Large language models (LLMs) benefit greatly from prompt engineering, with in-context learning standing as a pivital technique. While former approaches have provided various ways to construct the demonstrations used for in-context learning, they often ignore the inherent heterogeneity within datasets, applying the same demonstrations to all reasoning questions. We observed that the effectiveness of demonstrations varies depending on the specific question. This motivates our exploration of using prompt engineering to select appropriate demonstrations. To address the challenge of automatically creating and choosing demonstrations tailored to each question, we propose a novel prompt engineering workflow built around a novel object called the "demonstration notebook." This notebook helps identify the most suitable in-context learning example for a question by gathering and reusing information from the LLM's past interactions. Our experiments show that this approach outperforms all existing methods for automatic demonstration construction and selection (as far as we know), achieving state-of-the-art results on serveral reasoning benchmarks. The method's versatility is further demonstrated by its success in text summarization and prompt compression tasks. Additionally, we contribute a rigorous analysis method to reveal the "demonstrative regime" of a demonstration, providing valuable insights into how demonstrations relate to different question types within a dataset.
Many tasks within NLP can be framed as sequential decision problems, ranging from sequence tagging to text generation. However, for many tasks, the standard training methods, including maximum likelihood (teacher forcing) and scheduled sampling, suffer from exposure bias and a mismatch between metrics employed during training and inference. DAgger provides a solution to mitigate these problems, yet it requires a metric-specific dynamic oracle algorithm, which does not exist for many common metrics like span-based F1, ROUGE, and BLEU. In this paper, we develop these novel dynamic oracles and show they maintain DAgger's no-regret guarantee for decomposable metrics like span-based F1. We evaluate the algorithm's performance on named entity recognition (NER), text summarization, and machine translation (MT). While DAgger with dynamic oracle yields less favorable results in our MT experiments, it outperforms the baseline techniques in NER and text summarization.
Recently, with the rapid development in the fields of technology and the increasing amount of text t available on the internet, it has become urgent to develop effective tools for processing and understanding texts in a way that summaries the content without losing the fundamental essence of the information. Given this challenge, we have developed an advanced text summarization system targeting Arabic textbooks. Relying on modern natu-ral language processing models such as MT5, AraBART, AraT5, and mBART50, this system evaluates and extracts the most important sentences found in biology textbooks for the 11th and 12th grades in the Palestinian curriculum, which enables students and teachers to obtain accurate and useful summaries that help them easily understand the content. We utilized the Rouge metric to evaluate the performance of the trained models. Moreover, experts in education Edu textbook authoring assess the output of the trained models. This approach aims to identify the best solutions and clarify areas needing improvement. This research provides a solution for summarizing Arabic text. It enriches the field by offering results that can open new horizons for research and development in the technologies for understanding and generating the Arabic language. Additionally, it contributes to the field with Arabic texts through creating and compiling schoolbook texts and building a dataset.
Large language models (LLMs) have shown impressive capabilities in tasks such as machine translation, text summarization, question answering, and solving complex mathematical problems. However, their primary training on data-rich languages like English limits their performance in low-resource languages. This study addresses this gap by focusing on the Indexical Shift problem in Turkish. The Indexical Shift problem involves resolving pronouns in indexical shift contexts, a grammatical challenge not present in high-resource languages like English. We present the first study examining indexical shift in any language, releasing a Turkish dataset specifically designed for this purpose. Our Indexical Shift Dataset consists of 156 multiple-choice questions, each annotated with necessary linguistic details, to evaluate LLMs in a few-shot setting. We evaluate recent multilingual LLMs, including GPT-4, GPT-3.5, Cohere-AYA, Trendyol-LLM, and Turkcell-LLM, using this dataset. Our analysis reveals that even advanced models like GPT-4 struggle with the grammatical nuances of indexical shift in Turkish, achieving only moderate performance. These findings underscore the need for focused research on the grammatical challenges posed by low-resource languages. We released the dataset and code \href{https://anonymous.4open.science/r/indexical_shift_llm-E1B4} {here}.
Remarkable advances in large language models (LLMs) have enabled high-quality text summarization. However, this capability is currently accessible only through LLMs of substantial size or proprietary LLMs with usage fees. In response, smaller-scale LLMs (sLLMs) of easy accessibility and low costs have been extensively studied, yet they often suffer from missing key information and entities, i.e., low relevance, in particular, when input documents are long. We hence propose a key-element-informed instruction tuning for summarization, so-called KEITSum, which identifies key elements in documents and instructs sLLM to generate summaries capturing these key elements. Experimental results on dialogue and news datasets demonstrate that sLLM with KEITSum indeed provides high-quality summarization with higher relevance and less hallucinations, competitive to proprietary LLM.
While large language models (LLMs) excel in various natural language tasks in English, their performance in lower-resourced languages like Hebrew, especially for generative tasks such as abstractive summarization, remains unclear. The high morphological richness in Hebrew adds further challenges due to the ambiguity in sentence comprehension and the complexities in meaning construction. In this paper, we address this resource and evaluation gap by introducing HeSum, a novel benchmark specifically designed for abstractive text summarization in Modern Hebrew. HeSum consists of 10,000 article-summary pairs sourced from Hebrew news websites written by professionals. Linguistic analysis confirms HeSum's high abstractness and unique morphological challenges. We show that HeSum presents distinct difficulties for contemporary state-of-the-art LLMs, establishing it as a valuable testbed for generative language technology in Hebrew, and MRLs generative challenges in general.
Proprietary Large Language Models (LLMs) such as GPT-4 and Gemini have demonstrated promising capabilities in clinical text summarization tasks. However, due to patient data privacy concerns and computational costs, many healthcare providers prefer using small, locally-hosted models over external generic LLMs. This study presents a comprehensive domain- and task-specific adaptation process for the open-source LLaMA-2 13 billion parameter model, enabling it to generate high-quality clinical notes from outpatient patient-doctor dialogues. Our process incorporates continued pre-training, supervised fine-tuning, and reinforcement learning from both AI and human feedback. We introduced a new approach, DistillDirect, for performing on-policy reinforcement learning with Gemini 1.0 Pro as the teacher model. Our resulting model, LLaMA-Clinic, can generate clinical notes comparable in quality to those authored by physicians. In a blinded physician reader study, the majority (90.4%) of individual evaluations rated the notes generated by LLaMA-Clinic as "acceptable" or higher across all three criteria: real-world readiness, completeness, and accuracy. In the more challenging "Assessment and Plan" section, LLaMA-Clinic scored higher (4.2/5) in real-world readiness than physician-authored notes (4.1/5). We highlight key considerations for future clinical note-generation tasks, emphasizing the importance of pre-defining a best-practice note format, rather than relying on LLMs to determine this for clinical practice.
Large language models (LLMs) have demonstrated the capacity to improve summary quality by mirroring a human-like iterative process of critique and refinement starting from the initial draft. Two strategies are designed to perform this iterative process: Prompt Chaining and Stepwise Prompt. Prompt chaining orchestrates the drafting, critiquing, and refining phases through a series of three discrete prompts, while Stepwise prompt integrates these phases within a single prompt. However, the relative effectiveness of the two methods has not been extensively studied. This paper is dedicated to examining and comparing these two methods in the context of text summarization to ascertain which method stands out as the most effective. Experimental results show that the prompt chaining method can produce a more favorable outcome. This might be because stepwise prompt might produce a simulated refinement process according to our various experiments. Since refinement is adaptable to diverse tasks, our conclusions have the potential to be extrapolated to other applications, thereby offering insights that may contribute to the broader development of LLMs.
Data derived from the realm of the social sciences is often produced in digital text form, which motivates its use as a source for natural language processing methods. Researchers and practitioners have developed and relied on artificial intelligence techniques to collect, process, and analyze documents in the legal field, especially for tasks such as text summarization and classification. While increasing procedural efficiency is often the primary motivation behind natural language processing in the field, several works have proposed solutions for human rights-related issues, such as assessment of public policy and institutional social settings. One such issue is the presence of gender biases in court decisions, which has been largely studied in social sciences fields; biased institutional responses to gender-based violence are a violation of international human rights dispositions since they prevent gender minorities from accessing rights and hamper their dignity. Natural language processing-based approaches can help detect these biases on a larger scale. Still, the development and use of such tools require researchers and practitioners to be mindful of legal and ethical aspects concerning data sharing and use, reproducibility, domain expertise, and value-charged choices. In this work, we (a) present an experimental framework developed to automatically detect gender biases in court decisions issued in Brazilian Portuguese and (b) describe and elaborate on features we identify to be critical in such a technology, given its proposed use as a support tool for research and assessment of court~activity.
The evaluation of summary quality encompasses diverse dimensions such as consistency, coherence, relevance, and fluency. However, existing summarization methods often target a specific dimension, facing challenges in generating well-balanced summaries across multiple dimensions. In this paper, we propose multi-objective reinforcement learning tailored to generate balanced summaries across all four dimensions. We introduce two multi-dimensional optimization (MDO) strategies for adaptive learning: 1) MDO_min, rewarding the current lowest dimension score, and 2) MDO_pro, optimizing multiple dimensions similar to multi-task learning, resolves conflicting gradients across dimensions through gradient projection. Unlike prior ROUGE-based rewards relying on reference summaries, we use a QA-based reward model that aligns with human preferences. Further, we discover the capability to regulate the length of summaries by adjusting the discount factor, seeking the generation of concise yet informative summaries that encapsulate crucial points. Our approach achieved substantial performance gains compared to baseline models on representative summarization datasets, particularly in the overlooked dimensions.
The startling success of ChatGPT and other large language models (LLMs) using transformer-based generative neural network architecture in applications such as natural language processing and image synthesis has many researchers excited about potential opportunities in process systems engineering (PSE). The almost human-like performance of LLMs in these areas is indeed very impressive, surprising, and a major breakthrough. Their capabilities are very useful in certain tasks, such as writing first drafts of documents, code writing assistance, text summarization, etc. However, their success is limited in highly scientific domains as they cannot yet reason, plan, or explain due to their lack of in-depth domain knowledge. This is a problem in domains such as chemical engineering as they are governed by fundamental laws of physics and chemistry (and biology), constitutive relations, and highly technical knowledge about materials, processes, and systems. Although purely data-driven machine learning has its immediate uses, the long-term success of AI in scientific and engineering domains would depend on developing hybrid AI systems that use first principles and technical knowledge effectively. We call these hybrid AI systems Large Knowledge Models (LKMs), as they will not be limited to only NLP-based techniques or NLP-like applications. In this paper, we discuss the challenges and opportunities in developing such systems in chemical engineering.
Large Language Models (LLMs) are gaining popularity as tools for reading and summarization aids. However, little is known about their potential benefits when integrated with mixed reality (MR) interfaces to support everyday reading assistants. We developed RealitySummary, an MR reading assistant that seamlessly integrates LLMs with always-on camera access, OCR-based text extraction, and augmented spatial and visual responses in MR interfaces. Developed iteratively, RealitySummary evolved across three versions, each shaped by user feedback and reflective analysis: 1) a preliminary user study to understand user perceptions (N=12), 2) an in-the-wild deployment to explore real-world usage (N=11), and 3) a diary study to capture insights from real-world work contexts (N=5). Our findings highlight the unique advantages of combining AI and MR, including an always-on implicit assistant, minimal context switching, and spatial affordances, demonstrating significant potential for future LLM-MR interfaces beyond traditional screen-based interactions.
Reinforcement learning from human feedback (RLHF) has demonstrated great promise in aligning large language models (LLMs) with human preference. Depending on the availability of preference data, both online and offline RLHF are active areas of investigation. A key bottleneck is understanding how to incorporate uncertainty estimation in the reward function learned from the preference data for RLHF, regardless of how the preference data is collected. While the principles of optimism or pessimism under uncertainty are well-established in standard reinforcement learning (RL), a practically-implementable and theoretically-grounded form amenable to large language models is not yet available, as standard techniques for constructing confidence intervals become intractable under arbitrary policy parameterizations. In this paper, we introduce a unified approach to online and offline RLHF -- value-incentivized preference optimization (VPO) -- which regularizes the maximum-likelihood estimate of the reward function with the corresponding value function, modulated by a $\textit{sign}$ to indicate whether the optimism or pessimism is chosen. VPO also directly optimizes the policy with implicit reward modeling, and therefore shares a simpler RLHF pipeline similar to direct preference optimization. Theoretical guarantees of VPO are provided for both online and offline settings, matching the rates of their standard RL counterparts. Moreover, experiments on text summarization and dialog verify the practicality and effectiveness of VPO.
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant memories from an external database. However, existing RAG methods typically organize all memories in a whole database, potentially limiting focus on crucial memories and introducing noise. In this paper, we introduce a multiple partition paradigm for RAG (called M-RAG), where each database partition serves as a basic unit for RAG execution. Based on this paradigm, we propose a novel framework that leverages LLMs with Multi-Agent Reinforcement Learning to optimize different language generation tasks explicitly. Through comprehensive experiments conducted on seven datasets, spanning three language generation tasks and involving three distinct language model architectures, we confirm that M-RAG consistently outperforms various baseline methods, achieving improvements of 11%, 8%, and 12% for text summarization, machine translation, and dialogue generation, respectively.
The extraction of essential news elements through the 5W1H framework (\textit{What}, \textit{When}, \textit{Where}, \textit{Why}, \textit{Who}, and \textit{How}) is critical for event extraction and text summarization. The advent of Large language models (LLMs) such as ChatGPT presents an opportunity to address language-related tasks through simple prompts without fine-tuning models with much time. While ChatGPT has encountered challenges in processing longer news texts and analyzing specific attributes in context, especially answering questions about \textit{What}, \textit{Why}, and \textit{How}. The effectiveness of extraction tasks is notably dependent on high-quality human-annotated datasets. However, the absence of such datasets for the 5W1H extraction increases the difficulty of fine-tuning strategies based on open-source LLMs. To address these limitations, first, we annotate a high-quality 5W1H dataset based on four typical news corpora (\textit{CNN/DailyMail}, \textit{XSum}, \textit{NYT}, \textit{RA-MDS}); second, we design several strategies from zero-shot/few-shot prompting to efficient fine-tuning to conduct 5W1H aspects extraction from the original news documents. The experimental results demonstrate that the performance of the fine-tuned models on our labelled dataset is superior to the performance of ChatGPT. Furthermore, we also explore the domain adaptation capability by testing the source-domain (e.g. NYT) models on the target domain corpus (e.g. CNN/DailyMail) for the task of 5W1H extraction.
