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. |
Similar Papers
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. |
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. |
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. |
Detecting Subtle Biases: An Ethical Lens on Underexplored Areas in AI Language Models Biases (2026.eacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly embedded in the daily lives of individuals across diverse social classes. |
| Approach: | They propose to analyze LLMs' responses to 1,016 scenarios categorized into ethical, unethical, and neutral types. |
| Outcome: | The proposed model analyzed 1,016 scenarios categorized into ethical, unethical, and neutral types. |
Uncovering Implicit Gender Bias in Narratives through Commonsense Inference (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models learn harmful biases from their training corpora and may repeat these biase if used for generation. |
| Approach: | They focus on gender biases associated with the protagonist in model-generated stories and use a commonsense reasoning engine to uncover them. |
| Outcome: | The proposed model-generated stories are based on a commonsense reasoning engine and are able to uncover gender biases in the protagonist's motivations, attributes, mental states, and implications on others. |
Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflicts (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models acquire beliefs about gender from training data and can therefore generate text with stereotypical gender attitudes. |
| Approach: | They use a decision-making lens to examine gender equity within large language models . they explore relationships through typical and gender-neutral names . |
| Outcome: | The proposed model generation and classification models exhibit stereotypical gender biases . the proposed model generates gender-neutral names, with and without safety enhancements, and egalitarian versus traditional scenarios across topics. |
Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models often exhibit gender bias, resulting in unequal treatment of male and female subjects across contexts. |
| Approach: | They propose a framework that encourages exploratory thinking in large language models . the framework generates story pairs featuring male and female protagonists in structurally identical scenarios . |
| Outcome: | The proposed framework reduces gender bias while preserving or even enhancing general model capabilities. |
How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making? (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that LLMs exhibit social biases inherited from training data. |
| Approach: | They propose a framework for evaluation and mitigation of bias in Large Language Models applied to complex clinical cases using a dataset based on the JAMA Clinical Challenge. |
| Outcome: | The proposed framework employs multiple choice questions and explanations to evaluate gender and ethnicity biases in LLMs. |
Evaluating Gender Bias of LLMs in Making Morality Judgements (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in a multitude of NLP tasks, but are still not immune to limitations such as gender bias. |
| Approach: | They propose to use a dataset to examine whether LLMs possess gender bias when asked to give moral opinions. |
| Outcome: | The proposed models show that they are biased when asked to give moral opinions. |
Intersectional Stereotypes in Large Language Models: Dataset and Analysis (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on intersectional stereotypes focus on broader, individual categories . current studies focus on single-group stereotypes, such as racial bias against African Americans . |
| Approach: | They propose to use a dataset of intersectional stereotypes curated with the ChatGPT model to analyze propagation in three contemporary LLMs. |
| Outcome: | The proposed dataset enables analysis of stereotype propagation in three contemporary LLMs. |