Papers by Donghyun Kim

16 papers
Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA (2026.eacl-long)

Copied to clipboard

Challenge: Recent studies leverage large language models (LLMs) in LVQA benchmarks, achieving exceptional performance while relying on vision language models to convert all visual content into natural language.
Approach: They propose a modular and training-free framework that leverages large language models to generate a small subset of informative frames tailored to each question.
Outcome: The proposed framework achieves state-of-the-art performance among similar models across four benchmark LVQA datasets: EgoSchema, NExT-QA, IntentQA, VideoMME.
Data-Efficient Adaptation to Contextual Shifts in LLM-based Conversational Recommendation (2026.findings-acl)

Copied to clipboard

Challenge: Existing data selection methods struggle to distinguish learnable samples under contextual shifts.
Approach: They propose a framework agnostic to underlying large language model-based conversational recommender systems (CRSs) that captures user preferences through free-form conversations and generates contextually relevant recommendations.
Outcome: The proposed framework outperforms baselines on three CRS benchmarks with real-world temporal splits.
MATE: Meet At The Embedding - Connecting Images with Long Texts (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in Vision Language Models (VLMs) focus on aligning images with short descriptive captions.
Approach: They propose a method that combines VLMs with Large Language Models to efficiently align images with long texts without additional text pairs.
Outcome: The proposed method bridges the gap between VLM and LLM without additional image-long text pairs.
Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning (2026.eacl-long)

Copied to clipboard

Challenge: Recent advances in reinforcement learning with verifiable rewards (RLVR) show that large language models enhance their reasoning abilities when trained with veriable signals.
Approach: They propose a method for a problem-aware filtering system that maximizes learning efficiency by selecting tasks of intermediate difficulty.
Outcome: The proposed model improves when trained with verifiable rewards, but training efficiency is bottleneck . the proposed model achieves +12% gains in less than half the training steps of standard GRPO .
Persona Expansion with Commonsense Knowledge for Diverse and Consistent Response Generation (2023.eacl-main)

Copied to clipboard

Challenge: Existing researches have focused on generating diverse and consistent responses based on personal traits.
Approach: They propose a consistent persona expansion framework that improves not only the diversity but also the consistency of persona-based responses.
Outcome: The proposed framework improves not only the diversity but also the consistency of persona-based responses on the Persona-Chat dataset.
Large Language Models as Realistic Microservice Trace Generators (2025.emnlp-main)

Copied to clipboard

Challenge: Obtaining real-world traces is difficult due to limited public data availability and the difficulty of collecting them at large scale from diverse environments.
Approach: They propose to train a large language model to generate microservice call graphs using a recursive approach to capture hierarchical structures and implicit constraints in such traces.
Outcome: The proposed method outperforms existing methods in accuracy and validity.
Concept-based Persona Expansion for Improving Diversity of Persona-Grounded Dialogue (2023.eacl-main)

Copied to clipboard

Challenge: Existing approaches to improve the quality of persona-grounded dialogues are limited to a few informative words.
Approach: They propose a concept-based persona expansion framework that takes the original persona as input and generates expanded personas that contain conceptually rich content.
Outcome: The proposed framework improves the quality of persona-grounded dialogue responses in diversity and richness.
Conversation Model Fine-Tuning for Classifying Client Utterances in Counseling Dialogues (N19-1)

Copied to clipboard

Challenge: Recent surge of text-based online counseling applications enables us to collect and analyze interactions between counselors and clients.
Approach: They develop a pre-trained conversation model that learns to classify client utterances into categories that help counselors in diagnosing client status and predicting counseling outcome.
Outcome: The proposed model outperforms state-of-the-art comparison models and shows expected linguistic patterns for each category.
Keep Me Updated! Memory Management in Long-term Conversations (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing studies do not deal with cases where memorized information is outdated, which may cause confusion in later conversations.
Approach: They propose a task where bots keep track of and bring up the latest information about users while conversing through multiple sessions.
Outcome: The proposed method outperforms baselines that leave the stored memory unchanged in terms of engagingness and humanness, and a larger performance gap in the later sessions.
LLMs as Knowledge Graph Refiners: Mitigating Factual Inconsistencies in Generative Knowledge Extraction (2026.acl-long)

Copied to clipboard

Challenge: Knowledge graphs (KGs) represent real-world entities and their relations in a structured form.
Approach: They propose a framework that performs triple-level refinement on KGs constructed via GKE.
Outcome: The proposed framework improves KG quality from diverse perspectives.
PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints (2026.findings-acl)

Copied to clipboard

Challenge: Recent research explores multi-agent systems where agents collaborate toward shared goals to handle complex tasks.
Approach: They propose a benchmark for systematic evaluation of multi-agent collaboration under privacy constraints.
Outcome: The proposed benchmark shows that privacy constraints degrade collaboration performance and make outcomes depend more on the initiating agent than the partner.
Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models (2022.naacl-main)

Copied to clipboard

Challenge: Recent large-scale language models have produced human-like responses in open-domain dialogue systems.
Approach: They propose a framework for imposing roles on open-domain dialogue systems . they use few-shot learning to build a Korean dialogue dataset from scratch .
Outcome: The proposed framework meets role specifications while maintaining conversational abilities.
Aligning Large Language Models through Synthetic Feedback (2023.emnlp-main)

Copied to clipboard

Challenge: Currently, alignment learning requires significant human demonstrations and feedback from proprietary LLMs such as ChatGPT.
Approach: They propose a framework that uses synthetic feedback to align large language models to human values without extensive human annotations and proprietary LLMs.
Outcome: The proposed model outperforms open-source models on human-annotated demonstrations in alignment benchmarks.
StitchLLM: Serving LLMs, One Block at a Time (2025.acl-long)

Copied to clipboard

Challenge: Existing techniques like distillation and pruning are not efficient for large language models.
Approach: They propose a dynamic model routing framework that uses a powerful bottom model to process all queries and a lightweight routing mechanism to allocate computational resources appropriately.
Outcome: The proposed framework improves system throughput while minimizing performance degradation.
Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances (2022.naacl-main)

Copied to clipboard

Challenge: Existing approaches for recognizing feature transitions between utterances extract features for the context at the coarse-grained level.
Approach: They propose a method to recognize feature transitions between utterances that helps understand dialogue flow . they propose empathetic response generation strategy to focus on emotion and keywords related to appropriate features when generating responses.
Outcome: The proposed approach outperforms baseline approaches and improves on multi-turn dialogues.

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