Tagged articles
Knowledge Integration
11 articles · Page 1 of 1
The article analyzes MEMO, a framework that equips a frozen large language model with a lightweight 1.5B‑parameter memory model fine‑tuned on a target corpus, detailing its architecture, five‑step data synthesis pipeline, structured inference protocol, experimental advantages over RAG and fine‑tuning, as well as its limitations and future research directions.
Knowledge IntegrationLLMRAG
0 likes · 19 min read

This review examines how formal knowledge representations (ontologies) can be integrated with large language models to enhance reasoning, reduce hallucinations, and improve factual reliability, outlining three roles—information provider, reasoner, validator—while analyzing recent frameworks, open‑source projects, and future research challenges.
AIKnowledge IntegrationRAG
0 likes · 29 min read

This article reviews recent AI self‑evolution research and provides an in‑depth analysis of the SEAL (Self‑Adapting Language) framework, which enables large language models to generate and learn from their own synthetic data through a nested reinforcement‑learning and fine‑tuning loop, with experimental results on few‑shot and knowledge‑integration tasks.
Few-Shot LearningKnowledge IntegrationMeta-learning
0 likes · 11 min read

Professor Wang Yichao from Huawei Noah's Ark Lab presents a comprehensive exploration of large language models in recommendation systems, covering background, challenges, two key projects (LLM4Rec and Uni-CTR), experimental results, and future directions for open, knowledge‑enhanced, generative recommendation pipelines.
AIKnowledge IntegrationLLM4Rec
0 likes · 13 min read

This article reviews the evolution of dialogue systems from modular task‑oriented designs to end‑to‑end large‑scale models, detailing Baidu's PLATO series, their technical innovations, real‑world deployments, challenges such as inference efficiency and safety, and future research directions in conversational AI.
AI safetyConversational AIDialogue Systems
0 likes · 13 min read

This report reviews the background, recent research progress, practical applications, and future directions of controllable text generation using transformer‑based pretrained language models, highlighting methods such as decoding strategies, prompt learning, memory networks, continual learning, contrastive training, and knowledge integration.
Continual LearningKnowledge Integrationcontrastive training
0 likes · 13 min read

This talk presents recent year’s research on natural language generation, covering the ProphetNet pre‑trained generation model, external‑knowledge integration for generation, non‑autoregressive pre‑training (BANG), the Poolingformer long‑text architecture, EL‑attention for faster decoding, and a new multi‑task generation benchmark.
Knowledge IntegrationNon-autoregressivePretraining
0 likes · 22 min read

This article presents the business background of Tmall Genie’s voice‑driven content‑on‑demand service, critiques the traditional pipeline for entity extraction, and details an end‑to‑end speech‑semantic model—including the Speech2Slot architecture, knowledge‑enhanced encoding, and Phoneme‑BERT unsupervised pre‑training—demonstrating significant performance gains in both generation and classification tasks.
Entity ExtractionKnowledge IntegrationSpeech Recognition
0 likes · 14 min read


JD TechFeb 2, 2021 · Artificial Intelligence
The article reviews recent research on multimodal digital content generation and automatic text summarization, outlining the evolution from extractive to abstractive methods, highlighting four key technology trends such as pretrained language models, transformer dominance, knowledge‑enhanced generation, and multimodal‑knowledge joint modeling, and describing an industrial e‑commerce application built on these advances.
Generative ModelsKnowledge Integratione-commerce
0 likes · 12 min read

This article provides a detailed survey of pre‑trained models (PTMs) for natural language processing, classifying them into shallow embeddings and contextual encoders, discussing training paradigms such as knowledge integration and model compression, and offering guidance on transfer learning and future challenges.
Knowledge IntegrationPretrained Modelsmodel compression
0 likes · 25 min read

This paper introduces Heterogeneous Memory Networks (HMNs), combining context‑free and context‑aware memory modules to jointly process user queries, dialogue history, and knowledge bases, achieving state‑of‑the‑art performance on three task‑oriented dialogue datasets in both BLEU and F1 metrics.
Dialogue SystemsKnowledge Integrationmemory networks
0 likes · 17 min read