FAQ documents are commonly used with text documents and websites to provide important information in the form of question answer pairs to either aid in reading comprehension or provide a shortcut to the key ideas. We suppose that salient sentences from a given document serve as a good proxy fro the answers to an aggregated set of FAQs from readers. We propose a system for generating FAQ documents that extract the salient questions and their corresponding answers from sizeable text documents scraped from the Stanford Encyclopedia of Philosophy. We use existing text summarization, sentence ranking via the Text rank algorithm, and question-generation tools to create an initial set of questions and answers. Finally, we apply some heuristics to filter out invalid questions. We use human evaluation to rate the generated questions on grammar, whether the question is meaningful, and whether the question's answerability is present within a summarized context. On average, participants thought 71 percent of the questions were meaningful.
The paper benchmarks several Transformer models [4], to show how these models can judge sentiment from a news event. This signal can then be used for downstream modelling and signal identification for commodity trading. We find that fine-tuned BERT models outperform fine-tuned or vanilla GPT models on this task. Transformer models have revolutionized the field of natural language processing (NLP) in recent years, achieving state-of-the-art results on various tasks such as machine translation, text summarization, question answering, and natural language generation. Among the most prominent transformer models are Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformer (GPT), which differ in their architectures and objectives. A CopBERT model training data and process overview is provided. The CopBERT model outperforms similar domain specific BERT trained models such as FinBERT. The below confusion matrices show the performance on CopBERT & CopGPT respectively. We see a ~10 percent increase in f1_score when compare CopBERT vs GPT4 and 16 percent increase vs CopGPT. Whilst GPT4 is dominant It highlights the importance of considering alternatives to GPT models for financial engineering tasks, given risks of hallucinations, and challenges with interpretability. We unsurprisingly see the larger LLMs outperform the BERT models, with predictive power. In summary BERT is partially the new XGboost, what it lacks in predictive power it provides with higher levels of interpretability. Concluding that BERT models might not be the next XGboost [2], but represent an interesting alternative for financial engineering tasks, that require a blend of interpretability and accuracy.
Recent efforts have evaluated large language models (LLMs) in areas such as commonsense reasoning, mathematical reasoning, and code generation. However, to the best of our knowledge, no work has specifically investigated the performance of LLMs in natural language generation (NLG) tasks, a pivotal criterion for determining model excellence. Thus, this paper conducts a comprehensive evaluation of well-known and high-performing LLMs, namely ChatGPT, ChatGLM, T5-based models, LLaMA-based models, and Pythia-based models, in the context of NLG tasks. We select English and Chinese datasets encompassing Dialogue Generation and Text Summarization. Moreover, we propose a common evaluation setting that incorporates input templates and post-processing strategies. Our study reports both automatic results, accompanied by a detailed analysis.
In the task of Knowledge Graph Completion (KGC), the existing datasets and their inherent subtasks carry a wealth of shared knowledge that can be utilized to enhance the representation of knowledge triplets and overall performance. However, no current studies specifically address the shared knowledge within KGC. To bridge this gap, we introduce a multi-level Shared Knowledge Guided learning method (SKG) that operates at both the dataset and task levels. On the dataset level, SKG-KGC broadens the original dataset by identifying shared features within entity sets via text summarization. On the task level, for the three typical KGC subtasks - head entity prediction, relation prediction, and tail entity prediction - we present an innovative multi-task learning architecture with dynamically adjusted loss weights. This approach allows the model to focus on more challenging and underperforming tasks, effectively mitigating the imbalance of knowledge sharing among subtasks. Experimental results demonstrate that SKG-KGC outperforms existing text-based methods significantly on three well-known datasets, with the most notable improvement on WN18RR.
The paper discusses the creation of a multimodal dataset of Russian-language scientific papers and testing of existing language models for the task of automatic text summarization. A feature of the dataset is its multimodal data, which includes texts, tables and figures. The paper presents the results of experiments with two language models: Gigachat from SBER and YandexGPT from Yandex. The dataset consists of 420 papers and is publicly available on https://github.com/iis-research-team/summarization-dataset.