With the explosive growth of textual information, summarization systems have become increasingly important. This work aims to concisely indicate the current state of the art in abstractive text summarization. As part of this, we outline the current paradigm shifts towards pre-trained encoder-decoder models and large autoregressive language models. Additionally, we delve further into the challenges of evaluating summarization systems and the potential of instruction-tuned models for zero-shot summarization. Finally, we provide a brief overview of how summarization systems are currently being integrated into commercial applications.
Generative Pre-trained Transformer 4 (GPT-4) is the fourth-generation language model in the GPT series, developed by OpenAI, which promises significant advancements in the field of natural language processing (NLP). In this research article, we have discussed the features of GPT-4, its potential applications, and the challenges that it might face. We have also compared GPT-4 with its predecessor, GPT-3. GPT-4 has a larger model size (more than one trillion), better multilingual capabilities, improved contextual understanding, and reasoning capabilities than GPT-3. Some of the potential applications of GPT-4 include chatbots, personal assistants, language translation, text summarization, and question-answering. However, GPT-4 poses several challenges and limitations such as computational requirements, data requirements, and ethical concerns.
Backdoor learning has become an emerging research area towards building a trustworthy machine learning system. While a lot of works have studied the hidden danger of backdoor attacks in image or text classification, there is a limited understanding of the model's robustness on backdoor attacks when the output space is infinite and discrete. In this paper, we study a much more challenging problem of testing whether sequence-to-sequence (seq2seq) models are vulnerable to backdoor attacks. Specifically, we find by only injecting 0.2\% samples of the dataset, we can cause the seq2seq model to generate the designated keyword and even the whole sentence. Furthermore, we utilize Byte Pair Encoding (BPE) to create multiple new triggers, which brings new challenges to backdoor detection since these backdoors are not static. Extensive experiments on machine translation and text summarization have been conducted to show our proposed methods could achieve over 90\% attack success rate on multiple datasets and models.
With direct access to human-written reference as memory, retrieval-augmented generation has achieved much progress in a wide range of text generation tasks. Since better memory would typically prompt better generation~(we define this as primal problem). The traditional approach for memory retrieval involves selecting memory that exhibits the highest similarity to the input. However, this method is constrained by the quality of the fixed corpus from which memory is retrieved. In this paper, by exploring the duality of the primal problem: better generation also prompts better memory, we propose a novel framework, selfmem, which addresses this limitation by iteratively employing a retrieval-augmented generator to create an unbounded memory pool and using a memory selector to choose one output as memory for the subsequent generation round. This enables the model to leverage its own output, referred to as self-memory, for improved generation. We evaluate the effectiveness of selfmem on three distinct text generation tasks: neural machine translation, abstractive text summarization, and dialogue generation, under two generation paradigms: fine-tuned small model and few-shot LLM. Our approach achieves state-of-the-art results in four directions in JRC-Acquis, XSum (50.3 ROUGE-1), and BigPatent (62.9 ROUGE-1), demonstrating the potential of self-memory in enhancing retrieval-augmented generation models. Furthermore, we conduct thorough analyses of each component in the selfmem framework to identify bottlenecks and provide insights for future research.
Recent pre-trained language models (PLMs) achieve promising results in existing abstractive summarization datasets. However, existing summarization benchmarks overlap in time with the standard pre-training corpora and finetuning datasets. Hence, the strong performance of PLMs may rely on the parametric knowledge that is memorized during pre-training and fine-tuning. Moreover, the knowledge memorized by PLMs may quickly become outdated, which affects the generalization performance of PLMs on future data. In this work, we propose TempoSum, a novel benchmark that contains data samples from 2010 to 2022, to understand the temporal generalization ability of abstractive summarization models. Through extensive human evaluation, we show that parametric knowledge stored in summarization models significantly affects the faithfulness of the generated summaries on future data. Moreover, existing faithfulness enhancement methods cannot reliably improve the faithfulness of summarization models on future data. Finally, we discuss several recommendations to the research community on how to evaluate and improve the temporal generalization capability of text summarization models.
