Related papers: Generating Faithful Text From a Knowledge Graph wi…
Recent advances in large language models (LLMs) have led to impressive progress in natural language generation, yet their tendency to produce hallucinated or unsubstantiated content remains a critical concern. To improve factual…
Pre-trained language models (PTLM) have achieved impressive results in a range of natural language understanding (NLU) and generation (NLG) tasks. However, current pre-training objectives such as masked token prediction (for BERT-style…
Large language models like GPT-4, Gemini, and Claude have transformed natural language processing (NLP) tasks such as question answering, dialogue generation, summarization, and so forth; yet their susceptibility to hallucination stands as…
Graph-to-text generation aims to generate fluent texts from graph-based data. In this paper, we investigate two recently proposed pretrained language models (PLMs) and analyze the impact of different task-adaptive pretraining strategies for…
Currently, the main approach for Large Language Models (LLMs) to tackle the hallucination issue is incorporating Knowledge Graphs(KGs).However, LLMs typically treat KGs as plain text, extracting only semantic information and limiting their…
Constructing Knowledge Graphs (KGs) from unstructured text provides a structured framework for knowledge representation and reasoning, yet current LLM-based approaches struggle with a fundamental trade-off: factual coverage often leads to…
This paper studies speculative reasoning task on real-world knowledge graphs (KG) that contain both \textit{false negative issue} (i.e., potential true facts being excluded) and \textit{false positive issue} (i.e., unreliable or outdated…
Large language models (LLMs) have demonstrated immense potential across various tasks. However, research for exploring and improving the capabilities of LLMs in interpreting graph structures remains limited. To address this gap, we conduct…
Most available data is unstructured, making it challenging to access valuable information. Automatically building Knowledge Graphs (KGs) is crucial for structuring data and making it accessible, allowing users to search for information…
Typical user-friendly renderings of knowledge graphs are visualisations and natural language text. Within the latter HCI solution approach, data-driven natural language generation systems receive increased attention, but they are often…
Data-to-text generation has recently attracted substantial interests due to its wide applications. Existing methods have shown impressive performance on an array of tasks. However, they rely on a significant amount of labeled data for each…
This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e.g., BERT, GPT-2/3), without human supervision. Popular KGs (e.g, Wikidata, NELL) are built in either a supervised or semi-supervised manner,…
Knowledge graphs automatically constructed from text are increasingly used in real-world applications. However, their inherent noise, fragmentation, and semantic inconsistencies significantly affect the performance of Graph Neural Networks…
Knowledge graphs (KGs) have commonly been constructed using predefined symbolic relation schemas, typically implemented as categorical relation labels. This design has notable shortcomings: real-world relations are often contextual,…
Graph Self-Supervised Learning (GSSL) offers a powerful paradigm for learning graph representations without labeled data. However, existing work assumes clean, manually curated graphs. Recent advances in NLP enable the large-scale automatic…
Recent advancements in Large Language Models (LLMs) have showcased their proficiency in answering natural language queries. However, their effectiveness is hindered by limited domain-specific knowledge, raising concerns about the…
In ad text generation (ATG), desirable ad text is both faithful and informative. That is, it should be faithful to the input document, while at the same time containing important information that appeals to potential customers. The existing…
Conditional text generation has been a challenging task that is yet to see human-level performance from state-of-the-art models. In this work, we specifically focus on the Commongen benchmark, wherein the aim is to generate a plausible…
Despite the superior performance of large language models to generate natural language texts, it is hard to generate texts with correct logic according to a given task, due to the difficulties for neural models to capture implied rules from…
Large language models (LLMs) have demonstrated remarkable capabilities across various domains, although their susceptibility to hallucination poses significant challenges for their deployment in critical areas such as healthcare. To address…