Papers by Kangmin Kim
MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks for investigating knowledge conflict have notable limitations, including a narrow focus on the question answering setup, heavy reliance on entity substitution techniques, and a restricted range of conflict types. |
| Approach: | They propose a knowledge graph-based framework that generates varied and subtle conflicts between two similar yet distinct contexts while ensuring interpretability through the explicit relational structure of KGs. |
| Outcome: | The proposed framework generates varied and subtle conflicts between two similar yet distinct contexts while ensuring interpretability through the explicit relational structure of KGs. |
SentiCSE: A Sentiment-aware Contrastive Sentence Embedding Framework with Sentiment-guided Textual Similarity (2024.lrec-main)
Copied to clipboard
| Challenge: | Sentiment-aware pre-trained language models (PLMs) demonstrate impressive results in downstream sentiment analysis tasks, but they neglect to evaluate the quality of constructed sentiment representations. |
| Approach: | They propose a new metric for evaluating the quality of sentiment representations that is based on the degree of equivalence in sentiment polarity between two sentences. |
| Outcome: | The proposed framework outperforms the existing sentiment-aware models in sentiment analysis tasks. |