The recent introduction of ChatGPT has drawn significant attention from both industry and academia due to its impressive capabilities in solving a diverse range of tasks, including language translation, text summarization, and computer programming. Its capability for writing, modifying, and even correcting code together with its ease of use and access is already dramatically impacting computer science education. This paper aims to explore how well ChatGPT can perform in an introductory-level functional language programming course. In our systematic evaluation, we treated ChatGPT as one of our students and demonstrated that it can achieve a grade B- and its rank in the class is 155 out of 314 students overall. Our comprehensive evaluation provides valuable insights into ChatGPT's impact from both student and instructor perspectives. Additionally, we identify several potential benefits that ChatGPT can offer to both groups. Overall, we believe that this study significantly clarifies and advances our understanding of ChatGPT's capabilities and potential impact on computer science education.
Prompt engineering is a critical technique in the field of natural language processing that involves designing and optimizing the prompts used to input information into models, aiming to enhance their performance on specific tasks. With the recent advancements in large language models, prompt engineering has shown significant superiority across various domains and has become increasingly important in the healthcare domain. However, there is a lack of comprehensive reviews specifically focusing on prompt engineering in the medical field. This review will introduce the latest advances in prompt engineering in the field of natural language processing for the medical field. First, we will provide the development of prompt engineering and emphasize its significant contributions to healthcare natural language processing applications such as question-answering systems, text summarization, and machine translation. With the continuous improvement of general large language models, the importance of prompt engineering in the healthcare domain is becoming increasingly prominent. The aim of this article is to provide useful resources and bridges for healthcare natural language processing researchers to better explore the application of prompt engineering in this field. We hope that this review can provide new ideas and inspire for research and application in medical natural language processing.
Bibliometric and Scientometric analyses offer invaluable perspectives on the complex research terrain and collaborative dynamics spanning diverse academic disciplines. This paper presents pyBibX, a python library devised to conduct comprehensive bibliometric and scientometric analyses on raw data files sourced from Scopus, Web of Science, and PubMed, seamlessly integrating state of the art AI capabilities into its core functionality. The library executes a comprehensive EDA, presenting outcomes via visually appealing graphical illustrations. Network capabilities have been deftly integrated, encompassing Citation, Collaboration, and Similarity Analysis. Furthermore, the library incorporates AI capabilities, including Embedding vectors, Topic Modeling, Text Summarization, and other general Natural Language Processing tasks, employing models such as Sentence-BERT, BerTopic, BERT, chatGPT, and PEGASUS. As a demonstration, we have analyzed 184 documents associated with multiple-criteria decision analysis published between 1984 and 2023. The EDA emphasized a growing fascination with decision-making and fuzzy logic methodologies. Next, Network Analysis further accentuated the significance of central authors and intra-continental collaboration, identifying Canada and China as crucial collaboration hubs. Finally, AI Analysis distinguished two primary topics and chatGPT preeminence in Text Summarization. It also proved to be an indispensable instrument for interpreting results, as our library enables researchers to pose inquiries to chatGPT regarding bibliometric outcomes. Even so, data homogeneity remains a daunting challenge due to database inconsistencies. PyBibX is the first application integrating cutting-edge AI capabilities for analyzing scientific publications, enabling researchers to examine and interpret these outcomes more effectively.
ChatGPT is an AI language model developed by OpenAI that can understand and generate human-like text. It can be used for a variety of use cases such as language generation, question answering, text summarization, chatbot development, language translation, sentiment analysis, content creation, personalization, text completion, and storytelling. While ChatGPT has garnered significant positive attention, it has also generated a sense of apprehension and uncertainty in academic circles. There is concern that students may leverage ChatGPT to complete take-home assignments and exams and obtain favorable grades without genuinely acquiring knowledge. This paper adopts a quantitative approach to demonstrate ChatGPT's high degree of unreliability in answering a diverse range of questions pertaining to topics in undergraduate computer science. Our analysis shows that students may risk self-sabotage by blindly depending on ChatGPT to complete assignments and exams. We build upon this analysis to provide constructive recommendations to both students and instructors.
Search engines are vulnerable to attacks against indexing and searching via text encoding manipulation. By imperceptibly perturbing text using uncommon encoded representations, adversaries can control results across search engines for specific search queries. We demonstrate that this attack is successful against two major commercial search engines - Google and Bing - and one open source search engine - Elasticsearch. We further demonstrate that this attack is successful against LLM chat search including Bing's GPT-4 chatbot and Google's Bard chatbot. We also present a variant of the attack targeting text summarization and plagiarism detection models, two ML tasks closely tied to search. We provide a set of defenses against these techniques and warn that adversaries can leverage these attacks to launch disinformation campaigns against unsuspecting users, motivating the need for search engine maintainers to patch deployed systems.
