[HTML][HTML] Exploring the frontiers of deep learning and natural language processing: A comprehensive overview of key challenges and emerging trends

W Khan, A Daud, K Khan, S Muhammad… - Natural Language …, 2023‏ - Elsevier
In the recent past, more than 5 years or so, Deep Learning (DL) especially the large
language models (LLMs) has generated extensive studies out of a distinctly average …

[HTML][HTML] Advancements in complex knowledge graph question answering: a survey

Y Song, W Li, G Dai, X Shang - Electronics, 2023‏ - mdpi.com
Complex Question Answering over Knowledge Graph (C-KGQA) seeks to solve complex
questions using knowledge graphs. Currently, KGQA systems achieve great success in …

FC-KBQA: A fine-to-coarse composition framework for knowledge base question answering

L Zhang, J Zhang, Y Wang, S Cao, X Huang… - arxiv preprint arxiv …, 2023‏ - arxiv.org
The generalization problem on KBQA has drawn considerable attention. Existing research
suffers from the generalization issue brought by the entanglement in the coarse-grained …

Glm-dialog: Noise-tolerant pre-training for knowledge-grounded dialogue generation

J Zhang, X Zhang, D Zhang-Li, J Yu, Z Yao… - Proceedings of the 29th …, 2023‏ - dl.acm.org
We present GLM-Dialog, a large-scale language model (LLM) with 10B parameters capable
of knowledge-grounded conversation in Chinese using a search engine to access the …

Aligning language models to explicitly handle ambiguity

HJ Kim, Y Kim, C Park, J Kim, C Park, KM Yoo… - arxiv preprint arxiv …, 2024‏ - arxiv.org
In interactions between users and language model agents, user utterances frequently
exhibit ellipsis (omission of words or phrases) or imprecision (lack of exactness) to prioritize …

Extractive question answering over ancient scriptures texts using generative AI and natural language processing techniques

AK Pandey, SS Roy - IEEE Access, 2024‏ - ieeexplore.ieee.org
Generative AI (GenAI) and Natural Language Processing (NLP) are transforming the
landscape of question-answering systems, shifting from traditional methods to more …

Dynamic multi teacher knowledge distillation for semantic parsing in KBQA

A Zou, J Zou, S Cao, J Zhang, J Liu, J Wan… - Expert Systems with …, 2025‏ - Elsevier
Abstract Knowledge base question answering (KBQA) is an important task of extracting
answers from a knowledge base by analyzing natural language questions. Semantic …

When to Speak, When to Abstain: Contrastive Decoding with Abstention

HJ Kim, Y Kim, S Lee, T Kim - arxiv preprint arxiv:2412.12527, 2024‏ - arxiv.org
Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks
by leveraging both pre-trained knowledge (ie, parametric knowledge) and external …

[HTML][HTML] SecureTLM: Private inference for transformer-based large model with MPC

Y Chen, X Meng, Z Shi, Z Ning, J Lin - Information Sciences, 2024‏ - Elsevier
Abstract Transformer-based Large Models (TLM), such as generative pre-trained models
(GPT), have become increasingly popular for practical applications through Deep Learning …

Hybrid-SQuAD: Hybrid Scholarly Question Answering Dataset

TA Taffa, D Baneerje, Y Assabie, R Usbeck - arxiv preprint arxiv …, 2024‏ - arxiv.org
Existing Scholarly Question Answering (QA) methods typically target homogeneous data
sources, relying solely on either text or Knowledge Graphs (KGs). However, scholarly …