Papers by Taehwan Kim

7 papers
Data Descriptions from Large Language Models with Influence Estimation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing explainable AI approaches focus on interpreting how models make predictions.
Approach: They propose a pipeline that generates textual descriptions using large language models . they propose 'cross-modal transfer classification' task to examine effectiveness of textual description .
Outcome: The proposed method improves classification accuracy compared to baselines and sheds light on how the model prioritizes and utilizes information for decision-making.
Sound of Story: Multi-modal Storytelling with Audio (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies on storytelling with sound have focused on visuals and sounds, but little attention has been given to sound.
Approach: They propose to establish a new component called background sound which is story context-based audio without any linguistic information.
Outcome: The proposed dataset is the largest well-curated dataset for storytelling with sound . it contains 27,354 stories with 19.6 images per story and 984 hours of speech-decoupled audio .
VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions (2025.emnlp-main)

Copied to clipboard

Challenge: VEHME is a vision language model for assessing handwritten math answers . traditional methods of assessing student work are limited by time constraints, class sizes and cognitive load .
Approach: They propose a Vision-Language Model for Evaluating Handwritten Mathematics Expressions to assess handwritten math responses with high accuracy and interpretable reasoning traces.
Outcome: VEHME achieves state-of-the-art performance among open-source models and approaches accuracy of proprietary systems.
GMoE: Global Mixture of Experts with Logit Propagation (2026.acl-long)

Copied to clipboard

Challenge: Sparse Mixture of Experts architectures retain large memory footprints and exhibit significant redundancy, both within and across layers.
Approach: They propose a sparse mixture of experts architecture that uses global experts shared across all layers and adds a Local Expert per layer for layer-specific adaptation.
Outcome: The proposed architecture reduces computational cost by activating only a subset of experts per token while maintaining strong performance.
Efficient Latent Variable Modeling for Knowledge-Grounded Dialogue Generation (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing knowledge-grounded dialogue generation algorithms require annotated knowledge to generate a response grounded on the retrieved knowledge.
Approach: They propose an efficient algorithm for latent variable modeling that leverages large amount of dialogue data.
Outcome: The proposed algorithm outperforms the supervised learning algorithm on knowledge-grounded dialogue datasets while maintaining efficiency and scalability.
Selective Token Generation for Few-shot Natural Language Generation (2022.coling-1)

Copied to clipboard

Challenge: Experimental results show that the proposed selective token generation algorithm outperforms the previous additive learning algorithms based on the PLMs.
Approach: They propose an additive learning algorithm that selectively outputs language tokens between a task-general PLM and a specific adapter during training and inference.
Outcome: The proposed algorithm outperforms existing methods on few-shot natural language generation tasks.
RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals (2025.findings-emnlp)

Copied to clipboard

Challenge: Transformers have shown strong performance in processing sequential data, but their parameters are larger . a novel approach to reduce the model parameters while maintaining high performance is proposed .
Approach: They propose a transformer-based model that processes input repeatedly in a circular, ring-like manner.
Outcome: The proposed approach reduces model parameters while maintaining high performance . the proposed approach is validated in the experiments.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations