Owl: A large language model for it operations

H Guo, J Yang, J Liu, L Yang, L Chai, J Bai… - arxiv preprint arxiv …, 2023‏ - arxiv.org
With the rapid development of IT operations, it has become increasingly crucial to efficiently
manage and analyze large volumes of data for practical applications. The techniques of …

Logformer: A pre-train and tuning pipeline for log anomaly detection

H Guo, J Yang, J Liu, J Bai, B Wang, Z Li… - Proceedings of the …, 2024‏ - ojs.aaai.org
Log anomaly detection is a key component in the field of artificial intelligence for IT
operations (AIOps). Considering log data of variant domains, retraining the whole network …

Stochastic rag: End-to-end retrieval-augmented generation through expected utility maximization

H Zamani, M Bendersky - Proceedings of the 47th International ACM …, 2024‏ - dl.acm.org
This paper introduces Stochastic RAG--a novel approach for end-to-end optimization of
retrieval-augmented generation (RAG) models that relaxes the simplifying assumptions of …

Conceptmath: A bilingual concept-wise benchmark for measuring mathematical reasoning of large language models

Y Wu, J Liu, X Bu, J Liu, Z Zhou, Y Zhang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
This paper introduces ConceptMath, a bilingual (English and Chinese), fine-grained
benchmark that evaluates concept-wise mathematical reasoning of Large Language Models …

Emerge: Integrating rag for improved multimodal ehr predictive modeling

Y Zhu, C Ren, Z Wang, X Zheng, S **e, J Feng… - arxiv preprint arxiv …, 2024‏ - arxiv.org
The integration of multimodal Electronic Health Records (EHR) data has notably advanced
clinical predictive capabilities. However, current models that utilize clinical notes and …

An information bottleneck perspective for effective noise filtering on retrieval-augmented generation

K Zhu, X Feng, X Du, Y Gu, W Yu, H Wang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Retrieval-augmented generation integrates the capabilities of large language models with
relevant information retrieved from an extensive corpus, yet encounters challenges when …

M2C: towards automatic multimodal manga complement

H Guo, B Wang, J Bai, J Liu, J Yang, Z Li - arxiv preprint arxiv:2310.17130, 2023‏ - arxiv.org
Multimodal manga analysis focuses on enhancing manga understanding with visual and
textual features, which has attracted considerable attention from both natural language …

EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generation

Y Zhu, C Ren, Z Wang, X Zheng, S **e, J Feng… - Proceedings of the 33rd …, 2024‏ - dl.acm.org
The integration of multimodal Electronic Health Records (EHR) data has significantly
advanced clinical predictive capabilities. Existing models, which utilize clinical notes and …

MLAD: A Unified Model for Multi-system Log Anomaly Detection

R Zang, H Guo, J Yang, J Liu, Z Li, T Zheng… - arxiv preprint arxiv …, 2024‏ - arxiv.org
In spite of the rapid advancements in unsupervised log anomaly detection techniques, the
current mainstream models still necessitate specific training for individual system datasets …

Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generation

X Wu, J Yang, T Li, D Liang, S Zhang, Y Du… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Incorporating external knowledge into dialogue generation (KIDG) is crucial for improving
the correctness of response, where evidence fragments serve as knowledgeable snippets …