110 citations · 271 across the 36 of their papers we have counts for
45 papers
Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data
Joonhyeok Jeong, Jy-yong Sohn, Kibok Lee
Supervised contrastive learning and its balanced variants have demonstrated their effectiveness for representation learning under long-tailed distributions. However, although prior…
Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders
Chungpa Lee, Jihoon Kwon, Kyle Min +1
Vision-language models map images and text into a joint embedding space. However, these embeddings often entangle multiple semantic features, which limits their interpretability an…
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
Jihoon Kwon, Jiwon Choi, Jy-yong Sohn
In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks through demonstrations, yet it suffers from escalating inference costs as context length increas…
Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback
Jungtaek Kim, Thomas Zeng, Ziqian Lin +5
Effective problem solving with Large Language Models (LLMs) can be enhanced when they are paired with external search algorithms. By viewing the space of diverse ideas and their fo…
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
Chungpa Lee, Jy-yong Sohn, Kangwook Lee
Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations. In practice, such models ar…
How to Correctly Report LLM-as-a-Judge Evaluations
Chungpa Lee, Thomas Zeng, Jongwon Jeong +2
Large language models (LLMs) are widely used as scalable evaluators of model responses in lieu of human annotators. However, imperfect sensitivity and specificity of the LLM judges…
Soft Task-Aware Routing of Experts for Equivariant Representation Learning
Jaebyeong Jeon, Hyeonseo Jang, Jy-yong Sohn +1
Equivariant representation learning aims to capture variations induced by input transformations in the representation space, whereas invariant representation learning encodes seman…
Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions
Jihoon Kwon, Kyle Min, Jy-yong Sohn
Despite recent advances, vision-language models trained with standard contrastive objectives still struggle with compositional reasoning -- the ability to understand structured rel…
On the Similarities of Embeddings in Contrastive Learning
Chungpa Lee, Sehee Lim, Kibok Lee +1
Contrastive learning operates on a simple yet effective principle: Embeddings of positive pairs are pulled together, while those of negative pairs are pushed apart. In this paper,…
Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective
Joonkyu Kim, Yejin Kim, Jy-yong Sohn
In continual learning scenarios, catastrophic forgetting of previously learned tasks is a critical issue, making it essential to effectively measure such forgetting. Recently, ther…
FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation
Chanyeol Choi, Jihoon Kwon, Jaeseon Ha +5
In the fast-paced financial domain, accurate and up-to-date information is critical to addressing ever-evolving market conditions. Retrieving this information correctly is essentia…
A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning
Chungpa Lee, Jeongheon Oh, Kibok Lee +1
Supervised contrastive learning (SupCL) has emerged as a prominent approach in representation learning, leveraging both supervised and self-supervised losses. However, achieving an…
Bridging Language Models and Financial Analysis
Alejandro Lopez-Lira, Jihoon Kwon, Sangwoon Yoon +2
The rapid advancements in Large Language Models (LLMs) have unlocked transformative possibilities in natural language processing, particularly within the financial sector. Financia…
Linq-Embed-Mistral Technical Report
Chanyeol Choi, Junseong Kim, Seolhwa Lee +5
This report explores the enhancement of text retrieval performance using advanced data refinement techniques. We develop Linq-Embed-Mistral\footnote{\url{https://huggingface.co/Lin…
Buffer-based Gradient Projection for Continual Federated Learning
Shenghong Dai, Jy-yong Sohn, Yicong Chen +5
Continual Federated Learning (CFL) is essential for enabling real-world applications where multiple decentralized clients adaptively learn from continuous data streams. A significa…
Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks
Jy-yong Sohn, Dohyun Kwon, Seoyeon An +1
Fine-tuning large pre-trained models is a common practice in machine learning applications, yet its mathematical analysis remains largely unexplored. In this paper, we study fine-t…
Improving Multi-lingual Alignment Through Soft Contrastive Learning
Minsu Park, Seyeon Choi, Chanyeol Choi +2
Making decent multi-lingual sentence representations is critical to achieve high performances in cross-lingual downstream tasks. In this work, we propose a novel method to align mu…
ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classification
Sehee Lim, Yejin Kim, Chi-Hyun Choi +2
Improving the accessibility of psychotherapy with the aid of Large Language Models (LLMs) is garnering a significant attention in recent years. Recognizing cognitive distortions fr…
Aligning Large Language Models for Enhancing Psychiatric Interviews Through Symptom Delineation and Summarization: Pilot Study
Jae-hee So, Joonhwan Chang, Eunji Kim +5
Background: Advancements in large language models (LLMs) have opened new possibilities in psychiatric interviews, an underexplored area where LLMs could be valuable. This study foc…
Analysis of Using Sigmoid Loss for Contrastive Learning
Chungpa Lee, Joonhwan Chang, Jy-yong Sohn
Contrastive learning has emerged as a prominent branch of self-supervised learning for several years. Especially, CLIP, which applies contrastive learning to large sets of captione…
Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses
Juyeon Kim, Jeongeun Lee, Yoonho Chang +3
Mitigating hallucination issues is a key challenge that must be overcome to reliably deploy large language models (LLMs) in real-world scenarios. Recently, various methods have bee…
Can Separators Improve Chain-of-Thought Prompting?
Yoonjeong Park, Hyunjin Kim, Chanyeol Choi +2
Chain-of-thought (CoT) prompting is a simple and effective method for improving the reasoning capabilities of Large Language Models (LLMs). The basic idea of CoT is to let LLMs bre…
Mini-Batch Optimization of Contrastive Loss
Jaewoong Cho, Kartik Sreenivasan, Keon Lee +7
Contrastive learning has gained significant attention as a method for self-supervised learning. The contrastive loss function ensures that embeddings of positive sample pairs (e.g.…
Looped Transformers as Programmable Computers
Angeliki Giannou, Shashank Rajput, Jy-yong Sohn +3
We present a framework for using transformer networks as universal computers by programming them with specific weights and placing them in a loop. Our input sequence acts as a punc…