# Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressions

arXiv: https://arxiv.org/abs/2510.08915 · HTML: https://mlsanity.com/paper/2510.08915/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 73 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Demographic Dialectal Variation in Social Media: A Case Study of African-American English](https://mlsanity.com/paper/1608.08868/) (2016)
- [Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models](https://mlsanity.com/paper/2402.16786/) (2024)
- [Large Language Models Understand and Can be Enhanced by Emotional Stimuli](https://mlsanity.com/paper/2307.11760/) (2023)
- [Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty](https://mlsanity.com/paper/2401.06730/) (2024)
- [Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence](https://mlsanity.com/paper/2002.04803/) (2020)
- [Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination](https://mlsanity.com/paper/2406.08818/) (2024)
- [Multilingual Language Models are not Multicultural: A Case Study in Emotion](https://mlsanity.com/paper/2307.01370/) (2023)
- [VALUE: Understanding Dialect Disparity in NLU](https://mlsanity.com/paper/2204.03031/) (2022)
- [Evaluation of African American Language Bias in Natural Language Generation](https://mlsanity.com/paper/2305.14291/) (2023)
- [Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models](https://mlsanity.com/paper/2206.11684/) (2022)
- [Empowering Personalized Learning through a Conversation-based Tutoring System with Student Modeling](https://mlsanity.com/paper/2403.14071/) (2024)
- [A Robust Bias Mitigation Procedure Based on the Stereotype Content Model](https://mlsanity.com/paper/2210.14552/) (2022)
- [ReIFE: Re-evaluating Instruction-Following Evaluation](https://mlsanity.com/paper/2410.07069/) (2024)
- [NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli](https://mlsanity.com/paper/2405.02814/) (2024)
- [Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference](https://mlsanity.com/paper/2501.00560/) (2024)
- [Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems](https://mlsanity.com/paper/2502.14019/) (2025)

## Built on by (most cited first, 2 of 2)

- [Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases](https://mlsanity.com/paper/2608.10503/) (2026)
- [The Hrunting of AI: Where and How to Improve English Dialectal Fairness](https://mlsanity.com/paper/2603.15187/) (2026)

## Abstract (arXiv)

We introduce and study artificial impressions--patterns in LLMs' internal representations of prompts that resemble human impressions and stereotypes based on language. We fit linear probes on generated prompts to predict impressions according to the two-dimensional Stereotype Content Model (SCM). Using these probes, we study the relationship between impressions and downstream model behavior as well as prompt features that may inform such impressions. We find that LLMs inconsistently report impressions when prompted, but also that impressions are more consistently linearly decodable from their hidden representations. Additionally, we show that artificial impressions of prompts are predictive of the quality and use of hedging in model responses. We also investigate how particular content, stylistic, and dialectal features in prompts impact LLM impressions.