In related work section of a scientific paper, authors collect relevant citations and structure them into coherent paragraphs that follow a logical order. Previous studies have addressed citation recommendation and related work section generation in settings where both the citations and their order are provided in advance. However, they have not adequately addressed the optimal ordering of these citations, which is a critical step for achieving fully automated related work section generation. In this study, we propose a new task, citation arrangement, which focuses on determining the optimal order of cited papers to enable fully automated related work section generation. Our approach decomposes citation arrangement into three tasks: citation clustering, paragraph ordering, and citation ordering within a paragraph. For each task, we propose a method that uses a large language model (LLM) in combination with a graph-based technique to comprehensively consider the context of each paper and the relationships among all cited papers. The experimental results show that our method is more effective than methods that generate outputs for each task using only an LLM.

In recent years, neural machine translation (NMT) has become widely used in everyday life. However, the current NMT lacks a mechanism to adjust the difficulty level of translations to match the user’s language level. Additionally, due to the bias in the training data for NMT, translations of simple source sentences are often produced with complex words. In particular, this could pose a problem for children, who may not be able to understand the meaning of the translations correctly. In this study, we propose a method that replaces high Age of Acquisitions (AoA) words in translations with simpler words to match the translations to the user’s level. We achieve this by using large language models (LLMs), providing a triple of a source sentence, a translation, and a target word to be replaced. We create a benchmark dataset using back-translation on Simple English Wikipedia. The experimental results obtained from the dataset show that our method effectively replaces high-AoA words with lower-AoA words and, moreover, can iteratively replace most of the high-AoA words while still maintaining high BLEU and COMET scores.

It has been known to be difficult to generate adequate sports updates from a sequence of vast amounts of diverse live tweets, although the live sports viewing experience with tweets is gaining the popularity. In this paper, we focus on soccer matches and work on building a system to generate live updates for soccer matches from tweets so that users can instantly grasp a match’s progress and enjoy the excitement of the match from raw tweets. Our proposed system is based on a large pre-trained language model and incorporates a mechanism to control the number of updates and a mechanism to reduce the redundancy of duplicate and similar updates.