Jinyoung Kim
2024
GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?
Dayoon Ko
|
Jinyoung Kim
|
Hahyeon Choi
|
Gunhee Kim
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
In the real world, knowledge is constantly evolving, which can render existing knowledge-based datasets outdated. This unreliability highlights the critical need for continuous updates to ensure both accuracy and relevance in knowledge-intensive tasks. To address this, we propose GrowOVER-QA and GrowOVER-Dialogue, dynamic open-domain QA and dialogue benchmarks that undergo a continuous cycle of updates, keeping pace with the rapid evolution of knowledge. Our research indicates that retrieval-augmented language models (RaLMs) struggle with knowledge that has not been trained on or recently updated. Consequently, we introduce a novel retrieval-interactive language model framework, where the language model evaluates and reflects on its answers for further re-retrieval. Our exhaustive experiments demonstrate that our training-free framework significantly improves upon existing methods, performing comparably to or even surpassing continuously trained language models.
DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG
Jinyoung Kim
|
Dayoon Ko
|
Gunhee Kim
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
In the rapidly evolving landscape of language, resolving new linguistic expressions in continuously updating knowledge bases remains a formidable challenge. This challenge becomes critical in retrieval-augmented generation (RAG) with knowledge bases, as emerging expressions hinder the retrieval of relevant documents, leading to generator hallucinations. To address this issue, we introduce a novel task aimed at resolving emerging mentions to dynamic entities and present DynamicER benchmark. Our benchmark includes dynamic entity mention resolution and entity-centric knowledge-intensive QA task, evaluating entity linking and RAG model’s adaptability to new expressions, respectively. We discovered that current entity linking models struggle to link these new expressions to entities. Therefore, we propose a temporal segmented clustering method with continual adaptation, effectively managing the temporal dynamics of evolving entities and emerging mentions. Extensive experiments demonstrate that our method outperforms existing baselines, enhancing RAG model performance on QA task with resolved mentions.
2023
Contrastively Pretrained Vision-Language Transformers and Domain Adaptation Methods for Multimodal TOD Systems
Youngjae Chang
|
Doo Young Kim
|
Jinyoung Kim
|
Keunha Kim
|
Hyunmook Cha
|
Suyoung Min
|
Youngjoong Ko
|
Kye-Hwan Lee
|
Joonwoo Park
Proceedings of The Eleventh Dialog System Technology Challenge
The Situated Interactive MultiModal Conversations (SIMMC2.1) Challenge 2022 is hosted by the Eleventh Dialog System Technology Challenge (DSTC11). This is the third consecutive year multimodal dialog systems have been selected as an official track of the competition, promoted by the continued interest in the research community. The task of SIMMC is to create a shopping assistant agent that can communicate with customers in a virtual store. It requires processing store scenes and product catalogs along with the customer’s request. The task is decomposed into four steps and each becomes a subtask. In this work, we explore the common approaches to modeling multimodality and find the method with the most potential. We also identify a discrepancy in using pretrained language models for dialog tasks and devise a simple domain-adaptation method. Our model came in third place for object coreferencing, dialog state tracking, and response generation tasks.
Search
Fix data
Co-authors
- Gunhee Kim 2
- Dayoon Ko 2
- Hyunmook Cha 1
- Youngjae Chang 1
- Hahyeon Choi 1
- show all...