JobFair framework identifies gender bias in automated resume evaluations.
― 6 min read
Computer Science - Artificial Intelligence
RSSA fresh method for testing language model safety and multilingual skills.
― 7 min read
A new method enhances exploration efficiency in reinforcement learning.
― 6 min read
Study reveals biases in AI hiring recommendations based on candidate names.
― 6 min read
Introducing model evolution for improved language model performance without extra training data.
― 6 min read
This study assesses how well language models understand social situations using a game.
― 6 min read
A study on improving LLMs' problem-solving abilities using a new framework.
― 7 min read
This article analyzes how language models understand and infer causal relationships.
― 6 min read
Methods for identifying important features in low-quality data environments.
― 6 min read
Learn why unique IDs for AI systems enhance safety and trust.
― 7 min read
A new method combines human and AI for efficient text classification.
― 14 min read
A new framework enhances 3D scene representation using limited 2D images.
― 5 min read
User traits influence the responses of language models and their safety.
― 6 min read
A study highlights discrepancies in AI access among ethnic groups.
― 5 min read
New strategy for conformance checking using fuzzy logs improves process analysis.
― 5 min read
A new benchmark for evaluating dynamic text-attributed graphs in various fields.
― 7 min read
This article discusses soft prompting as a method for machine unlearning in LLMs.
― 7 min read
Leveraging language models improves predictions for tabular data across various fields.
― 6 min read
New method enhances conversational effectiveness in language models through planning techniques.
― 7 min read
A new method enhances testing for language models using real user data.
― 5 min read
Examining the limitations of large language models in understanding code relationships.
― 7 min read
RepoExec evaluates code generation performance at the repository level.
― 6 min read
A framework improves code generation for specialized languages using documentation.
― 7 min read
Job-SDF offers insights into evolving skill demands in today's job market.
― 9 min read
A new approach enhances decision-making in uncertain maritime environments.
― 6 min read
A new dataset improves multi-document reasoning for eligibility questions.
― 8 min read
A new approach to improve safety assessments of AI systems using diverse perspectives.
― 5 min read
SCEPTR offers a new way to predict TCR specificity using sparse data efficiently.
― 8 min read
This article examines generative models that can outperform human experts in chess.
― 7 min read
A new framework helps language models learn symbolic language without human input.
― 7 min read
The Nemotron-4 340B family delivers powerful models for diverse applications and synthetic data generation.
― 7 min read
A toolkit for assessing performance of retrieval-augmented models in specific domains.
― 9 min read
Examining how cultural bias affects AI image understanding.
― 8 min read
New methods reveal challenges in unlearning knowledge from language models.
― 6 min read
A look at intersymbolic AI combining symbolic and subsymbolic methods for smarter systems.
― 6 min read
Language agents are becoming more adaptable, improving their communication and problem-solving skills.
― 4 min read
Researchers develop GECO dataset and GECOBench to tackle gender bias in AI.
― 6 min read
New method enhances retrieval-augmented generation for complex question answering.
― 6 min read
A new dual-transformer model enhances execution time predictions from source code analysis.
― 6 min read
Explores the challenges of supervising advanced AI models with weaker counterparts.
― 6 min read