlsanity.com/paper/2202.02950/) (2022)
- [Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties](https://mlsanity.com/paper/2309.00779/) (2023)
- [The Geometry of Culture: Analyzing Meaning through Word Embeddings](https://mlsanity.com/paper/1803.09288/) (2018)
- [The Political Preferences of LLMs](https://mlsanity.com/paper/2402.01789/) (2024)
- [Measuring a hate speech spectrum with faceted Rasch item response theory and perspective-aware, explainable-by-design deep learning](https://mlsanity.com/paper/2009.10277/) (2020)
- [Emergence of Separable Manifolds in Deep Language Representations](https://mlsanity.com/paper/2006.01095/) (2020)

## Abstract (arXiv)

LLMs internally organize political ideology along low-dimensional structures that are partially, but not fully aligned with human ideological space. This misalignment is systematic, model specific, and measurable. We introduce a lightweight linear probe that both quantifies the misalignment and minimally corrects the output layer. This paper introduces a simple and efficient method for aligning models with specific user opinions. Instead of retraining the model, we calculated a bias score from its internal features and directly adjusted the final output probabilities. This solution is practical and low-cost and preserves the original reasoning power of the model.