This paper connects transformer models with Markov chains to enhance understanding.
― 6 min read
Computer Science - Computation and Language
RSSThis study examines how LLMs can effectively rank various entities based on different features.
― 6 min read
MemeCraft creates engaging memes to promote social causes safely.
― 10 min read
A study on identifying and reducing cognitive bias in large language models.
― 5 min read
A new approach merges LLMs and cognitive systems to enhance kitchen robotic tasks.
― 7 min read
A deep dive into methods for abusive language detection and text style transfer.
― 5 min read
This study examines information extraction capabilities and biases in dense retrievers.
― 6 min read
MATHWELL helps teachers create engaging math problems for K-8 students quickly.
― 6 min read
This article discusses a new framework for assessing hallucinations in LVLMs.
― 6 min read
Exploring how quantum techniques can enhance natural language processing tasks.
― 7 min read
SportQA evaluates language models' understanding of sports through over 70,000 questions.
― 7 min read
New technology improves dysarthria detection and severity classification.
― 5 min read
Research highlights the bias in language model evaluations and proposes methods for improvement.
― 6 min read
Generative search engines face challenges from adversarial questions, impacting accuracy.
― 5 min read
Learn how social orientation affects conversation outcomes and communication quality.
― 5 min read
New methods enhance how agents learn to cooperate and communicate effectively.
― 6 min read
This paper introduces a new method to examine inaccuracies in language models.
― 4 min read
ASEM improves chatbot emotional recognition for better user interactions.
― 6 min read
This article reviews issues with AI watermarking and suggests improvements for security.
― 6 min read
New methods enhance early detection of voice problems using glottal source features.
― 5 min read
Analyzing the effects of reasoning methods on large language models' performance.
― 5 min read
EHRNoteQA tests language models using real clinical notes for better patient care.
― 5 min read
An adaptive agent improves teamwork in Codenames using multiple language models.
― 5 min read
A new method to identify influence campaigns by analyzing document parts.
― 6 min read
A new method improves how AI models express their confidence in answers.
― 6 min read
A new approach to improve knowledge distillation effectiveness using Sinkhorn distance.
― 5 min read
This article discusses explainability and fairness in legal judgment prediction models.
― 6 min read
Explore the data-centric approach to improving AI software systems.
― 8 min read
A system that enhances AI-generated navigation instructions by detecting errors and offering corrections.
― 6 min read
A new method improves text generation speed using large and small language models.
― 6 min read
MobiLlama offers efficient language processing for devices with limited resources.
― 5 min read
Research examines how LLMs connect information to answer complex questions.
― 6 min read
Language agents use graph models to enhance problem-solving abilities and collaboration.
― 4 min read
A study comparing GPT-4 and crowdsourcing in data labeling tasks.
― 6 min read
A look at how AI can help gather citizen values for better policies.
― 9 min read
Combining models improves sentiment analysis accuracy significantly.
― 5 min read
This resource clarifies word meanings through context and relationships in the Italian language.
― 5 min read
New methods reveal how Slovene words evolve in meaning over time.
― 6 min read
Explore how watermarking can protect the integrity of AI-generated content.
― 6 min read
New benchmark assesses LLMs' skills in interacting with multiple agents.
― 12 min read