Text summarization is essential for information aggregation and demands large amounts of training data. However, concerns about data privacy and security limit data collection and model training. To eliminate this concern, we propose a federated learning text summarization scheme, which allows users to share the global model in a cooperative learning manner without sharing raw data. Personalized federated learning (PFL) balances personalization and generalization in the process of optimizing the global model, to guide the training of local models. However, multiple local data have different distributions of semantics and context, which may cause the local model to learn deviated semantic and context information. In this paper, we propose FedSUMM, a dynamic gradient adapter to provide more appropriate local parameters for local model. Simultaneously, FedSUMM uses differential privacy to prevent parameter leakage during distributed training. Experimental evidence verifies FedSUMM can achieve faster model convergence on PFL algorithm for task-specific text summarization, and the method achieves superior performance for different optimization metrics for text summarization.
The exponential growth of biomedical texts such as biomedical literature and electronic health records (EHRs), poses a significant challenge for clinicians and researchers to access clinical information efficiently. To tackle this challenge, biomedical text summarization (BTS) has been proposed as a solution to support clinical information retrieval and management. BTS aims at generating concise summaries that distill key information from single or multiple biomedical documents. In recent years, the rapid advancement of fundamental natural language processing (NLP) techniques, from pre-trained language models (PLMs) to large language models (LLMs), has greatly facilitated the progress of BTS. This growth has led to numerous proposed summarization methods, datasets, and evaluation metrics, raising the need for a comprehensive and up-to-date survey for BTS. In this paper, we present a systematic review of recent advancements in BTS, leveraging cutting-edge NLP techniques from PLMs to LLMs, to help understand the latest progress, challenges, and future directions. We begin by introducing the foundational concepts of BTS, PLMs and LLMs, followed by an in-depth review of available datasets, recent approaches, and evaluation metrics in BTS. We finally discuss existing challenges and promising future directions in the era of LLMs. To facilitate the research community, we line up open resources including available datasets, recent approaches, codes, evaluation metrics, and the leaderboard in a public project: https://github.com/KenZLuo/Biomedical-Text-Summarization-Survey/tree/master. We believe that this survey will be a useful resource to researchers, allowing them to quickly track recent advancements and provide guidelines for future BTS research within the research community.
Large Language Models (LLM) are a new class of computation engines, "programmed" via prompt engineering. We are still learning how to best "program" these LLMs to help developers. We start with the intuition that developers tend to consciously and unconsciously have a collection of semantics facts in mind when working on coding tasks. Mostly these are shallow, simple facts arising from a quick read. For a function, examples of facts might include parameter and local variable names, return expressions, simple pre- and post-conditions, and basic control and data flow, etc. One might assume that the powerful multi-layer architecture of transformer-style LLMs makes them inherently capable of doing this simple level of "code analysis" and extracting such information, implicitly, while processing code: but are they, really? If they aren't, could explicitly adding this information help? Our goal here is to investigate this question, using the code summarization task and evaluate whether automatically augmenting an LLM's prompt with semantic facts explicitly, actually helps. Prior work shows that LLM performance on code summarization benefits from few-shot samples drawn either from the same-project or from examples found via information retrieval methods (such as BM25). While summarization performance has steadily increased since the early days, there is still room for improvement: LLM performance on code summarization still lags its performance on natural-language tasks like translation and text summarization. We find that adding semantic facts actually does help! This approach improves performance in several different settings suggested by prior work, including for two different Large Language Models. In most cases, improvement nears or exceeds 2 BLEU; for the PHP language in the challenging CodeSearchNet dataset, this augmentation actually yields performance surpassing 30 BLEU.
GPT-3 and several other language models (LMs) can effectively address various natural language processing (NLP) tasks, including machine translation and text summarization. Recently, they have also been successfully employed in the business process management (BPM) domain, e.g., for predictive process monitoring and process extraction from text. This, however, typically requires fine-tuning the employed LM, which, among others, necessitates large amounts of suitable training data. A possible solution to this problem is the use of prompt engineering, which leverages pre-trained LMs without fine-tuning them. Recognizing this, we argue that prompt engineering can help bring the capabilities of LMs to BPM research. We use this position paper to develop a research agenda for the use of prompt engineering for BPM research by identifying the associated potentials and challenges.
