LLMs obtain remarkable performance but suffer from hallucinations. Most research on detecting hallucination focuses on the questions with short and concrete correct answers that are easy to check the faithfulness. Hallucination detections for text generation with open-ended answers are more challenging. Some researchers use external knowledge to detect hallucinations in generated texts, but external resources for specific scenarios are hard to access. Recent studies on detecting hallucinations in long text without external resources conduct consistency comparison among multiple sampled outputs. To handle long texts, researchers split long texts into multiple facts and individually compare the consistency of each pairs of facts. However, these methods (1) hardly achieve alignment among multiple facts; (2) overlook dependencies between multiple contextual facts. In this paper, we propose a graph-based context-aware (GCA) hallucination detection for text generations, which aligns knowledge facts and considers the dependencies between contextual knowledge triples in consistency comparison. Particularly, to align multiple facts, we conduct a triple-oriented response segmentation to extract multiple knowledge triples. To model dependencies among contextual knowledge triple (facts), we construct contextual triple into a graph and enhance triples' interactions via message passing and aggregating via RGCN. To avoid the omission of knowledge triples in long text, we conduct a LLM-based reverse verification via reconstructing the knowledge triples. Experiments show that our model enhances hallucination detection and excels all baselines.

Answering questions using pre-trained language models (LMs) and knowledge graphs (KGs) presents challenges in identifying relevant knowledge and performing joint reasoning.We compared LMs (fine-tuned for the task) with the previously published QAGNN method for the Question-answering (QA) objective and further measured the impact of additional factual context on the QAGNN performance. The QAGNN method employs LMs to encode QA context and estimate KG node importance, and effectively update the question choice entity representations using Graph Neural Networks (GNNs). We further experimented with enhancing the QA context encoding by incorporating relevant knowledge facts for the question stem. The models are trained on the OpenbookQA dataset, which contains ~6000 4-way multiple choice questions and is widely used as a benchmark for QA tasks. Through our experimentation, we found that incorporating knowledge facts context led to a significant improvement in performance. In contrast, the addition of knowledge graphs to language models resulted in only a modest increase. This suggests that the integration of contextual knowledge facts may be more impactful for enhancing question answering performance compared to solely adding knowledge graphs.

Commonsense knowledge is crucial to many natural language processing tasks. Existing works usually incorporate graph knowledge with conventional graph neural networks (GNNs), leading to the text and graph knowledge encoding processes being separated in a serial pipeline. We argue that these separate representation learning stages may be suboptimal for neural networks to learn the overall context contained in both types of input knowledge. In this paper, we propose a novel context-aware graph-attention model (Context-aware GAT), which can effectively incorporate global features of relevant knowledge graphs based on a context-enhanced knowledge aggregation process. Specifically, our framework leverages a novel representation learning approach to process heterogeneous features - combining flattened graph knowledge with text. To the best of our knowledge, this is the first attempt at hierarchically applying graph knowledge aggregation on a connected subgraph in addition to contextual information to support commonsense dialogue generation. This framework shows superior performance compared to conventional GNN-based language frameworks. Both automatic and human evaluation demonstrates that our proposed model has significant performance uplifts over state-of-the-art baselines.

Previous studies have shown that large language models (LLMs) like GPTs store massive factual knowledge in their parameters. However, the stored knowledge could be false or out-dated. Traditional knowledge editing methods refine LLMs via fine-tuning on texts containing specific knowledge. However, with the increasing scales of LLMs, these gradient-based approaches bring large computation costs. The trend of model-as-a-service also makes it impossible to modify knowledge in black-box LMs. Inspired by in-context learning (ICL), a new paradigm based on demonstration contexts without parameter updating, we explore whether ICL can edit factual knowledge. To answer this question, we give a comprehensive empirical study of ICL strategies. Experiments show that in-context knowledge editing (IKE), without any gradient and parameter updating, achieves a competitive success rate compared to gradient-based methods on GPT-J (6B) but with much fewer side effects, including less over-editing on similar but unrelated facts and less knowledge forgetting on previously stored knowledge. We also apply the method to larger LMs with tens or hundreds of parameters like OPT-175B, which shows the scalability of our method. The code is available at https://github.com/Zce1112zslx/IKE.

Though pre-trained language models such as Bert and XLNet, have rapidly advanced the state-of-the-art on many NLP tasks, they implicit semantics only relying on surface information between words in corpus. Intuitively, background knowledge influences the efficacy of understanding. Inspired by this common sense, we focus on improving model pretraining by leveraging explicit knowledge. Different from recent research that optimize pretraining model by knowledge masking strategies, we propose a simple but general method to combine explicit knowledge with pretraining. To be specific, we first match knowledge facts from knowledge graph (KG) and then add a knowledge injunction layer to transformer directly without changing its architecture. The present study seeks to find the direct impact of explicit knowledge on transformer per-training. We conduct experiments on various datasets for different downstream tasks. The experimental results show that solely by adding external knowledge to transformer can improve the learning performance on many NLP tasks.

Multi-choice Machine Reading Comprehension (MRC) is a major and challenging form of MRC tasks that requires model to select the most appropriate answer from a set of candidates given passage and question. Most of the existing researches focus on the modeling of the task datasets without explicitly referring to external fine-grained commonsense sources, which is a well-known challenge in multi-choice tasks. Thus we propose a novel reference-based knowledge enhancement model based on span extraction called Reference Knowledgeable Network (RekNet), which simulates human reading strategy to refine critical information from the passage and quote external knowledge in necessity. In detail, RekNet refines fine-grained critical information and defines it as Reference Span, then quotes external knowledge quadruples by the co-occurrence information of Reference Span and answer options. Our proposed method is evaluated on two multi-choice MRC benchmarks: RACE and DREAM, which shows remarkable performance improvement with observable statistical significance level over strong baselines.

Open Domain Question Answering requires systems to retrieve external knowledge and perform multi-hop reasoning by composing knowledge spread over multiple sentences. In the recently introduced open domain question answering challenge datasets, QASC and OpenBookQA, we need to perform retrieval of facts and compose facts to correctly answer questions. In our work, we learn a semantic knowledge ranking model to re-rank knowledge retrieved through Lucene based information retrieval systems. We further propose a ``knowledge fusion model'' which leverages knowledge in BERT-based language models with externally retrieved knowledge and improves the knowledge understanding of the BERT-based language models. On both OpenBookQA and QASC datasets, the knowledge fusion model with semantically re-ranked knowledge outperforms previous attempts.

Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life. However, existing end-to-end neural models suffer from the problem of tending to generate uninformative and generic text because they cannot ground input context with background knowledge. In order to solve this problem, many researchers begin to consider combining external knowledge in text generation systems, namely knowledge-enhanced text generation. The challenges of knowledge enhanced text generation including how to select the appropriate knowledge from large-scale knowledge bases, how to read and understand extracted knowledge, and how to integrate knowledge into generation process. This survey gives a comprehensive review of knowledge-enhanced text generation systems, summarizes research progress to solving these challenges and proposes some open issues and research directions.

Open book question answering is a type of natural language based QA (NLQA) where questions are expected to be answered with respect to a given set of open book facts, and common knowledge about a topic. Recently a challenge involving such QA, OpenBookQA, has been proposed. Unlike most other NLQA tasks that focus on linguistic understanding, Open-BookQA requires deeper reasoning involving linguistic understanding as well as reasoning with common knowledge. In this paper we address QA with respect to the OpenBookQA dataset and combine state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy, an 11.6% improvement over the current state of the art.