# Language Models Predict Empathy Gaps Between Social In-groups and Out-groups

arXiv: https://arxiv.org/abs/2503.01030 · HTML: https://mlsanity.com/paper/2503.01030/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 74 references that are in the map.
- First posted on arXiv 2 Mar 2025.

## Builds on (most cited first, 28 of 28)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [On Measuring and Mitigating Biased Inferences of Word Embeddings](https://mlsanity.com/paper/1908.09369/) (2019)
- [Generative Language Models Exhibit Social Identity Biases](https://mlsanity.com/paper/2310.15819/) (2023)
- [Personas as a Way to Model Truthfulness in Language Models](https://mlsanity.com/paper/2310.18168/) (2023)
- [Dimensional Modeling of Emotions in Text with Appraisal Theories: Corpus Creation, Annotation Reliability, and Prediction](https://mlsanity.com/paper/2206.05238/) (2022)
- [Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution](https://mlsanity.com/paper/2403.03121/) (2024)
- [WASSA-2017 Shared Task on Emotion Intensity](https://mlsanity.com/paper/1708.03700/) (2017)
- [Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2310.05280/) (2023)
- [Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models](https://mlsanity.com/paper/2206.11684/) (2022)
- ["You Gotta be a Doctor, Lin": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations](https://mlsanity.com/paper/2406.12232/) (2024)
- [Emotion Intensities in Tweets](https://mlsanity.com/paper/1708.03696/) (2017)
- [Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directions](https://mlsanity.com/paper/2403.01222/) (2024)
- [How Hate Speech Varies by Target Identity: A Computational Analysis](https://mlsanity.com/paper/2210.10839/) (2022)
- [Measuring Emotions in the COVID-19 Real World Worry Dataset](https://mlsanity.com/paper/2004.04225/) (2020)
- [Multilingual large language models leak human stereotypes across language boundaries](https://mlsanity.com/paper/2312.07141/) (2023)
- [Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption](https://mlsanity.com/paper/2409.03843/) (2024)
- [Where are We in Event-centric Emotion Analysis? Bridging Emotion Role Labeling and Appraisal-based Approaches](https://mlsanity.com/paper/2309.02092/) (2023)
- [Toward Understanding Bias Correlations for Mitigation in NLP](https://mlsanity.com/paper/2205.12391/) (2022)
- [How people talk about each other: Modeling Generalized Intergroup Bias and Emotion](https://mlsanity.com/paper/2209.06687/) (2022)
- [Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias](https://mlsanity.com/paper/2305.16409/) (2023)
- [The Muddy Waters of Modeling Empathy in Language: The Practical Impacts of Theoretical Constructs](https://mlsanity.com/paper/2501.14981/) (2025)
- [Out of sight out of mind: Perceived physical distance between the observer and someone in pain shapes observer's neural empathic reactions](https://mlsanity.com/paper/1808.01805/) (2018)
- [Do they mean 'us'? Interpreting Referring Expressions in Intergroup Bias](https://mlsanity.com/paper/2406.17947/) (2024)

## Built on by (most cited first, 6 of 6)

- [Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications](https://mlsanity.com/paper/2505.00049/) (2025)
- [On the Mutual Influence of Gender and Occupation in LLM Representations](https://mlsanity.com/paper/2503.06792/) (2025)
- [Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication](https://mlsanity.com/paper/2505.21451/) (2025)
- ['Rich Dad, Poor Lad': How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?](https://mlsanity.com/paper/2509.16400/) (2025)
- [From Chatbots to Confidants: A Cross-Cultural Study of LLM Adoption for Emotional Support](https://mlsanity.com/paper/2604.25525/) (2026)
- [Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMs](https://mlsanity.com/paper/2609.15654/) (2026)

## Abstract (arXiv)

Studies of human psychology have demonstrated that people are more motivated to extend empathy to in-group members than out-group members (Cikara et al., 2011). In this study, we investigate how this aspect of intergroup relations in humans is replicated by LLMs in an emotion intensity prediction task. In this task, the LLM is given a short description of an experience a person had that caused them to feel a particular emotion; the LLM is then prompted to predict the intensity of the emotion the person experienced on a numerical scale. By manipulating the group identities assigned to the LLM's persona (the "perceiver") and the person in the narrative (the "experiencer"), we measure how predicted emotion intensities differ between in-group and out-group settings. We observe that LLMs assign higher emotion intensity scores to in-group members than out-group members. This pattern holds across all three types of social groupings we tested: race/ethnicity, nationality, and religion. We perform an in-depth analysis on Llama-3.1-8B, the model which exhibited strongest intergroup bias among those tested.