SRFUND offers detailed annotations for better document processing across multiple languages.
― 6 min read
Computer Science - Computation and Language
RSSA new tool to assess language models' continuous improvement through feedback.
― 6 min read
mOSCAR provides a multilingual dataset for improved AI understanding of text and images.
― 6 min read
A new benchmark evaluates how LVLMs rely on language prior.
― 6 min read
This article analyzes the performance of fine-tuned models versus generative AI in text classification tasks.
― 4 min read
An analysis of code-mixing among migrants discussing their experiences online.
― 8 min read
A new dataset and library enhance time series analysis using multimodal data.
― 6 min read
A new method improves Large Language Models' ability to forget sensitive information.
― 4 min read
A new approach enhances analysis of arguments in various texts.
― 6 min read
A new framework assesses language models on emotional intelligence and creativity.
― 7 min read
A new approach enhances translation quality by teaching models to reflect on their outputs.
― 7 min read
Using AI chatbots to boost communication in disaster readiness for multiethnic groups.
― 4 min read
A new benchmark aims to assess MLLMs in video understanding across multiple topics.
― 6 min read
A look into how LLMs tackle programming by example challenges.
― 5 min read
Investigating the synergy between LLMs and KGs in AI applications.
― 5 min read
This study examines how figurative language aids in identifying writing style and authorship.
― 6 min read
This article investigates gender bias in language models used for depression evaluation.
― 5 min read
A new approach for interpreting tables directly from images enhances data analysis.
― 5 min read
Assessing LLMs' role in improving structured representation of scientific papers.
― 7 min read
This study examines how ambiguity in sentences affects search system performance.
― 5 min read
Research highlights methods to enhance language models using human feedback.
― 6 min read
Exploring the role of microservices in knowledge discovery for patent applications.
― 6 min read
New methods enhance language models' performance through better example selection.
― 7 min read
A look at advancements in language models for Indic languages and their challenges.
― 5 min read
Understanding how transformers process information sheds light on memory recall challenges.
― 6 min read
A new framework enhances reasoning in language models through visual sketches.
― 3 min read
This framework improves predictions for language models, especially in low-resource settings.
― 5 min read
A new method improves translating mixed-language speech into English.
― 5 min read
A new method uses natural language explanations to improve entity matching.
― 8 min read
A new engine enhances access to Khmer language documents and improves search results.
― 5 min read
Learn how preference feedback shapes better language model outputs.
― 6 min read
A study on neuron activation across languages and tasks in multilingual models.
― 10 min read
ReadCtrl allows language models to better match text complexity to reader abilities.
― 5 min read
A new data set assesses how LLMs reason with multiple images.
― 5 min read
A new benchmark assesses how well models understand time and events.
― 6 min read
New dataset helps assess AI text accuracy and reliability.
― 6 min read
This study explores new models for improving language translation using paired data.
― 8 min read
New test CoTempQA improves understanding of events in language models.
― 5 min read
A new benchmark for evaluating AI-generated text detection methods.
― 8 min read
Investigating how LLM predictions align with human choices using statistical modeling.
― 9 min read