Search Results for author: Jy-yong Sohn

Found 18 papers, 7 papers with code

ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classification

no code implementations21 Mar 2024 Sehee Lim, Yejin Kim, Chi-Hyun Choi, Jy-yong Sohn, Byung-Hoon Kim

Improving the accessibility of psychotherapy with the aid of Large Language Models (LLMs) is garnering a significant attention in recent years.

Specificity

Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses

no code implementations27 Feb 2024 Juyeon Kim, Jeongeun Lee, Yoonho Chang, Chanyeol Choi, JunSeong Kim, Jy-yong Sohn

Mitigating hallucination issues is one of the main challenges of LLMs we need to overcome, in order to reliably use them in real-world scenarios.

Hallucination

Analysis of Using Sigmoid Loss for Contrastive Learning

no code implementations20 Feb 2024 Chungpa Lee, Joonhwan Chang, Jy-yong Sohn

The optimal embedding ranges from simplex equiangular-tight-frame to antipodal structure, depending on the temperature parameter used in the sigmoid loss.

Contrastive Learning Self-Supervised Learning

Can Separators Improve Chain-of-Thought Prompting?

no code implementations16 Feb 2024 Yoonjeong Park, HyunJin Kim, Chanyeol Choi, JunSeong Kim, Jy-yong Sohn

The basic idea of CoT is to let LLMs break down their thought processes step-by-step by putting exemplars in the input prompt.

Looped Transformers as Programmable Computers

1 code implementation30 Jan 2023 Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris Papailiopoulos

We present a framework for using transformer networks as universal computers by programming them with specific weights and placing them in a loop.

In-Context Learning

Can We Find Strong Lottery Tickets in Generative Models?

no code implementations16 Dec 2022 Sangyeop Yeo, Yoojin Jang, Jy-yong Sohn, Dongyoon Han, Jaejun Yoo

To the best of our knowledge, we are the first to show the existence of strong lottery tickets in generative models and provide an algorithm to find it stably.

Model Compression Network Pruning

Equal Improvability: A New Fairness Notion Considering the Long-term Impact

1 code implementation13 Oct 2022 Ozgur Guldogan, Yuchen Zeng, Jy-yong Sohn, Ramtin Pedarsani, Kangwook Lee

In order to promote long-term fairness, we propose a new fairness notion called Equal Improvability (EI), which equalizes the potential acceptance rate of the rejected samples across different groups assuming a bounded level of effort will be spent by each rejected sample.

Fairness

LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks

1 code implementation14 Jun 2022 Tuan Dinh, Yuchen Zeng, Ruisu Zhang, Ziqian Lin, Michael Gira, Shashank Rajput, Jy-yong Sohn, Dimitris Papailiopoulos, Kangwook Lee

LIFT does not make any changes to the model architecture or loss function, and it solely relies on the natural language interface, enabling "no-code machine learning with LMs."

BIG-bench Machine Learning General Classification +2

Breaking Fair Binary Classification with Optimal Flipping Attacks

no code implementations12 Apr 2022 Changhun Jo, Jy-yong Sohn, Kangwook Lee

Minimizing risk with fairness constraints is one of the popular approaches to learning a fair classifier.

Binary Classification Classification +2

Rare Gems: Finding Lottery Tickets at Initialization

1 code implementation24 Feb 2022 Kartik Sreenivasan, Jy-yong Sohn, Liu Yang, Matthew Grinde, Alliot Nagle, Hongyi Wang, Eric Xing, Kangwook Lee, Dimitris Papailiopoulos

Frankle & Carbin conjecture that we can avoid this by training "lottery tickets", i. e., special sparse subnetworks found at initialization, that can be trained to high accuracy.

Finding Everything within Random Binary Networks

no code implementations18 Oct 2021 Kartik Sreenivasan, Shashank Rajput, Jy-yong Sohn, Dimitris Papailiopoulos

A recent work by Ramanujan et al. (2020) provides significant empirical evidence that sufficiently overparameterized, random neural networks contain untrained subnetworks that achieve state-of-the-art accuracy on several predictive tasks.

Communication-Computation Efficient Secure Aggregation for Federated Learning

no code implementations10 Dec 2020 Beongjun Choi, Jy-yong Sohn, Dong-Jun Han, Jaekyun Moon

Through extensive real-world experiments, we demonstrate that our scheme, using only $20 \sim 30\%$ of the resources required in the conventional scheme, maintains virtually the same levels of reliability and data privacy in practical federated learning systems.

Federated Learning Privacy Preserving

Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks

no code implementations NeurIPS 2020 Jy-yong Sohn, Dong-Jun Han, Beongjun Choi, Jaekyun Moon

Recent advances in large-scale distributed learning algorithms have enabled communication-efficient training via SignSGD.

Cannot find the paper you are looking for? You can Submit a new open access paper.