Large language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Add...
详细信息
Model fusing has always been an important topic, especially in an era where large language models (LLM) and multi-modal language models (MLM) with different architectures, parameter sizes and training pipelines, are b...
详细信息
The knowledge graph-to-text (KG-to-text) generation task aims to synthesize coherent and engaging sentences that accurately convey the complex information derived from an input knowledge graph. One of the primary chal...
详细信息
ISBN:
(纸本)9798891760608
The knowledge graph-to-text (KG-to-text) generation task aims to synthesize coherent and engaging sentences that accurately convey the complex information derived from an input knowledge graph. One of the primary challenges in this task is bridging the gap between the diverse structures of the KG and the target text, while preserving the details of the input KG. To address this, we propose a novel approach that efficiently integrates graph structure-aware modules with pre-trained language models. Unlike conventional techniques, which only consider direct connections between first-order neighbors, our method delves deeper by incorporating Relative Distance Encoding as a bias within the graph structure-aware module. This enables our model to better capture the intricate topology information present in the KG. To further elevate the fidelity of the generated text, Planning Selection and Similarity Distinction are introduced. Our approach filters the most relevant linearized sequences by employing a planning scorer, while simultaneously distinguishing similar input KGs through contrastive learning techniques. Experiments on two datasets demonstrate the superiority of our model.
This study presents a novel evaluation framework for the Vision-language Navigation (VLN) task. It aims to diagnose current models for various instruction categories at a finer-grained level. The framework is structur...
详细信息
Multilingual large language models (MLLMs), trained on multilingual balanced data, demonstrate better zero-shot learning performance in non-English languages compared to large language models trained on English-domina...
详细信息
Recent advancements in instruction-tuning datasets have predominantly focused on specific tasks like mathematical or logical reasoning. There has been a notable gap in data designed for aligning language models to mai...
详细信息
The recent development of fact verification systems with natural logic has enhanced their explainability by aligning claims with evidence through set-theoretic operators, providing faithful justifications. Despite the...
详细信息
In this work, we address the challenge of cross-lingual proper noun recognition in automatic speech recognition (ASR), where proper nouns in an utterance may originate from a language different from the language in wh...
详细信息
Advancements in Large language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performanc...
详细信息
Social manufacturing (SocialMfg), as an emerging paradigm, leverages socialized manufacturing resource nodes (SMRNs) grouped into manufacturing communities (MCs) through cyber-physical-social connections to collective...
详细信息
Social manufacturing (SocialMfg), as an emerging paradigm, leverages socialized manufacturing resource nodes (SMRNs) grouped into manufacturing communities (MCs) through cyber-physical-social connections to collectively create, produce, and share goods and services. Despite its nascent stage, the potential impact of SocialMfg on mass personalization and sustainability is significant, prompting manufacturing enterprises to increasingly adopt this model facilitated by various industrial Internet platforms (IIPs). However, SMRNs face challenges such as trust and reputation and alignment of interests when forming MCs. This article proposes an approach that integrates naturallanguageprocessing and community detection algorithm to autonomously form relevant MCs among SMRNs on IIPs. A novel BERT -like model, SoManBERT, is introduced to accurately classify the manufacturing interests and roles of SMRNs, revealing their expertise. Subsequently, a recommender system, integrating trust scores and a modified -density -peaks -based overlapping community detection (DPOCD) algorithm, is designed to recommend reliable SMRNs with similar manufacturing interests or roles to each other. The effectiveness of the proposed approach is verified through a case study on a SocialMfg prototype system. empirical evaluations reveal that this approach surpasses baseline methods, demonstrating its potential for SocialMfg environments.
暂无评论