Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation, and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions, and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.

This paper proposes a framework for quantitatively evaluating interactive LLMs such as ChatGPT using publicly available data sets. We carry out an extensive technical evaluation of ChatGPT using 23 data sets covering 8 different common NLP application tasks. We evaluate the multitask, multilingual and multi-modal aspects of ChatGPT based on these data sets and a newly designed multimodal dataset. We find that ChatGPT outperforms LLMs with zero-shot learning on most tasks and even outperforms fine-tuned models on some tasks. We find that it is better at understanding non-Latin script languages than generating them. It is able to generate multimodal content from textual prompts, via an intermediate code generation step. Moreover, we find that ChatGPT is 63.41% accurate on average in 10 different reasoning categories under logical reasoning, non-textual reasoning, and commonsense reasoning, hence making it an unreliable reasoner. It is, for example, better at deductive than inductive reasoning. ChatGPT suffers from hallucination problems like other LLMs and it generates more extrinsic hallucinations from its parametric memory as it does not have access to an external knowledge base. Finally, the interactive feature of ChatGPT enables human collaboration with the underlying LLM to improve its performance, i.e, 8% ROUGE-1 on summarization and 2% ChrF++ on machine translation, in a multi-turn "prompt engineering" fashion. We also release codebase for evaluation set extraction.

Machine learning systems produce biased results towards certain demographic groups, known as the fairness problem. Recent approaches to tackle this problem learn a latent code (i.e., representation) through disentangled representation learning and then discard the latent code dimensions correlated with sensitive attributes (e.g., gender). Nevertheless, these approaches may suffer from incomplete disentanglement and overlook proxy attributes (proxies for sensitive attributes) when processing real-world data, especially for unstructured data, causing performance degradation in fairness and loss of useful information for downstream tasks. In this paper, we propose a novel fairness framework that performs debiasing with regard to both sensitive attributes and proxy attributes, which boosts the prediction performance of downstream task models without complete disentanglement. The main idea is to, first, leverage gradient-based explanation to find two model focuses, 1) one focus for predicting sensitive attributes and 2) the other focus for predicting downstream task labels, and second, use them to perturb the latent code that guides the training of downstream task models towards fairness and utility goals. We show empirically that our framework works with both disentangled and non-disentangled representation learning methods and achieves better fairness-accuracy trade-off on unstructured and structured datasets than previous state-of-the-art approaches.

Conversational models that are generative and open-domain are particularly susceptible to generating unsafe content since they are trained on web-based social data. Prior approaches to mitigating this issue have drawbacks, such as disrupting the flow of conversation, limited generalization to unseen toxic input contexts, and sacrificing the quality of the dialogue for the sake of safety. In this paper, we present a novel framework, named "LOT" (Learn NOT to), that employs a contrastive loss to enhance generalization by learning from both positive and negative training signals. Our approach differs from the standard contrastive learning framework in that it automatically obtains positive and negative signals from the safe and unsafe language distributions that have been learned beforehand. The LOT framework utilizes divergence to steer the generations away from the unsafe subspace and towards the safe subspace while sustaining the flow of conversation. Our approach is memory and time-efficient during decoding and effectively reduces toxicity while preserving engagingness and fluency. Empirical results indicate that LOT reduces toxicity by up to four-fold while achieving four to six-fold higher rates of engagingness and fluency compared to baseline models. Our findings are further corroborated by human evaluation.

We present NusaCrowd, a collaborative initiative to collect and unify existing resources for Indonesian languages, including opening access to previously non-public resources. Through this initiative, we have brought together 137 datasets and 118 standardized data loaders. The quality of the datasets has been assessed manually and automatically, and their value is demonstrated through multiple experiments. NusaCrowd's data collection enables the creation of the first zero-shot benchmarks for natural language understanding and generation in Indonesian and the local languages of Indonesia. Furthermore, NusaCrowd brings the creation of the first multilingual automatic speech recognition benchmark in Indonesian and the local languages of Indonesia. Our work strives to advance natural language processing (NLP) research for languages that are under-represented despite being widely spoken.

