[PDF][PDF] Merging mixture of experts and retrieval augmented generation for enhanced information retrieval and reasoning

X **ong, M Zheng - 2024 - assets-eu.researchsquare.com
This study investigates the integration of Retrieval Augmented Generation (RAG) into the
Mistral 8x7B Large Language Model (LLM), which already uses Mixture of Experts (MoE), to …

Evaluating large language models on Wikipedia-style survey generation

F Gao, H Jiang, R Yang, Q Zeng, J Lu… - Findings of the …, 2024 - aclanthology.org
Educational materials such as survey articles in specialized fields like computer science
traditionally require tremendous expert inputs and are therefore expensive to create and …

Leveraging large language models for concept graph recovery and question answering in nlp education

R Yang, B Yang, S Ouyang, T She, A Feng… - arxiv preprint arxiv …, 2024 - arxiv.org
In the domain of Natural Language Processing (NLP), Large Language Models (LLMs) have
demonstrated promise in text-generation tasks. However, their educational applications …

Rethinking llm-based preference evaluation

Z Hu, L Song, J Zhang, Z **ao, J Wang, Z Chen… - arxiv preprint arxiv …, 2024 - arxiv.org
The use of large language model (LLM)-based preference evaluations has become
widespread for comparing model responses, but it has revealed a notable bias towards …

Large language models on wikipedia-style survey generation: an evaluation in nlp concepts

F Gao, H Jiang, R Yang, Q Zeng, J Lu, M Blum… - arxiv preprint arxiv …, 2023 - arxiv.org
Educational materials such as survey articles in specialized fields like computer science
traditionally require tremendous expert inputs and are therefore expensive to create and …

Graphusion: Leveraging large language models for scientific knowledge graph fusion and construction in nlp education

R Yang, B Yang, S Ouyang, T She, A Feng… - arxiv preprint arxiv …, 2024 - arxiv.org
Knowledge graphs (KGs) are crucial in the field of artificial intelligence and are widely
applied in downstream tasks, such as enhancing Question Answering (QA) systems. The …

E-eval: a comprehensive Chinese k-12 education evaluation benchmark for large language models

J Hou, C Ao, H Wu, X Kong, Z Zheng, D Tang… - arxiv preprint arxiv …, 2024 - arxiv.org
With the accelerating development of Large Language Models (LLMs), many LLMs are
beginning to be used in the Chinese K-12 education domain. The integration of LLMs and …

AAAR-1.0: Assessing AI's Potential to Assist Research

R Lou, H Xu, S Wang, J Du, R Kamoi, X Lu… - arxiv preprint arxiv …, 2024 - arxiv.org
Numerous studies have assessed the proficiency of AI systems, particularly large language
models (LLMs), in facilitating everyday tasks such as email writing, question answering, and …

[PDF][PDF] PointTFA: training-free clustering adaption for large 3D point cloud models

J Wu, C Cao, H Zhang, B Fernando… - Proceedings of the …, 2024 - researchgate.net
The success of contrastive learning models like CLIP, known for aligning 2D image-text
pairs, has inspired the development of triplet alignment for Large 3D Point Cloud Models …

IOLBENCH: Benchmarking LLMs on Linguistic Reasoning

S Goyal, S Dan - arxiv preprint arxiv:2501.04249, 2025 - arxiv.org
Despite the remarkable advancements and widespread applications of deep neural
networks, their ability to perform reasoning tasks remains limited, particularly in domains …