Search Results for author: Hwaran Lee

Found 21 papers, 12 papers with code

Compositional Sentence Representation from Character within Large Context Text

no code implementations2 May 2016 Geonmin Kim, Hwaran Lee, Jisu Choi, Soo-Young Lee

In the HCRN, word representations are built from characters, thus resolving the data-sparsity problem, and inter-sentence dependency is embedded into sentence representation at the level of sentence composition.

Dialogue Act Classification General Classification +1

Deep CNNs along the Time Axis with Intermap Pooling for Robustness to Spectral Variations

no code implementations10 Jun 2016 Hwaran Lee, Geonmin Kim, Ho-Gyeong Kim, Sang-Hoon Oh, Soo-Young Lee

Convolutional neural networks (CNNs) with convolutional and pooling operations along the frequency axis have been proposed to attain invariance to frequency shifts of features.

Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition

1 code implementation6 Nov 2018 Geonmin Kim, Hwaran Lee, Bo-Kyeong Kim, Sang-Hoon Oh, Soo-Young Lee

Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator.

Generative Adversarial Network Speech Enhancement +2

SUMBT+LaRL: Effective Multi-domain End-to-end Neural Task-oriented Dialog System

no code implementations22 Sep 2020 Hwaran Lee, Seokhwan Jo, HyungJun Kim, SangKeun Jung, Tae-Yoon Kim

To our best knowledge, our work is the first comprehensive study of a modularized E2E multi-domain dialog system that learning from each component to the entire dialog policy for task success.

reinforcement-learning Reinforcement Learning (RL)

Plug-and-Play Adaptation for Continuously-updated QA

no code implementations Findings (ACL) 2022 Kyungjae Lee, Wookje Han, Seung-won Hwang, Hwaran Lee, Joonsuk Park, Sang-Woo Lee

To this end, we first propose a novel task--Continuously-updated QA (CuQA)--in which multiple large-scale updates are made to LMs, and the performance is measured with respect to the success in adding and updating knowledge while retaining existing knowledge.

ClaimDiff: Comparing and Contrasting Claims on Contentious Issues

1 code implementation24 May 2022 Miyoung Ko, Ingyu Seong, Hwaran Lee, Joonsuk Park, Minsuk Chang, Minjoon Seo

With the growing importance of detecting misinformation, many studies have focused on verifying factual claims by retrieving evidence.

Fact Verification Misinformation

Critic-Guided Decoding for Controlled Text Generation

no code implementations21 Dec 2022 Minbeom Kim, Hwanhee Lee, Kang Min Yoo, Joonsuk Park, Hwaran Lee, Kyomin Jung

In this work, we propose a novel critic decoding method for controlled language generation (CriticControl) that combines the strengths of reinforcement learning and weighted decoding.

Language Modelling reinforcement-learning +2

Who Wrote this Code? Watermarking for Code Generation

1 code implementation24 May 2023 Taehyun Lee, Seokhee Hong, Jaewoo Ahn, Ilgee Hong, Hwaran Lee, Sangdoo Yun, Jamin Shin, Gunhee Kim

Based on \citet{Kirchenbauer2023watermark}, we propose a new watermarking method, Selective WatErmarking via Entropy Thresholding (SWEET), that promotes "green" tokens only at the position with high entropy of the token distribution during generation, thereby preserving the correctness of the generated code.

Code Generation Text Detection

Query-Efficient Black-Box Red Teaming via Bayesian Optimization

1 code implementation27 May 2023 Deokjae Lee, JunYeong Lee, Jung-Woo Ha, Jin-Hwa Kim, Sang-Woo Lee, Hwaran Lee, Hyun Oh Song

To this end, we propose Bayesian red teaming (BRT), novel query-efficient black-box red teaming methods based on Bayesian optimization, which iteratively identify diverse positive test cases leading to model failures by utilizing the pre-defined user input pool and the past evaluations.

Bayesian Optimization Language Modelling

KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application

1 code implementation28 May 2023 Hwaran Lee, Seokhee Hong, Joonsuk Park, Takyoung Kim, Gunhee Kim, Jung-Woo Ha

Large language models (LLMs) learn not only natural text generation abilities but also social biases against different demographic groups from real-world data.

Language Modelling Large Language Model +1

KoBBQ: Korean Bias Benchmark for Question Answering

no code implementations31 Jul 2023 Jiho Jin, Jiseon Kim, Nayeon Lee, Haneul Yoo, Alice Oh, Hwaran Lee

In this paper, we present KoBBQ, a Korean bias benchmark dataset, and we propose a general framework that addresses considerations for cultural adaptation of a dataset.

Question Answering

Prometheus: Inducing Fine-grained Evaluation Capability in Language Models

1 code implementation12 Oct 2023 Seungone Kim, Jamin Shin, Yejin Cho, Joel Jang, Shayne Longpre, Hwaran Lee, Sangdoo Yun, Seongjin Shin, Sungdong Kim, James Thorne, Minjoon Seo

We first construct the Feedback Collection, a new dataset that consists of 1K fine-grained score rubrics, 20K instructions, and 100K responses and language feedback generated by GPT-4.

Language Modelling Large Language Model

LifeTox: Unveiling Implicit Toxicity in Life Advice

no code implementations16 Nov 2023 Minbeom Kim, Jahyun Koo, Hwanhee Lee, Joonsuk Park, Hwaran Lee, Kyomin Jung

As large language models become increasingly integrated into daily life, detecting implicit toxicity across diverse contexts is crucial.

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

1 code implementation20 Feb 2024 Martin Gubri, Dennis Ulmer, Hwaran Lee, Sangdoo Yun, Seong Joon Oh

Large Language Model (LLM) services and models often come with legal rules on who can use them and how they must use them.

Language Modelling Large Language Model

KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge

no code implementations21 Feb 2024 Jiyoung Lee, Minwoo Kim, Seungho Kim, Junghwan Kim, Seunghyun Won, Hwaran Lee, Edward Choi

For the common knowledge dataset, we constructed samples based on Korean textbooks and GED reference materials.

Multiple-choice

Calibrating Large Language Models Using Their Generations Only

1 code implementation9 Mar 2024 Dennis Ulmer, Martin Gubri, Hwaran Lee, Sangdoo Yun, Seong Joon Oh

As large language models (LLMs) are increasingly deployed in user-facing applications, building trust and maintaining safety by accurately quantifying a model's confidence in its prediction becomes even more important.

Question Answering Text Generation

Why Knowledge Distillation Amplifies Gender Bias and How to Mitigate from the Perspective of DistilBERT

no code implementations NAACL (GeBNLP) 2022 Jaimeen Ahn, Hwaran Lee, JinHwa Kim, Alice Oh

Knowledge distillation is widely used to transfer the language understanding of a large model to a smaller model. However, after knowledge distillation, it was found that the smaller model is more biased by gender compared to the source large model. This paper studies what causes gender bias to increase after the knowledge distillation process. Moreover, we suggest applying a variant of the mixup on knowledge distillation, which is used to increase generalizability during the distillation process, not for augmentation. By doing so, we can significantly reduce the gender bias amplification after knowledge distillation. We also conduct an experiment on the GLUE benchmark to demonstrate that even if the mixup is applied, it does not have a significant adverse effect on the model’s performance.

Knowledge Distillation

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