The core challenge in numerous real-world applications is to match an inquiry to the best document from a mutable and finite set of candidates. Existing industry solutions, especially latency-constrained services, often rely on similarity algorithms that sacrifice quality for speed. In this paper we introduce a generic semantic learning-to-rank framework, Self-training Semantic Cross-attention Ranking (sRank). This transformer-based framework uses linear pairwise loss with mutable training batch sizes and achieves quality gains and high efficiency, and has been applied effectively to show gains on two industry tasks at Microsoft over real-world large-scale data sets: Smart Reply (SR) and Ambient Clinical Intelligence (ACI). In Smart Reply, sRank assists live customers with technical support by selecting the best reply from predefined solutions based on consumer and support agent messages. It achieves 11.7% gain in offline top-one accuracy on the SR task over the previous system, and has enabled 38.7% time reduction in composing messages in telemetry recorded since its general release in January 2021. In the ACI task, sRank selects relevant historical physician templates that serve as guidance for a text summarization model to generate higher quality medical notes. It achieves 35.5% top-one accuracy gain, along with 46% relative ROUGE-L gain in generated medical notes.
Extractive summarization is a crucial task in natural language processing that aims to condense long documents into shorter versions by directly extracting sentences. The recent introduction of large language models has attracted significant interest in the NLP community due to its remarkable performance on a wide range of downstream tasks. This paper first presents a thorough evaluation of ChatGPT's performance on extractive summarization and compares it with traditional fine-tuning methods on various benchmark datasets. Our experimental analysis reveals that ChatGPT exhibits inferior extractive summarization performance in terms of ROUGE scores compared to existing supervised systems, while achieving higher performance based on LLM-based evaluation metrics. In addition, we explore the effectiveness of in-context learning and chain-of-thought reasoning for enhancing its performance. Furthermore, we find that applying an extract-then-generate pipeline with ChatGPT yields significant performance improvements over abstractive baselines in terms of summary faithfulness. These observations highlight potential directions for enhancing ChatGPT's capabilities in faithful summarization using two-stage approaches.
Human experts write summaries using different techniques, including extracting a sentence from the document and rewriting it, or fusing various information from the document to abstract it. These techniques are flexible and thus difficult to be imitated by any single method. To address this issue, we propose an adaptive model, GEMINI, that integrates a rewriter and a generator to mimic the sentence rewriting and abstracting techniques, respectively. GEMINI adaptively chooses to rewrite a specific document sentence or generate a summary sentence from scratch. Experiments demonstrate that our adaptive approach outperforms the pure abstractive and rewriting baselines on three benchmark datasets, achieving the best results on WikiHow. Interestingly, empirical results show that the human summary styles of summary sentences are consistently predictable given their context. We release our code and model at \url{https://github.com/baoguangsheng/gemini}.
Evaluating text summarization is a challenging problem, and existing evaluation metrics are far from satisfactory. In this study, we explored ChatGPT's ability to perform human-like summarization evaluation using four human evaluation methods on five datasets. We found that ChatGPT was able to complete annotations relatively smoothly using Likert scale scoring, pairwise comparison, Pyramid, and binary factuality evaluation. Additionally, it outperformed commonly used automatic evaluation metrics on some datasets. Furthermore, we discussed the impact of different prompts, compared its performance with that of human evaluation, and analyzed the generated explanations and invalid responses.
In this work, we develop language models for the Sanskrit language, namely Bidirectional Encoder Representations from Transformers (BERT) and its variants: A Lite BERT (ALBERT), and Robustly Optimized BERT (RoBERTa) using Devanagari Sanskrit text corpus. Then we extracted the features for the given text from these models. We applied the dimensional reduction and clustering techniques on the features to generate an extractive summary for a given Sanskrit document. Along with the extractive text summarization techniques, we have also created and released a Sanskrit Devanagari text corpus publicly.
Document similarity is an important part of Natural Language Processing and is most commonly used for plagiarism-detection and text summarization. Thus, finding the overall most effective document similarity algorithm could have a major positive impact on the field of Natural Language Processing. This report sets out to examine the numerous document similarity algorithms, and determine which ones are the most useful. It addresses the most effective document similarity algorithm by categorizing them into 3 types of document similarity algorithms: statistical algorithms, neural networks, and corpus/knowledge-based algorithms. The most effective algorithms in each category are also compared in our work using a series of benchmark datasets and evaluations that test every possible area that each algorithm could be used in.