Although large language models (LLMs) have 001 made significant advancements, they still lack 002 the ability to personalize responses. However, 003 manually inputting personal information into 004 LLMs can be tedious and may never be com-005 pleted. Since conversations contain a wealth 006 of personal information, we propose to ex-007 tract personal information and populate a per-008 sonal knowledge graph (PKG) from conversa-009 tion. We explored finetuning and prompting 010 LLMs, but found that they still struggle with 011 generating desired PKGs. Our analysis shows 012 that GPT-3.5 cannot generate knowledge triples 013 with desired relations and T5 often fails to iden-014 tify the correct subject. Furthermore, GPT-3.5 015 struggles with extracting in-context subjects, 016 recognizing negation expressions, and differen-017 tiating between questions and statements. By 018 highlighting these limitations, we aim to inspire 019 future research on PKG population from con-020 versation and the development of personalized 021 dialogue systems. 022

Large-scale vision-language pre-trained (VLP) models are prone to hallucinate non-existent visual objects when generating text based on visual information. In this paper, we systematically study the object hallucination problem from three aspects. First, we examine recent state-of-the-art VLP models, showing that they still hallucinate frequently, and models achieving better scores on standard metrics (e.g., CIDEr) could be more unfaithful. Second, we investigate how different types of image encoding in VLP influence hallucination, including region-based, grid-based, and patch-based. Surprisingly, we find that patch-based features perform the best and smaller patch resolution yields a non-trivial reduction in object hallucination. Third, we decouple various VLP objectives and demonstrate that token-level image-text alignment and controlled generation are crucial to reducing hallucination. Based on that, we propose a simple yet effective VLP loss named ObjMLM to further mitigate object hallucination. Results show that it reduces object hallucination by up to 17.4% when tested on two benchmarks (COCO Caption for in-domain and NoCaps for out-of-domain evaluation).

Closed-book question answering (QA) requires a model to directly answer an open-domain question without access to any external knowledge. Prior work on closed-book QA either directly finetunes or prompts a pretrained language model (LM) to leverage the stored knowledge. However, they do not fully exploit the parameterized knowledge. To address this inefficiency, we propose a two-stage, closed-book QA framework which employs a coarse-to-fine approach to extract the relevant knowledge and answer a question. We first generate a related context for a given question by prompting a pretrained LM. We then prompt the same LM to generate an answer using the generated context and the question. Additionally, we marginalize over the generated contexts to improve the accuracies and reduce context uncertainty. Experimental results on three QA benchmarks show that our method significantly outperforms previous closed-book QA methods. For example on TriviaQA, our method improves exact match accuracy from 55.3% to 68.6%, and is on par with open-book QA methods (68.6% vs. 68.0%). Our results show that our new methodology is able to better exploit the stored knowledge in pretrained LMs without adding extra learnable parameters or needing finetuning, and paves the way for hybrid models that integrate pretrained LMs with external knowledge.

Intravenous (IV) leiomyomatosis is a rare IV disease. Our case presents Ga-68-FAPI and F-18-FDG PET/CT findings of IV leiomyomatosis in a 37-year-old woman. Intravenous leiomyomatosis shows only mild FDG but intense Ga-68-FAPI activity on PET/CT studies. In this case, Ga-68-FAPI was superior to F-18-FDG PET/CT in detecting IV leiomyomatosis.

Considerable advancements have been made in various NLP tasks based on the impressive power of large language models (LLMs) and many NLP applications are deployed in our daily lives. In this work, we challenge the capability of LLMs with the new task of Ethical Quandary Generative Question Answering. Ethical quandary questions are more challenging to address because multiple conflicting answers may exist to a single quandary. We explore the current capability of LLMs in providing an answer with a deliberative exchange of different perspectives to an ethical quandary, in the approach of Socratic philosophy, instead of providing a closed answer like an oracle. We propose a model that searches for different ethical principles applicable to the ethical quandary and generates an answer conditioned on the chosen principles through prompt-based few-shot learning. We also discuss the remaining challenges and ethical issues involved in this task and suggest the direction toward developing responsible NLP systems by incorporating human values explicitly.

