Unmasking Implicit Bias: Evaluating Persona-Prompted LLM Responses in Power-Disparate Social Scenarios (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence, but they risk perpetuating societal biases, especially when demographic information is involved. |
| Approach: | They propose a framework that measures semantic shifts in responses and an LLM-judged Preference Win Rate to assess how demographic prompts affect response quality across power-disparate social scenarios. |
| Outcome: | The proposed framework measures semantic shifts in responses and an LLM-judged Preference Win Rate (WR) to assess how demographic prompts affect response quality across power-disparate social scenarios. |
Similar Papers
Your Mileage May Vary: How Empathy and Demographics Shape Human Preferences in LLM Responses (2025.findings-emnlp)
Copied to clipboard
| Challenge: | large language models (LLMs) increasingly assist subjective decision-making . prior work uses aggregate human judgments, but demographic variation and its linguistic drivers remain underexplored. |
| Approach: | They analyze how demographic background and empathy level correlate with LLM-generated dilemma responses . they also identify markers that predict group-level differences . |
| Outcome: | The authors show that demographic background and empathy level correlate with LLM preferences . their findings highlight the need for demographically informed LLM evaluations. |
Who Gets Which Message? Auditing Demographic Bias in LLM-Generated Targeted Text (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models generate demographically conditioned persuasive texts at scale . authors argue that such capabilities raise questions about fairness and representational bias in automated communication. |
| Approach: | They propose a framework for evaluating demographic-conditioned targeted messages . they find gender- and age-based asymmetries in male- and youth-targeted messages a . |
| Outcome: | The proposed framework evaluates generated messages across three dimensions: lexical content, language style, and persuasive framing. |
Reading Between the Prompts: How Stereotypes Shape LLM’s Implicit Personalization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has shown that such inferences can lead to lower quality responses for users assumed to be from minority groups. |
| Approach: | They analyze LLMs' latent user representations through both model internals and generated answers to targeted user questions. |
| Outcome: | The proposed models infer demographic attributes based on stereotypical signals, which persists even when the user explicitly identifies with a different demographic group. |
Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that large language models are susceptible to societal biases due to their exposure to human-generated data. |
| Approach: | They propose two strategies to mitigate implicit gender biases in large language models . they create scenarios where implicit gender is present and develop a metric to assess the presence of biase . |
| Outcome: | The proposed methods mitigate implicit biases with self-reflection and fine-tuning. |
Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personas (2024.findings-emnlp)
Copied to clipboard
Salvatore Giorgi, Tingting Liu, Ankit Aich, Kelsey Isman, Garrick Sherman, Zachary Fried, João Sedoc, Lyle Ungar, Brenda Curtis
| Challenge: | Large language models (LLMs) are increasingly being used in human-centered social scientific tasks, such as data annotation, synthetic data creation, and engaging in dialog. |
| Approach: | They propose to prompt LLMs with human-like personas and ask them to answer as if they were a specific human, either explicitly, with exact demographics, political beliefs, and lived experiences, or implicitly via names prevalent in specific populations. |
| Outcome: | The proposed model is based on explicit, explicit, and implicit personas, and fails to show implicit biases. |
Neutral Is Not Unbiased: Evaluating Implicit and Intersectional Identity Bias in LLMs Through Structured Narrative Scenarios (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models often reproduce societal biases, yet most evaluations overlook how such biase evolve across nuanced contexts or intersecting identities. |
| Approach: | They propose a scenario-based evaluation framework built on 100 narrative tasks . they use critical discourse analysis and quantitative linguistic metrics to analyze LLMs . |
| Outcome: | The proposed evaluation framework provides ethically coherent and socially plausible settings for probing model behavior. |
Ask LLMs Directly, “What shapes your bias?”: Measuring Social Bias in Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to evaluate social bias in large language models have limitations . et al., 1995: stereotypes shape social perceptions without objective basis . |
| Approach: | They propose a method to intuitively quantify social perceptions and suggest metrics to evaluate biases within LLMs. |
| Outcome: | The proposed metrics capture the multi-dimensional aspects of social bias, the paper shows . they show that the proposed metrics can be used to evaluate bias in large language models . |
Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to quantify and quantify social biases in Large Language Models (LLMs) focus on explicit bias, with little attention to implicit bias. |
| Approach: | They propose a self-reflection-based evaluation framework that measures implicit bias and evaluates explicit bias by prompting LLMs to analyze their own generated content. |
| Outcome: | The proposed framework compares explicit and implicit biases in large language models . it demonstrates that explicit bias manifests as mild stereotypes, while implicit bias exhibits strong stereotypes. |
Quantifying the Persona Effect in LLM Simulations (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown remarkable promise in simulating human language and behavior. |
| Approach: | They investigate how integrating persona variables—demographic, social, and behavioral factors—impacts LLMs’ ability to simulate diverse perspectives. |
| Outcome: | The proposed model improves on a zero-shot model with persona prompting. |
Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations? (2026.acl-long)
Copied to clipboard
| Challenge: | Power differences shape human communication through well-documented socio-cognitive effects . asymmetric relationships or power differentials give rise to well-known socio-computational effects - lianelli, 1976 . |
| Approach: | They simulate multi-turn, power-asymmetric dialogues with personas from diverse professions . they find that LLMs show key socio-cognitive effects of power, albeit with nuances and variability . |
| Outcome: | The results show that large language models exhibit socio-cognitive effects of power . the results are consistent with previous studies on LLMs . |