Knowledge graphs meet multi-modal learning: A comprehensive survey

Z Chen, Y Zhang, Y Fang, Y Geng, L Guo… - arXiv preprint arXiv …, 2024 - arxiv.org
Knowledge Graphs (KGs) play a pivotal role in advancing various AI applications, with the
semantic web community's exploration into multi-modal dimensions unlocking new avenues …

Understanding llms: A comprehensive overview from training to inference

Y Liu, H He, T Han, X Zhang, M Liu, J Tian… - arXiv preprint arXiv …, 2024 - arxiv.org
The introduction of ChatGPT has led to a significant increase in the utilization of Large
Language Models (LLMs) for addressing downstream tasks. There's an increasing focus on …

Self-prompting large language models for zero-shot open-domain QA

J Li, J Wang, Z Zhang, H Zhao - arXiv preprint arXiv:2212.08635, 2022 - arxiv.org
Open-Domain Question Answering (ODQA) aims to answer questions without explicitly
providing specific background documents. This task becomes notably challenging in a zero …

Learning to filter context for retrieval-augmented generation

Z Wang, J Araki, Z Jiang, MR Parvez… - arXiv preprint arXiv …, 2023 - arxiv.org
On-the-fly retrieval of relevant knowledge has proven an essential element of reliable
systems for tasks such as open-domain question answering and fact verification. However …

Funqa: Towards surprising video comprehension

B Xie, S Zhang, Z Zhou, B Li, Y Zhang, J Hessel… - … on Computer Vision, 2025 - Springer
Surprising videos, eg, funny clips, creative performances, or visual illusions, attract
significant attention. Enjoyment of these videos is not simply a response to visual stimuli; …

Large language models are temporal and causal reasoners for video question answering

D Ko, JS Lee, W Kang, B Roh, HJ Kim - arXiv preprint arXiv:2310.15747, 2023 - arxiv.org
Large Language Models (LLMs) have shown remarkable performances on a wide range of
natural language understanding and generation tasks. We observe that the LLMs provide …

Hagrid: A human-llm collaborative dataset for generative information-seeking with attribution

E Kamalloo, A Jafari, X Zhang, N Thakur… - arXiv preprint arXiv …, 2023 - arxiv.org
The rise of large language models (LLMs) had a transformative impact on search, ushering
in a new era of search engines that are capable of generating search results in natural …

Sequential recommendation with latent relations based on large language model

S Yang, W Ma, P Sun, Q Ai, Y Liu, M Cai… - Proceedings of the 47th …, 2024 - dl.acm.org
Sequential recommender systems predict items that may interest users by modeling their
preferences based on historical interactions. Traditional sequential recommendation …

Can llms master math? investigating large language models on math stack exchange

A Satpute, N Gießing, A Greiner-Petter… - Proceedings of the 47th …, 2024 - dl.acm.org
Large Language Models (LLMs) have demonstrated exceptional capabilities in various
natural language tasks, often achieving performances that surpass those of humans …

Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering

V Adlakha, P BehnamGhader, XH Lu… - Transactions of the …, 2024 - direct.mit.edu
Instruction-following models are attractive alternatives to fine-tuned approaches for question
answering (QA). By simply prepending relevant documents and an instruction to their input …