Multicalibration enhances LLM accuracy by refining confidence scores and addressing hallucinations.
― 6 min read
Computer Science - Computation and Language
RSSA new method uses machine learning to analyze online reviews effectively.
― 6 min read
A method to improve AI performance while ensuring clear decision-making.
― 6 min read
A new method enhances entity classification in complex documents using spatial data.
― 5 min read
Explore how machine translation improves multilingual classifiers with innovative techniques.
― 8 min read
A benchmark to identify AI models pretending to be safe.
― 5 min read
Phishing email attacks are changing with AI technology, making detection more challenging.
― 7 min read
Strategies to reduce overly cautious behavior in language models.
― 7 min read
New dataset aims to improve translation tools for Creole language speakers.
― 6 min read
Introducing a method that enhances data summarization across multiple tables based on user queries.
― 8 min read
New techniques improve entity matching for diverse data formats.
― 7 min read
This study analyzes the effectiveness of LLMs in evaluating AI-generated explanations.
― 7 min read
This study assesses biases in LLMs impacting healthcare across demographic groups.
― 5 min read
A new approach enhances the accuracy of reasoning graphs from language inputs.
― 6 min read
Assessing the role of LLMs in diagnosing common illnesses through symptom analysis.
― 5 min read
Exploring how language and actions work together in human communication.
― 7 min read
This study presents a method for agents to learn in flexible environments using past knowledge.
― 6 min read
Learn effective methods to quantize LLMs while maintaining accuracy and performance.
― 7 min read
A new framework evaluates how well language models help experts with writing tasks.
― 5 min read
This article examines how fine-tuning affects language models' accuracy and hallucinations.
― 5 min read
Exploring how disagreement in data labeling can provide valuable insights.
― 6 min read
A framework combining human expertise and LLMs to improve qualitative research.
― 7 min read
This method classifies text claims efficiently with minimal data.
― 6 min read
Introducing MemVP to improve efficiency in vision-language models.
― 6 min read
A framework to ensure language models provide accurate information.
― 8 min read
Examining code-mixing and its impact on language acceptability in multilingual settings.
― 6 min read
This framework improves text evaluation efficiency and accuracy using Large Language Models.
― 7 min read
This study explores Federated Learning's role in Document Visual Question Answering.
― 6 min read
This study investigates memory efficiency in large language models through low-rank decomposition.
― 5 min read
ADSumm provides crucial summaries for better disaster response.
― 6 min read
ATSumm enhances tweet summarization during disasters for effective decision-making.
― 7 min read
Examining the impact of gender bias in Hindi language tools.
― 6 min read
A new method categorizes health responses for easier access.
― 4 min read
SaudiBERT enhances analysis of the Saudi dialect in digital communications.
― 6 min read
This study examines LLMs for predicting heart disease risks in healthcare.
― 6 min read
New method improves documentation of AI models and datasets using advanced language models.
― 7 min read
A project tests AI's role in live comedy performances alongside human actors.
― 6 min read
Research shows word meaning affects tone pronunciation in Mandarin Chinese.
― 7 min read
This study assesses GPT-4V's performance on low-level chart tasks.
― 8 min read
Examining how language models shape children's views on culture and identity.
― 5 min read