A multi-llm debiasing framework
DM Owens, RA Rossi, S Kim, T Yu… - arxiv preprint arxiv …, 2024 - arxiv.org
Large Language Models (LLMs) are powerful tools with the potential to benefit society
immensely, yet, they have demonstrated biases that perpetuate societal inequalities …
immensely, yet, they have demonstrated biases that perpetuate societal inequalities …
In-context learning may not elicit trustworthy reasoning: A-not-b errors in pretrained language models
Recent advancements in artificial intelligence have led to the creation of highly capable
large language models (LLMs) that can perform tasks in a human-like manner. However …
large language models (LLMs) that can perform tasks in a human-like manner. However …
[HTML][HTML] Construction of Cultural Heritage Knowledge Graph Based on Graph Attention Neural Network
Y Wang, J Liu, W Wang, J Chen, X Yang, L Sang… - Applied Sciences, 2024 - mdpi.com
To address the challenges posed by the vast and complex knowledge information in cultural
heritage design, such as low knowledge retrieval efficiency and limited visualization, this …
heritage design, such as low knowledge retrieval efficiency and limited visualization, this …
Are Large Language Models a Good Replacement of Taxonomies?
Large language models (LLMs) demonstrate an impressive ability to internalize knowledge
and answer natural language questions. Although previous studies validate that LLMs …
and answer natural language questions. Although previous studies validate that LLMs …
From Bias to Fairness: The Role of Domain-Specific Knowledge and Efficient Fine-Tuning
W Zheng, A Yang, N Lin, D Zhou - International Conference on Intelligent …, 2024 - Springer
In the field of Natural Language Processing (NLP), Large Language Models (LLMs)
demonstrate proficiency in complex tasks and are widely used in many real-world …
demonstrate proficiency in complex tasks and are widely used in many real-world …
Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings
Z Liu, T **e, X Zhang - arxiv preprint arxiv:2412.06134, 2024 - arxiv.org
Current social bias benchmarks for Large Language Models (LLMs) primarily rely on pre-
defined question formats like multiple-choice, limiting their ability to reflect the complexity …
defined question formats like multiple-choice, limiting their ability to reflect the complexity …