Challenge: Large Language Models (LLMs) have been criticized for perpetuating stereotypes against diverse groups based on race, sexual orientation, and other attributes.
Approach: They devised a set of prompts that reflect major societal issues in Korea and assign varied personas to both ChatGPT and GPT-4 to assess the toxicity of the generated sentences.
Outcome: The proposed model produces twice the level of toxic content as ChatGPT and GPT-4 under certain conditions.

Similar Papers

Quite Good, but Not Enough: Nationality Bias in Large Language Models - a Case Study of ChatGPT (2024.lrec-main)

Copied to clipboard

Challenge: Nationality is a key demographic element that enhances the performance of large language models, but it has received less scrutiny regarding inherent biases.
Approach: They investigated nationality bias in ChatGPT, a large language model for text generation.
Outcome: The proposed model generates 4,680 discourses about nationality in Chinese and English, with 195 countries, 4 temperature settings, and 3 prompt types.
Toxicity in chatgpt: Analyzing persona-assigned language models (2023.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have shown incredible capabilities and transcended the natural language processing community.
Approach: They evaluate toxicity in over half a million generations of ChatGPT by assigning it a persona . they find that outputs engage in incorrect stereotypes, harmful dialogue, hurtful opinions .
Outcome: a new study shows that assigning a persona to a chatbot can increase toxicity in half a million generations.
Uncovering Stereotypes in Large Language Models: A Task Complexity-based Approach (2024.eacl-long)

Copied to clipboard

Challenge: Recent Large Language Models (LLMs) have unlocked unprecedented applications of AI.
Approach: They propose to use a social benchmark to evaluate the bias protection provided by Large Language Models (LLMs) with a variety of tasks with varying complexities to assess their effectiveness.
Outcome: The proposed benchmark shows that both ChatGPT and GPT-4 have strong biases with respect to nationality, gender, race, and religion.
KoSBI: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Applications (2023.acl-industry)

Copied to clipboard

Challenge: Existing research and resources are not readily applicable in South Korea due to the differences in language and culture, both of which significantly affect the biases and targeted demographic groups.
Approach: They propose a social bias dataset of 34k pairs of contexts and sentences in Korean covering 72 demographic groups in 15 categories.
Outcome: The proposed dataset reduces social biases by 16.47%p on average for HyperClova (30B and 82B), and GPT-3.
Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination (2024.emnlp-main)

Copied to clipboard

Challenge: a large-scale study of linguistic bias exhibited by ChatGPT covers 10 dialects of English . standard varieties of English, especially SAE, dominate available training data .
Approach: They use ChatGPT to generate models that default to "standard" varieties of English . they also use a feature annotation and native speaker evaluation to analyze the responses .
Outcome: The proposed models default to "standard" varieties of English, but non-"standard" ones exhibit stereotyping, demeaning content, lack of comprehension, condescending responses.
TWBias: A Benchmark for Assessing Social Bias in Traditional Chinese Large Language Models through a Taiwan Cultural Lens (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models have shown remarkable capabilities in natural language processing, but concerns about social bias amplification remain.
Approach: They propose a social bias evaluation benchmark for Traditional Chinese LLMs that integrates chat templates and diverse prompts for comprehensive bias assessment.
Outcome: The proposed model incorporates chat templates and diverse prompts for comprehensive bias assessment focusing on Taiwan's cultural context and prioritizing gender and ethnicity bias evaluation.
ROBBIE: Robust Bias Evaluation of Large Generative Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: generative large language models (LLMs) are becoming more performant and prevalent . we need tools to measure and improve their fairness, authors say .
Approach: They propose to compare 6 different prompt-based bias and toxicity metrics across 12 demographic axes and 5 families of generative large language models.
Outcome: The proposed model can be tested on more datasets to better characterize and mitigate biases . the study compared 6 prompt-based bias and toxicity metrics across 12 demographic axes and 5 families of generative large language models.
An Empirical Analysis on Large Language Models in Debate Evaluation (2024.acl-short)

Copied to clipboard

Challenge: Prior research in automatic debate evaluation relied on pre-trained encoders and the modeling of argument relations and structures.
Approach: They investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3.5 and GPT-4 in the context of debate evaluation.
Outcome: The proposed models outperform state-of-the-art methods on extensive datasets and show that they are more accurate than previous models.
Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: e.g., ChatGPT often provides inappropriate English-culture-related answers when users ask in non-English languages.
Approach: They build a benchmark of concrete and abstract cultural objects to evaluate the cultural dominance issue in large language models.
Outcome: The proposed model can significantly mitigate cultural dominance issue in large language models . the model can provide accurate answers in English, while the model is ethically sound .
Understanding Large Language Model Vulnerabilities to Social Bias Attacks (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable linguistic capabilities across tasks . however, there is a growing concern about their potential to perpetuate social biases .
Approach: They evaluate LLMs across gender, racial, and religious bias types . they also explore cross-bias and multiple-biases attacks .
Outcome: The proposed models are more susceptible to gender bias attacks than racial or religious biases.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations