More Like this

1. Automated Mining of Structured Knowledge from Text in the Era of Large Language Models

   https://doi.org/10.1145/3637528.3671469  

   Zhang, Yunyi; Zhong, Ming; Ouyang, Siru; Jiao, Yizhu; Zhou, Sizhe; Ding, Linyi; Han, Jiawei (August 2024, ACM)

   Baeza-Yates, Ricardo; Bonchi, Francesco (Ed.)

   Massive amount of unstructured text data are generated daily, ranging from news articles to scientific papers. How to mine structured knowledge from the text data remains a crucial research question. Recently, large language models (LLMs) have shed light on the text mining field with their superior text understanding and instructionfollowing ability. There are typically two ways of utilizing LLMs: fine-tune the LLMs with human-annotated training data, which is labor intensive and hard to scale; prompt the LLMs in a zero-shot or few-shot way, which cannot take advantage of the useful information in the massive text data. Therefore, it remains a challenge on automated mining of structured knowledge from massive text data in the era of large language models. In this tutorial, we cover the recent advancements in mining structured knowledge using language models with very weak supervision. We will introduce the following topics in this tutorial: (1) introduction to large language models, which serves as the foundation for recent text mining tasks, (2) ontology construction, which automatically enriches an ontology from a massive corpus, (3) weakly-supervised text classification in flat and hierarchical label space, (4) weakly-supervised information extraction, which extracts entity and relation structures. 

   more » « less
2. From Text to Emotion: Unveiling the Emotion Annotation Capabilities of LLMs

   Niu, Minxue; Jaiswal, Mimansa; Mower_Provost, Emily (September 2024, Interspeech)

   Training emotion recognition models has relied heavily on human annotated data, which present diversity, quality, and cost challenges. In this paper, we explore the potential of Large Language Models (LLMs), specifically GPT-4, in automating or assisting emotion annotation. We compare GPT-4 with supervised models and/or humans in three aspects: agreement with human annotations, alignment with human perception, and impact on model training. We find that common metrics that use aggregated human annotations as ground truth can underestimate GPT-4's performance, and our human evaluation experiment reveals a consistent preference for GPT-4 annotations over humans across multiple datasets and evaluators. Further, we investigate the impact of using GPT-4 as an annotation filtering process to improve model training. Together, our findings highlight the great potential of LLMs in emotion annotation tasks and underscore the need for refined evaluation methodologies. 

   more » « less
3. Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations

   Ki, Dayeon; Carpuat, Marine; Duh, Kevin; Gomez, Helena; Bethard, Steven (June 2024, Association for Computational Linguistics)

   Machine Translation (MT) remains one of the last NLP tasks where large language models (LLMs) have not yet replaced dedicated supervised systems. This work exploits the complementary strengths of LLMs and supervised MT by guiding LLMs to automatically post-edit MT with external feedback on its quality, derived from Multidimensional Quality Metric (MQM) annotations. Working with LLaMA-2 models, we consider prompting strategies varying the nature of feedback provided and then fine-tune the LLM to improve its ability to exploit the provided guidance. Through experiments on Chinese-English, English-German, and English-Russian MQM data, we demonstrate that prompting LLMs to post-edit MT improves TER, BLEU and COMET scores, although the benefits of fine-grained feedback are not clear. Fine-tuning helps integrate fine-grained feedback more effectively and further improves translation quality based on both automatic and human evaluation. 

   more » « less
4. Beyond Raw Bytes: Towards Large Malware Language Models

   Kurlandski, Luke; Berger, Harel; Pan, Yin; Wright, Matthew (February 2026, NDSS 2026)

   Malware poses an increasing threat to critical computing infrastructure, driving demand for more advanced detection and analysis methods. Although raw-binary malware classifiers show promise, they are limited in their capabilities and struggle with the challenges of modeling long sequences. Meanwhile, the rise of large language models (LLMs) in natural language processing showcases the power of massive, self-supervised models trained on heterogeneous datasets, offering flexible representations for numerous downstream tasks. The success behind these models is rooted in the size and quality of their training data, the expressiveness and scalability of their neural architecture, and their ability to learn from unlabeled data in a self-supervised manner. In this work, we take the first steps toward developing large malware language models (LMLMs), the malware analog to LLMs. We tackle the core aspects of this objective, namely, questions about data, models, pretraining, and finetuning. By pretraining a malware classification model with language modeling objectives, we were able to improve downstream performance on diverse practical malware classification tasks on average by 1.1% and up to 28.6%, indicating that these models could serve to succeed raw-binary malware classifiers. 

   more » « less
5. Can we teach language models to gloss endangered languages?

   https://doi.org/10.18653/v1/2024.findings-emnlp.337  

   Ginn, Michael; Hulden, Mans; Palmer, Alexis (November 2024, Association for Computational Linguistics)

   Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text would be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research has explored a number of statistical and neural methods for automatically producing IGT. As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages, it is natural to wonder whether they can be utilized for the task of generating IGT. We explore whether LLMs can be effective at the task of interlinear glossing with in-context learning, without any traditional training. We propose new approaches for selecting examples to provide in-context, observing that targeted selection can significantly improve performance. We find that LLM-based methods beat standard transformer baselines, despite requiring no training at all. These approaches still underperform state-of-the-art supervised systems for the task, but are highly practical for researchers outside of the NLP community, requiring minimal effort to use. 

   more » « less