While sentence simplification is an active research topic in NLP, its adjacent tasks of sentence complexification and same-level paraphrasing are not. To train models on all three tasks, we present two new unsupervised datasets. We compare these datasets, one labeled by a weak classifier and the other by a rule-based approach, with a single supervised dataset. Using these three datasets for training, we perform extensive experiments on both multitasking and prompting strategies. Compared to other systems trained on unsupervised parallel data, models trained on our weak classifier labeled dataset achieve state-of-the-art performance on the ASSET simplification benchmark. Our models also outperform previous work on sentence level targeting. Finally, we establish how a handful of Large Language Models perform on these tasks under a zero-shot setting.

The law is typically a natural-language-based domain, and natural-language texts are pervasive in the law. First, natural language is the medium that legislation (including administrative regulations of all kinds) uses to express legal prescriptions, which humans (both experts and laypeople) are assumed to understand and comply with. Legislative and regulatory bodies have produced complex and evolving networks of natural language texts, which have complex structures and interconnections and use diverse terminologies to express technical and non-technical content. Second, natural language is used in judicial proceedings and opinions. In a proceeding, the parties to a legal case rely on natural language to express their arguments, motions, and claims, as do witnesses in their testimonies.

This work studies a challenging yet more realistic setting for zero-shot cross-task generalization: demonstration-free learning from textual instructions, presuming the existence of a paragraph-style task definition while no demonstrations exist. To better learn the task supervision from the definition, we propose two strategies: first, to automatically find out the critical sentences in the definition; second, a ranking objective to force the model to generate the gold outputs with higher probabilities when those critical parts are highlighted in the definition. The joint efforts of the two strategies yield state-of-the-art performance on the challenging benchmark. Our code will be released in the final version of the paper.

EduChat (https://www.educhat.top/) is a large-scale language model (LLM)-based chatbot system in the education domain. Its goal is to support personalized, fair, and compassionate intelligent education, serving teachers, students, and parents. Guided by theories from psychology and education, it further strengthens educational functions such as open question answering, essay assessment, Socratic teaching, and emotional support based on the existing basic LLMs. Particularly, we learn domain-specific knowledge by pre-training on the educational corpus and stimulate various skills with tool use by fine-tuning on designed system prompts and instructions. Currently, EduChat is available online as an open-source project, with its code, data, and model parameters available on platforms (e.g., GitHub https://github.com/icalk-nlp/EduChat, Hugging Face https://huggingface.co/ecnu-icalk ). We also prepare a demonstration of its capabilities online (https://vimeo.com/851004454). This initiative aims to promote research and applications of LLMs for intelligent education.

Automatic fake news detection with machine learning can prevent the dissemination of false statements before they gain many views. Several datasets labeling statements as legitimate or false have been created since the 2016 United States presidential election for the prospect of training machine learning models. We evaluate the robustness of both traditional and deep state-of-the-art models to gauge how well they may perform in the real world. We find that traditional models tend to generalize better to data outside the distribution it was trained on compared to more recently-developed large language models, though the best model to use may depend on the specific task at hand.

The recent advances in large language models (LLM) and foundation models with emergent capabilities have been shown to improve the performance of many NLP tasks. LLMs and Knowledge Graphs (KG) can complement each other such that LLMs can be used for KG construction or completion while existing KGs can be used for different tasks such as making LLM outputs explainable or fact-checking in Neuro-Symbolic manner. In this paper, we present Text2KGBench, a benchmark to evaluate the capabilities of language models to generate KGs from natural language text guided by an ontology. Given an input ontology and a set of sentences, the task is to extract facts from the text while complying with the given ontology (concepts, relations, domain/range constraints) and being faithful to the input sentences. We provide two datasets (i) Wikidata-TekGen with 10 ontologies and 13,474 sentences and (ii) DBpedia-WebNLG with 19 ontologies and 4,860 sentences. We define seven evaluation metrics to measure fact extraction performance, ontology conformance, and hallucinations by LLMs. Furthermore, we provide results for two baseline models, Vicuna-13B and Alpaca-LoRA-13B using automatic prompt generation from test cases. The baseline results show that there is room for improvement using both Semantic Web and Natural Language Processing techniques.

Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences. This is a computational challenge as presented by the practice of sequence generation problems, such as machine translation, where we often deal with a large action space (\textit{e.g.,} a vocabulary) and a long action sequence (\textit{e.g.,} a translation). In this work, we introduce two-stage sampling and dynamic sampling approaches to improve the sampling efficiency during training sequence generation models via RL. We experiment with our approaches on the traditional sequence generation tasks, including machine translation and abstractive summarization. Furthermore, we evaluate our approaches in RL from human feedback (RLHF) through training a large language model using the reward model. Experimental results show that the efficient sampling-based RL, referred to as ESRL, can outperform all baselines in terms of both training efficiency and memory consumption. Notably, ESRL yields consistent performance gains over the strong REINFORCE, minimum risk training, and proximal policy optimization methods.

This survey focuses in encoder Language Models for solving tasks in the clinical domain in the Spanish language. We review the contributions of 17 corpora focused mainly in clinical tasks, then list the most relevant Spanish Language Models and Spanish Clinical Language models. We perform a thorough comparison of these models by benchmarking them over a curated subset of the available corpora, in order to find the best-performing ones; in total more than 3000 models were fine-tuned for this study. All the tested corpora and the best models are made publically available in an accessible way, so that the results can be reproduced by independent teams or challenged in the future when new Spanish Clinical Language models are created.

Unsupervised Domain Adaptation (UDA) is a popular technique that aims to reduce the domain shift between two data distributions. It was successfully applied in computer vision and natural language processing. In the current work, we explore the effects of various unsupervised domain adaptation techniques between two text classification tasks: fake and hyperpartisan news detection. We investigate the knowledge transfer from fake to hyperpartisan news detection without involving target labels during training. Thus, we evaluate UDA, cluster alignment with a teacher, and cross-domain contrastive learning. Extensive experiments show that these techniques improve performance, while including data augmentation further enhances the results. In addition, we combine clustering and topic modeling algorithms with UDA, resulting in improved performances compared to the initial UDA setup.

Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than merely responding to queries from human users. Most existing language agents, however, are not optimized using environment-specific rewards. Although some agents enable iterative refinement through verbal feedback, they do not reason and plan in ways that are compatible with gradient-based learning from rewards. This paper introduces a principled framework for reinforcing large language agents by learning a retrospective model, which automatically tunes the language agent prompts from environment feedback through policy gradient. Specifically, our proposed agent architecture learns from rewards across multiple environments and tasks, for fine-tuning a pre-trained language model which refines the language agent prompt by summarizing the root cause of prior failed attempts and proposing action plans. Experimental results on various tasks demonstrate that the language agents improve over time and that our approach considerably outperforms baselines that do not properly leverage gradients from the environment. This demonstrates that using policy gradient optimization to improve language agents, for which we believe our work is one of the first, seems promising and can be applied to optimize other models in the agent architecture to enhance agent performances over time.