Knowledge-augmented reasoning distillation for small language models in knowledge-intensive tasks
Abstract Large Language Models (LLMs) have shown promising performance in knowledge-
intensive reasoning tasks that require a compound understanding of knowledge. However …
intensive reasoning tasks that require a compound understanding of knowledge. However …
Retrieval-Augmented Generation for Natural Language Processing: A Survey
Large language models (LLMs) have demonstrated great success in various fields,
benefiting from their huge amount of parameters that store knowledge. However, LLMs still …
benefiting from their huge amount of parameters that store knowledge. However, LLMs still …
Model compression and efficient inference for large language models: A survey
Transformer based large language models have achieved tremendous success. However,
the significant memory and computational costs incurred during the inference process make …
the significant memory and computational costs incurred during the inference process make …
MLLM-FL: Multimodal Large Language Model Assisted Federated Learning on Heterogeneous and Long-tailed Data
Previous studies on federated learning (FL) often encounter performance degradation due
to data heterogeneity among different clients. In light of the recent advances in multimodal …
to data heterogeneity among different clients. In light of the recent advances in multimodal …
Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application
Large Language Models (LLMs) have showcased exceptional capabilities in various
domains, attracting significant interest from both academia and industry. Despite their …
domains, attracting significant interest from both academia and industry. Despite their …
Teaching Small Language Models to Reason for Knowledge-Intensive Multi-Hop Question Answering
Abstract Large Language Models (LLMs) can teach small language models (SLMs) to solve
complex reasoning tasks (eg, mathematical question answering) by Chain-of-thought …
complex reasoning tasks (eg, mathematical question answering) by Chain-of-thought …
Knowledge boosting during low-latency inference
Models for low-latency, streaming applications could benefit from the knowledge capacity of
larger models, but edge devices cannot run these models due to resource constraints. A …
larger models, but edge devices cannot run these models due to resource constraints. A …
Event Temporal Relation Extraction based on Retrieval-Augmented on LLMs
X Zhang, L Zang, Q Liu, S Wei, S Hu - arXiv preprint arXiv:2403.15273, 2024 - arxiv.org
Event temporal relation (TempRel) is a primary subject of the event relation extraction task.
However, the inherent ambiguity of TempRel increases the difficulty of the task. With the rise …
However, the inherent ambiguity of TempRel increases the difficulty of the task. With the rise …
SolMover: Smart Contract Code Translation Based on Concepts
Large language models (LLMs) have showcased remarkable skills, rivaling or even
exceeding human intelligence in certain areas. Their proficiency in translation is notable, as …
exceeding human intelligence in certain areas. Their proficiency in translation is notable, as …