Task-adaptive pre-training (TAPT) alleviates the lack of labelled data and provides performance lift by adapting unlabelled data to downstream task. Unfortunately, existing adaptations mainly involve deterministic rules that cannot generalize well. Here, we propose Clozer, a sequence-tagging based cloze answer extraction method used in TAPT that is extendable for adaptation on any cloze-style machine reading comprehension (MRC) downstream tasks. We experiment on multiple-choice cloze-style MRC tasks, and show that Clozer performs significantly better compared to the oracle and state-of-the-art in escalating TAPT effectiveness in lifting model performance, and prove that Clozer is able to recognize the gold answers independently of any heuristics.

To diversify and enrich generated dialogue responses, knowledge-grounded dialogue has been investigated in recent years. The existing methods tackle the knowledge grounding challenge by retrieving the relevant sentences over a large corpus and augmenting the dialogues with explicit extra information. Despite their success, however, the existing works have drawbacks on the inference efficiency. This paper proposes KnowExpert, an end-to-end framework to bypass the explicit retrieval process and inject knowledge into the pre-trained language models with lightweight adapters and adapt to the knowledge-grounded dialogue task. To the best of our knowledge, this is the first attempt to tackle this challenge without retrieval in this task under an open-domain chit-chat scenario. The experimental results show that KnowExpert performs comparably with some retrieval-based baselines while being time-efficient in inference, demonstrating the effectiveness of our proposed method.

Long-form question answering (LFQA) aims to generate a paragraph-length answer for a given question. While current work on LFQA using large pre-trained model for generation are effective at producing fluent and somewhat relevant content, one primary challenge lies in how to generate a faithful answer that has less hallucinated content. We propose a new end-to-end framework that jointly models answer generation and machine reading. The key idea is to augment the generation model with fine-grained, answer-related salient information which can be viewed as an emphasis on faithful facts. State-of-the-art results on two LFQA datasets, ELI5 and MS MARCO, demonstrate the effectiveness of our method, in comparison with strong baselines on automatic and human evaluation metrics. A detailed analysis further proves the competency of our methods in generating fluent, relevant, and more faithful answers.

In this thesis, we investigated the relevance, faithfulness, and succinctness aspects of Long Form Question Answering (LFQA). LFQA aims to generate an in-depth, paragraph-length answer for a given question, to help bridge the gap between real scenarios and the existing open-domain QA models which can only extract short-span answers. LFQA is quite challenging and under-explored. Few works have been done to build an effective LFQA system. It is even more challenging to generate a good-quality long-form answer relevant to the query and faithful to facts, since a considerable amount of redundant, complementary, or contradictory information will be contained in the retrieved documents. Moreover, no prior work has been investigated to generate succinct answers. We are among the first to research the LFQA task. We pioneered the research direction to improve the answer quality in terms of 1) query-relevance, 2) answer faithfulness, and 3) answer succinctness.

Multi-hop question generation (MQG) aims to generate com-plex questions which require reasoning over multiple pieces of information of the input passage. Most existing work on MQG has focused on exploring graph-based networks to equip the traditional Sequence-to-sequence framework with reasoning ability. However, these models do not take full advantage of the constraint between questions and answers. Furthermore, studies on multi-hop question answering (QA) suggest that Transformers can replace the graph structure for multi-hop reasoning. Therefore, in this work, we propose a novel framework, QA4QG, a QA-augmented BART-based framework for MQG. It augments the standard BART model with an additional multi-hop QA module to further con-strain the generated question. Our results on the HotpotQA dataset show that QA4QG outperforms all state-of-the-art models, with an increase of 8 BLEU-4 and 8 ROUGE points compared to the best results previously reported. Our work suggests the advantage of introducing pre-trained language models and QA module for the MQG task.

