# Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes

arXiv: https://arxiv.org/abs/2501.14294 · HTML: https://mlsanity.com/paper/2501.14294/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 31 of its 59 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 30 of 31)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [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)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [The Capacity for Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2302.07459/) (2023)
- [Alignment of Language Agents](https://mlsanity.com/paper/2103.14659/) (2021)
- [Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF](https://mlsanity.com/paper/2312.08358/) (2023)
- [Evaluating and Mitigating Discrimination in Language Model Decisions](https://mlsanity.com/paper/2312.03689/) (2023)
- [Evaluating Cognitive Maps and Planning in Large Language Models with CogEval](https://mlsanity.com/paper/2309.15129/) (2023)
- [Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity](https://mlsanity.com/paper/2209.12106/) (2022)
- [CommunityLM: Probing Partisan Worldviews from Language Models](https://mlsanity.com/paper/2209.07065/) (2022)
- [Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models](https://mlsanity.com/paper/2206.11684/) (2022)
- [Misinfo Reaction Frames: Reasoning about Readers' Reactions to News Headlines](https://mlsanity.com/paper/2104.08790/) (2021)
- [The Trickle-down Impact of Reward (In-)consistency on RLHF](https://mlsanity.com/paper/2309.16155/) (2023)
- [Examining the Causal Effect of First Names on Language Models: The Case of Social Commonsense Reasoning](https://mlsanity.com/paper/2306.01117/) (2023)
- [StereoMap: Quantifying the Awareness of Human-like Stereotypes in Large Language Models](https://mlsanity.com/paper/2310.13673/) (2023)

## Built on by (most cited first, 3 of 3)

- [Continuous Latent Diffusion Language Model](https://mlsanity.com/paper/2605.06548/) (2026)
- [Understanding the Impact of Linguistic Realization Choices on LLM Stance with Causal Tracing](https://mlsanity.com/paper/2607.20115/) (2026)
- [From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations](https://mlsanity.com/paper/2610.16498/) (2026)

## Abstract (arXiv)

Examining the alignment of large language models (LLMs) has become increasingly important, e.g., when LLMs fail to operate as intended. This study examines the alignment of LLMs with human values for the domain of politics. Prior research has shown that LLM-generated outputs can include political leanings and mimic the stances of political parties on various issues. However, the extent and conditions under which LLMs deviate from empirical positions are insufficiently examined. To address this gap, we analyze the factors that contribute to LLMs' deviations from empirical positions on political issues, aiming to quantify these deviations and identify the conditions that cause them. Drawing on findings from cognitive science about representativeness heuristics, i.e., situations where humans lean on representative attributes of a target group in a way that leads to exaggerated beliefs, we scrutinize LLM responses through this heuristics' lens. We conduct experiments to determine how LLMs inflate predictions about political parties, which results in stereotyping. We find that while LLMs can mimic certain political parties' positions, they often exaggerate these positions more than human survey respondents do. Also, LLMs tend to overemphasize representativeness more than humans. This study highlights the susceptibility of LLMs to representativeness heuristics, suggesting a potential vulnerability of LLMs that facilitates political stereotyping. We also test prompt-based mitigation strategies, finding that strategies that can mitigate representative heuristics in humans are also effective in reducing the influence of representativeness on LLM-generated responses.