Complex QA and language models hybrid architectures, Survey

X Daull, P Bellot, E Bruno, V Martin… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper reviews the state-of-the-art of language models architectures and strategies for"
complex" question-answering (QA, CQA, CPS) with a focus on hybridization. Large …

LAIT: Efficient multi-segment encoding in transformers with layer-adjustable interaction

J Milbauer, A Louis, MJ Hosseini, A Fabrikant… - arXiv preprint arXiv …, 2023 - arxiv.org
Transformer encoders contextualize token representations by attending to all other tokens at
each layer, leading to quadratic increase in compute effort with the input length. In practice …

Retrieval-Enhanced Machine Learning: Synthesis and Opportunities

F Diaz, A Drozdov, TE Kim, A Salemi… - Proceedings of the 2024 …, 2024 - dl.acm.org
Retrieval-enhanced machine learning (REML) refers to the use of information retrieval
methods to support reasoning and inference in machine learning tasks. Although relatively …

ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science

S Munikoti, A Acharya, S Wagle… - arXiv preprint arXiv …, 2023 - arxiv.org
Large language models record impressive performance on many natural language
processing tasks. However, their knowledge capacity is limited to the pretraining corpus …

Bridging the preference gap between retrievers and llms

Z Ke, W Kong, C Li, M Zhang, Q Mei… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Language Models (LLMs) have demonstrated superior results across a wide range of
tasks, while retrieval has long been established as an effective means of obtaining task …

Recall: Empowering Multimodal Embedding for Edge Devices

D Cai, S Wang, C Peng, Z Zhang, M Xu - arXiv preprint arXiv:2409.15342, 2024 - arxiv.org
Human memory is inherently prone to forgetting. To address this, multimodal embedding
models have been introduced, which transform diverse real-world data into a unified …

[引用][C] Late-interaction 기반메모리증강임베딩을활용한한국어오픈도메인질의응답

박영준, 이정, 나승훈 - 한국정보과학회학술발표논문집, 2024 - dbpia.co.kr
요 약오픈 도메인 질의응답 (Open-domain Question Answering) 은 주어진 질문에 대해 방대한
지식 소스에서 정확한 답변을추출하는 과제이다. 기존 검색 증강 언어 모델 (Retrieval …