Knowledge editing allows for targeted updates of specific factual information in Large Language Models (LLMs). While existing methods can effectively update localized facts, they often struggle to coherently integrate these updates into the model's broader knowledge structure. Multi-hop knowledge editing addresses this issue by aiming that edited information is consistently reflected throughout the multi-hop reasoning process. However, current evaluation methods primarily assess the correctness of the final answer, which cannot guarantee that the edited knowledge has been correctly integrated into the reasoning process. To address these limitations, we propose a novel evaluation framework to systematically examine how edited knowledge is integrated within a multi-hop reasoning process. We introduce three types of entity-level errors: (i) Entity Persistence, where outdated entities remain; (ii) Entity Mismatch, where unrelated entities appear; and (iii) Entity Distortion, where entities are morphologically distorted, such as misspellings or truncations. Our analysis reveals that these errors frequently occur even when the final answer is correct. Moreover, when the final answer is incorrect, Entity Mismatch Errors are commonly observed, indicating unintended side effects of knowledge editing. The code is available at https://github.com/KUNLP/multihop-edit-eval.

Large Language Models (LLMs) acquire extensive factual knowledge from large-scale datasets and demonstrate remarkable performance across various tasks. However, since real-world knowledge is constantly changing, it is necessary to modify or expand the model's knowledge. To achieve this, knowledge editing techniques are employed to correct inaccurate or outdated information and inject new knowledge, thereby ensuring that the model remains current. However, in existing subject-centered editing approaches, repeatedly editing the same subject can lead to knowledge degradation, where previously edited knowledge is forgotten. In this paper, we analyze the causes of this knowledge degradation phenomenon and propose a two-step editing method that independently edits subjects and relations to mitigate this issue. Our method effectively alleviates knowledge degradation compared to existing knowledge editing techniques, achieving average performance improvements of 22.9% in multi-edit scenarios and 7.2% in sequential editing.

Automated essay scoring (AES) is a crucial research area with potential applications in education and beyond. However, recent studies have primarily focused on AES models that evaluate essays within a specific domain or using a holistic score, leaving a gap in research and resources for more generalized models capable of assessing essays with detailed items from multiple perspectives. As evaluating and scoring essays based on complex traits is costly and time-consuming, datasets for such AES evaluations are limited. To address these issues, we developed a cross-prompt trait scoring AES model and proposed a suitable curriculum learning (CL) design. By devising difficulty scores and introducing the key curriculum method, we demonstrated its effectiveness compared to existing CL strategies in natural language understanding tasks.

Document-level relation extraction is a natural language processing task for extracting relations among entities in a document. Compared with sentence-level relation extraction, there are more challenges to document-level relation extraction. To acquire mutual information among entities in a document, recent studies have designed mention-level graphs or improved pretrained language models based on co-occurrence or coreference information. However, these methods cannot utilize the anaphoric information of pronouns, which play an important role in document-level relation extraction. In addition, there is a possibility of losing lexical information of the relations among entities directly expressed in a sentence. To address this issue, we propose two novel graph structures: an anaphoric graph and a local-context graph. The proposed method outperforms the existing graph-based relation extraction method when applying the document-level relation extraction dataset, DocRED.

We propose a kernel-based model to automatically extract social relations such as economic relations and political relations between two people from news articles. To determine whether two people are structurally associated with each other, the proposed model uses an SVM (support vector machine) tree kernel based on trigrams of head-dependent relations between them. In the experiments with the automatic content extraction (ACE) corpus and a Korean news corpus, the proposed model outperformed the previous systems based on SVM tree kernels even though it used more shallow linguistic knowledge.