Papers by Harksoo Kim
Do Large Language Models Have “Emotion Neurons”? Investigating the Existence and Role (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluations of LLMs' emotional capabilities have been criticized for not illuminating how emotion information is processed and represented within an LLM. |
| Approach: | They examine whether there are “emotion neurons” within large language models that selectively process and express certain emotions and what functional role they play. |
| Outcome: | The proposed model is based on the representative emotion theory of the six basic emotions and demonstrates that it is functionally significant to examine whether the prediction accuracy for a specific emotion decreases when the neurons are removed. |
Generation-Based and Emotion-Reflected Memory Update: Creating the KEEM Dataset for Better Long-Term Conversation (2025.coling-main)
Copied to clipboard
| Challenge: | KEEM is a dynamically generated dataset designed to enhance memory updates in long-term conversational systems. |
| Approach: | They propose a dataset that keeps emotional and essential memories and generates integrative memories that incorporate emotional context and causal relationships. |
| Outcome: | The Keep Emotional and Essential Memory (KEEM) dataset enhances memory updates in long-term conversational systems. |
Relation Extraction among Multiple Entities Using a Dual Pointer Network with a Multi-Head Attention Mechanism (D19-66)
Copied to clipboard
| Challenge: | Existing studies on relation extrac-tion focus on finding only one relation between two entities in a single sentence. |
| Approach: | They propose a relation extraction model based on a dual pointer network with a multi-head attention mechanism that finds n-to-1 subject-object relations by using a forward decoder and a backward decode-r. |
| Outcome: | The proposed model achieves the state-of-the-art performance on the ACE-05 and NYT datasets. |
Small Changes, Big Impact: How Manipulating a Few Neurons Can Drastically Alter LLM Aggression (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have led to innovations in various domains such as education, healthcare, and finance, while raising serious concerns that they can be easily misused for malicious purposes. |
| Approach: | They identify specific neurons (“aggression neurons”) closely related to the expression of aggression and analyze how manipulating them affects the model’s overall aggression. |
| Outcome: | The proposed model outputs show that manipulating neurons can increase aggression by up to 33% in all models and even more extreme when they are concentrated in certain layers. |
STEAM: A Semantic-Level Knowledge Editing Framework for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for locate-and-editing focus on token-level likelihood optimization without addressing semantic coherence. |
| Approach: | They propose a semantic-level knowledge editing framework that enhances integration of updated knowledge into the model's knowledge structure. |
| Outcome: | The proposed framework improves integration of updated knowledge into the model's knowledge structure and improves semantic coherence. |
Does the Emotional Understanding of LVLMs Vary Under High-Stress Environments and Across Different Demographic Attributes? (2025.acl-long)
Copied to clipboard
| Challenge: | According to psychological and neuroscientific research, a high-stress environment can restrict attentional resources and intensify negative affect, thereby impairing the ability to understand emotions. |
| Approach: | They constructed a large-vision language model that combines race, gender, and age group and used the Pretend prompt technique to induce LVLMs to interpret others’ emotions. |
| Outcome: | The results suggest that the effects of high-stress and demographic attributes identified in human research may also be reflected in LVLMs. |
Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods for aspect-based sentiment analysis (ABSA) consider relationships implicitly among subtasks at the word level. |
| Approach: | They propose a deep contextualized relation-aware network that allows interactive relations among subtasks . they propose self-supervised strategies that deal with multiple aspects . |
| Outcome: | The proposed method outperforms state-of-the-art methods on three widely used benchmarks. |
Exploring the Impact of Instruction-Tuning on LLM’s Susceptibility to Misinformation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies highlight that large language models are receptive to external information that contradicts their parametric knowledge, but little research has been conducted on the direct impact of instruction-tuning on this phenomenon. |
| Approach: | They examine how instruction-tuning influences LLMs' susceptibility to misinformation, particularly in knowledge conflict situations. |
| Outcome: | The proposed model is more user-oriented and more likely to accept misinformation when it is presented by the user. |
Title-based Extractive Summarization via MRC Framework (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on extractive summarization focus on scoring and selecting summary sentences . existing models tend to select generalized sentences while overlooking the overall content of a document. |
| Approach: | They propose a machine reading comprehension framework for extractive summarization by setting a query as the title. |
| Outcome: | The proposed framework outperforms existing models on long and short summaries in Korean and English . it can consider the semantic coherence and relevance of summary sentences in relation to the overall content . |
Bridging the Code Gap: A Joint Learning Framework across Medical Coding Systems (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for automating medical coding focus on a single coding system . however, there are still challenges to overcome in coding. |
| Approach: | They propose a joint learning framework for Across Medical coding systems which jointly learns different coding system through multi-task learning. |
| Outcome: | The proposed framework improves the performance of the MIMIC-IV ICD-9 and MIMICIV I CD-10 datasets. |
Analyzing Key Factors Influencing Emotion Prediction Performance of VLLMs in Conversational Contexts (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that large language models and vision large language model (VLLMs) possess EI and the ability to understand emotional stimuli in the form of text and images. |
| Approach: | They analyze the key elements affecting the emotion prediction performance of VLLMs in conversational contexts. |
| Outcome: | The proposed model performance was compared with other models in a conversational context. |
Exploring Nested Named Entity Recognition with Large Language Models: Methods, Challenges, and Insights (2024.emnlp-main)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a challenging task in natural language processing . nested NER requires sophisticated techniques to identify entities within entities . |
| Approach: | They investigate the application of Large Language Models (LLMs) to nested NER . they find methodologies from previous work are less effective . |
| Outcome: | The proposed methods outperform BERT-based models in nested NER tasks . however, they do not outperformed the existing models on the GENIA dataset . |
A Framework for Vision-Language Warm-up Tasks in Multimodal Dialogue Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for building multimodal open-domain dialogue agents based on large datasets are limited in real-world settings . |
| Approach: | They propose a new learning strategy called vision-language warm-up tasks for multimodal dialogue models that relies solely on learning from target data. |
| Outcome: | The proposed learning strategy achieves comparable and in some cases superior performance compared to existing state-of-the-art models on various evaluation metrics. |
Can Large Language Models Differentiate Harmful from Argumentative Essays? Steps Toward Ethical Essay Scoring (2025.coling-main)
Copied to clipboard
| Challenge: | Existing automated essay scoring systems overlook ethical and moral aspects of content, erroneously assigning high scores to essays that propagate harmful opinions. |
| Approach: | They introduce a Harmful Essay Detection benchmark to test the effectiveness of various Large Language Models (LLMs) they find that current AES systems overlook ethically and morally problematic elements in essays . |
| Outcome: | The proposed benchmark compared LLMs and AES models to identify and score harmful essays. |