Query focused summarization (QFS) models aim to generate summaries from source documents that can answer the given query. Most previous work on QFS only considers the query relevance criterion when producing the summary. However, studying the effect of answer relevance in the summary generating process is also important. In this paper, we propose QFS-BART, a model that incorporates the explicit answer relevance of the source documents given the query via a question answering model, to generate coherent and answer-related summaries. Furthermore, our model can take advantage of large pre-trained models which improve the summarization performance significantly. Empirical results on the Debatepedia dataset show that the proposed model achieves the new state-of-the-art performance.

This paper analyzes the formation mechanism of urban hazard chains. The results demonstrate that the complex interaction between the disaster-bearing bodies under the action of disaster-causing factors is the direct cause of urban hazard chains. The analysis of the energy effects of urban hazard chains shows that the coupling of the excitation energy released by the causative agent and the energy of the disaster-bearing bodies is the fundamental cause of urban hazard chains. Based on the description of the dynamical mechanism of the urban disaster chain system, this paper first sets up a disaster scenario and considers the effect of the time lag to establish a system dynamics model of the urban disaster chain and urban disaster management. The model of urban disaster management system dynamics shows the mutual influence and complementary relationship between disasters and the economy, pointing out that emphasizing the spill-over effects of disaster management systems can improve the effectiveness of disaster mitigation. This study also uses equilibrium entropy and brittle entropy theories to characterize the vulnerability of single-function networks and the degree of brittle association of each lifeline subsystem, respectively, and establishes a model for assessing the sensitivity of lifeline systems to disaster damage. Built on the collection and feedback of information from disaster areas after the occurrence of emergencies, this paper establishes a deterministic multihazard emergency resource dispatches model and an uncertain multihazard emergency resource dispatch model.

While question answering (QA) systems have witnessed great breakthroughs in reading comprehension (RC) tasks, spoken question answering (SQA) is still a much less investigated area. Previous work shows that existing SQA systems are limited by catastrophic impact of automatic speech recognition (ASR) errors [1] and the lack of large-scale real SQA datasets [2]. In this paper, we propose using contextualized word representations to mitigate the effects of ASR errors and pretraining on existing textual QA datasets to mitigate the data scarcity issue. New state-of-the-art results have been achieved using contextualized word representations on both the artificially synthesised and real SQA benchmark data sets, with 21.5 EM/18.96 F1 score improvement over the sub-word unit based baseline on the Spoken-SQuAD [1] data, and 13.11 EM/10.99 F1 score improvement on the ODSQA data [2]. By further fine-tuning pre-trained models with existing large scaled textual QA data, we obtained 38.12 EM/34.1 F1 improvement over the baseline of fine-tuned only on small sized real SQA data.

Multi-hop Question Generation (QG) aims to generate answer-related questions by aggregating and reasoning over multiple scattered evidence from different paragraphs. It is a more challenging yet under-explored task compared to conventional single-hop QG, where the questions are generated from the sentence containing the answer or nearby sentences in the same paragraph without complex reasoning. To address the additional challenges in multi-hop QG, we propose Multi-Hop Encoding Fusion Network for Question Generation (MulQG), which does context encoding in multiple hops with Graph Convolutional Network and encoding fusion via an Encoder Reasoning Gate. To the best of our knowledge, we are the first to tackle the challenge of multi-hop reasoning over paragraphs without any sentence-level information. Empirical results on HotpotQA dataset demonstrate the effectiveness of our method, in comparison with baselines on automatic evaluation metrics. Moreover, from the human evaluation, our proposed model is able to generate fluent questions with high completeness and outperforms the strongest baseline by 20.8% in the multi-hop evaluation. on. The code is publicly availableat https://github.com/HLTCHKU