Taeyoon Kwon

Hyungjoo Chae

Dongjin Kang

Seungjun Moon

Suyeon Lee

Dongil Yang

Minjin Kim

Hana Kim

Yongho Song

Dahyun Lee

Yu Jin Kim

Byung Jun Bae

Gayeon Lee

Language & AGI Lab aims to develop artificial intelligence that understands and generates human language, and ultimately to create artificial general intelligence (AGI). Our research focuses on various aspects of natural language processing (NLP), including large language models (LLMs), natural language understanding (NLU), natural language generation (NLG), machine translation, and dialogue systems. We are also interested in the broader implications of AGI, such as its ethical considerations and societal impact.

Language & AGI Lab은 인간의 언어를 이해하고 생성하는 인공지능을 개발하고, 궁극적으로 범용 인공지능(AGI)을 만드는 것을 목표로 합니다. 저희 연구는 대규모 언어 모델(LLM), 자연어 이해(NLU), 자연어 생성(NLG), 기계 번역, 대화 시스템을 포함한 자연어 처리(NLP)의 다양한 측면에 중점을 둡니다. 또한 AGI의 윤리적 고려 사항 및 사회적 영향과 같은 광범위한 함의에도 관심을 가지고 있습니다.

Efficient Keyword-Aware Representative Travel Route Recommendation

Conversion Prediction from Clickstream: Modeling Market Prediction and Customer Predictability

Large Language Models Are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales

Predicting Online Purchase Conversion for Retargeting

DeepPDT-Net: predicting the outcome of photodynamic therapy for chronic central serous chorioretinopathy using two-stage multimodal transfer learning

KSTR: Keyword-Aware Skyline Travel Route Recommendation

Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation

Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents

Less is More: Attention Supervision with Counterfactuals for Text Classification

Translations as Additional Contexts for Sentence Classification

Learning with Limited Data for Multilingual Reading Comprehension

Browsing2purchase

Natural language processing to predict isocitrate dehydrogenase genotype in diffuse glioma using MR radiology reports

Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization

Predicting branch retinal vein occlusion development using multimodal deep learning and pre-onset fundus hemisection images

Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning

Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset

TrustAL: Trustworthy Active Learning Using Knowledge Distillation

Dual Task Framework for Improving Persona-Grounded Dialogue Dataset

Machine-Translated Knowledge Transfer for Commonsense Causal Reasoning

Towards Lifelong Dialogue Agents via Timeline-based Memory Management

Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning

TUTORING: Instruction-grounded Conversational Agent for Language Learners

Evidence-Empowered Transfer Learning for Alzheimer's Disease

Modularized Transfer Learning with Multiple Knowledge Graphs for Commonsense Reasoning

Towards Psychological Counseling Conversations using Cognitive Behavioral Theory

A Novel Approach to Cross-Lingual Transfer for Low-Resource Languages

Understanding the Limitations of Large Language Models in Reasoning Tasks

Enhancing Dialogue System Robustness with Adversarial Training

Few-Shot Learning for Medical Text Classification

EMBGUARD: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length

PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints

Why These Documents? Explainable Generative Retrieval with Hierarchical Category Paths

MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender

Success and Failure of Human–AI Collaboration in Clinical Reasoning: An Experimental Study on Challenging Real-World Cases

Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization

Prior-based Noisy Text Data Filtering: Fast and Strong Alternative For Perplexity

AgenticShop: Benchmarking Agentic Product Curation for Personalized Web Shopping

Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions

PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents

Stop Playing the Guessing Game! Evaluating Conversational Recommender Systems via Target-free User Simulation

Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching

Designing Memory-Augmented AR Agents for Spatiotemporal Reasoning in Personalized Task Assistance

Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization

LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Study

Can You Share Your Story? Modeling Clients' Metacognition and Openness for LLM Therapist Evaluation

One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL

Age-Related Scattered Hypofluorescent Spots as an Adverse Prognostic Factor for Polypoidal Choroidal Vasculopathy

Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation

Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics

Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

Predicting Branch Retinal Vein Occlusion Development using Multimodal Deep Learning and Pre-onset Fundus Hemisection Images

Unsupervised Robust Cross-Lingual Entity Alignment via Neighbor Triple Matching with Entity and Relation Texts

Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models

COFFEE-GYM: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code

Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-shot Question Answering

CACTUS: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory

Unveiling Implicit Table Knowledge with Question-Then-Pinpoint Reasoner for Insightful Table Summarization

VERIFINER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Model

PEARL: A Review-driven Persona-Knowledge grounded Conversational Recommendation Dataset

Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-then-Assign Strategy

RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization

Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement

Evidentiality-aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering

Multitask Deep Learning for Joint Detection of Necrotizing Viral and Noninfectious Retinitis From Common Blood and Serology Test Data

Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales

Natural Language Processing to Predict Isocitrate Dehydrogenase Genotype in Diffuse Glioma using MR Radiology Reports

CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification

BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets

Dual Task Framework for Improving Persona-grounded Dialogue Dataset

TrustAL: Trustworthy Active Learning using Knowledge Distillation

DeepPDT-Net: Predicting the Outcome of Photodynamic Therapy for Chronic Central Serous Chorioretinopathy Using Two-Stage Multimodal Transfer Learning

Yonsei Language & AGI Lab

교수님 소개

Jinyoung Yeo

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

EMBGUARD: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length

PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

Jinyoung Yeo

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

EMBGUARD: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents

On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length

PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집