Large Language Model
GraphVis: Boosting LLMs with Visual Knowledge Graph Integration Yihe Deng Chenchen Y e Zijie Huang Mingyu Derek Ma Yiwen Kou Wei Wang University of California, Los Angeles
The rapid evolution of large language models (LLMs) has expanded their capabilities across various data modalities, extending from well-established image data to increasingly popular graph data.
UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis
Models (LLMs) in collaborating with external data, yet significant challenges exist in real-world scenarios. In areas such as academic literature and finance question answering, data are often found in raw text and tables in HTML or PDF formats, which can be lengthy and highly unstructured.
Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
Recent work utilizes plan-and-solve decomposition to decrease the complexity and leverage self-tests to refine the generated program.
Evaluate Large Language Model as Critic
Critique ability, i.e., the capability of Large Language Models (LLMs) to identify
Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks
Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge. However, deployment of the LLMs in real-world applications can be challenging due to their high computational requirements and concerns on data privacy.
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers Siyu Chen Department of Statistics and Data Science, Yale University
In particular, most existing work only theoretically explains how the attention mechanism facilitates ICL under certain data models.
DropCompute: simple and more robust distributed synchronous training via compute variance reduction
Thus, these methods are limited by the delays caused by straggling workers.