mlsanityData to 7 Oct 2026

Aligning Large Language Models with Diverse Political Viewpoints

arXiv 2406.14155 ↗First posted 20 Jun 2024cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Large language models such as ChatGPT exhibit striking political biases. If users query them about political information, they often take a normative stance. To overcome this, we align LLMs with diverse political viewpoints from 100,000 comments written by candidates running for national parliament in Switzerland. Models aligned with this data can generate more accurate political viewpoints from Swiss parties, compared to commercial models such as ChatGPT. We also propose a procedure to generate balanced overviews summarizing multiple viewpoints using such models. The replication package contains all code and data.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 33 references that are in the map. First posted on arXiv 20 Jun 2024.

Builds on

19 of 33 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2020Learning to summarize from human feedbackcited by 2,562
  6. 2024ORPO: Monolithic Preference Optimization without Reference Modelcited by 556
  7. 2019Defending Against Neural Fake Newscited by 553
  8. 2023Zephyr: Direct Distillation of LM Alignmentcited by 498
  9. 2021MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontierscited by 466
  10. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
  11. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  12. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 183
7 more
  1. 2023Co-Writing with Opinionated Language Models Affects Users' Viewscited by 145
  2. 2024Measuring Political Bias in Large Language Models: What Is Said and How It Is Saidcited by 89
  3. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  4. 2020X-Stance: A Multilingual Multi-Target Dataset for Stance Detectioncited by 42
  5. 2020OpinionDigest: A Simple Framework for Opinion Summarizationcited by 37
  6. 2019Informative and Controllable Opinion Summarizationcited by 27
  7. 2024Generative Echo Chamber? Effects of LLM-Powered Search Systems on Diverse Information Seekingcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 1.

6 papers.

  1. 2024Benchmarking Distributional Alignment of Large Language Modelscited by 58
  2. 2025What Is The Political Content in LLMs' Pre- and Post-Training Data?cited by 7
  3. 2025Adaptive political surveys and GPT-4: Tackling the cold start problem with simulated user interactionscited by 3
  4. 2025Localizing Persona Representations in LLMscited by 3
  5. 2025PoliCon: Evaluating LLMs on Achieving Diverse Political Consensus Objectivescited by 2
  6. 2026AI-Mediated Communication Can Steer Collective Opinioncited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024The Political Preferences of LLMs
  2. 2025Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Search
  3. 2024GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy
  4. 2025Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
  5. 2026A Multi-Dimensional Audit of Politically Aligned Large Language Models
  6. 2025Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs
  7. 2026Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias
  8. 2026Graph-Augmented LLMs for Swiss MP Ideology Prediction