Papers by Kang Min Yoo
Generating Information-Seeking Conversations from Unlabeled Documents (2022.emnlp-main)
Copied to clipboard
| Challenge: | a novel framework for conversational question answering from unlabeled documents has been proposed . a large-scale dataset of synthetic conversations is available for use in real-world applications . |
| Approach: | They propose a framework for conversational question answering from unlabeled documents . they propose 'SimSeek' framework that simulates conversation from unlabelled documents based on two scenarios . |
| Outcome: | The proposed framework achieves state-of-the-art performance on a recent CQA benchmark, QuAC. |
Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts (2024.findings-emnlp)
Copied to clipboard
Youna Kim, Hyuhng Joon Kim, Cheonbok Park, Choonghyun Park, Hyunsoo Cho, Junyeob Kim, Kang Min Yoo, Sang-goo Lee, Taeuk Kim
| Challenge: | Recent research has been developed to amplify contextual knowledge over parametric knowledge of large language models (LLMs) in knowledge-intensive tasks such as open-domain question-answering . |
| Approach: | They propose to amplify contextual knowledge over parametric knowledge of large language models (LLMs) by contrastive decoding to leverage contextual influence effectively. |
| Outcome: | The proposed approach improves open-domain question answering tasks especially in robustness by remaining undistracted by noisy contexts in retrieval-augmented generation. |
Aligning Language Models to Explicitly Handle Ambiguity (2024.emnlp-main)
Copied to clipboard
Hyuhng Joon Kim, Youna Kim, Cheonbok Park, Junyeob Kim, Choonghyun Park, Kang Min Yoo, Sang-goo Lee, Taeuk Kim
| Challenge: | Large language models (LLMs) are not specifically trained to deal with ambiguous utterances . ambiguity can lead to varying interpretations of the same input based on different assumptions or background knowledge . |
| Approach: | They propose a pipeline that aligns large language models to manage ambiguous queries . they propose to use their own assessment of perceived ambiguity to detect and manage queries a . |
| Outcome: | Experimental results show that APA empowers LLMs to detect and manage ambiguous queries while retaining the ability to answer clear questions. |
KMMLU: Measuring Massive Multitask Language Understanding in Korean (2025.naacl-long)
Copied to clipboard
Guijin Son, Hanwool Lee, Sungdong Kim, Seungone Kim, Niklas Muennighoff, Taekyoon Choi, Cheonbok Park, Kang Min Yoo, Stella Biderman
| Challenge: | Recent models struggle to show performance over 60%, significantly below the pass mark of the source exams (80%), highlighting the room for improvement. |
| Approach: | They propose to use Korean exams to collect 35,030 questions from an expert-level multiple choice model to capture linguistic and cultural aspects of the Korean language. |
| Outcome: | The proposed benchmark is based on 35,030 questions from original Korean exams. |
Continuous Decomposition of Granularity for Neural Paraphrase Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Prior work has shown that decomposing sentences at different levels of granularity has improved paragraph generation. |
| Approach: | They propose a model for continuous decomposing granularity for neural paraphrase generation that incorporates granules into attention. |
| Outcome: | The proposed model outperforms baseline models on Quora question pairs and Twitter URLs on two benchmarks. |
Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations (2022.emnlp-main)
Copied to clipboard
Kang Min Yoo, Junyeob Kim, Hyuhng Joon Kim, Hyunsoo Cho, Hwiyeol Jo, Sang-Woo Lee, Sang-goo Lee, Taeuk Kim
| Challenge: | Intuitively, ground-truth labels should have as much impact in in-context learning as supervised learning, but the impact of the quality of demonstrations remains elusive. |
| Approach: | They propose to measure input-label correspondence and ground-truth label effect ratio . they propose to use verbosity of prompt templates and language model size as controlling factors . |
| Outcome: | The proposed metrics show that ground-truth labels have less impact than previously thought . the authors identify key components as controlling factors to achieve noise-resilient ICL . |
What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers (2021.emnlp-main)
Copied to clipboard
Boseop Kim, HyoungSeok Kim, Sang-Woo Lee, Gichang Lee, Donghyun Kwak, Jeon Dong Hyeon, Sunghyun Park, Sungju Kim, Seonhoon Kim, Dongpil Seo, Heungsub Lee, Minyoung Jeong, Sungjae Lee, Minsub Kim, Suk Hyun Ko, Seokhun Kim, Taeyong Park, Jinuk Kim, Soyoung Kang, Na-Hyeon Ryu, Kang Min Yoo, Minsuk Chang, Soobin Suh, Sookyo In, Jinseong Park, Kyungduk Kim, Hiun Kim, Jisu Jeong, Yong Goo Yeo, Donghoon Ham, Dongju Park, Min Young Lee, Jaewook Kang, Inho Kang, Jung-Woo Ha, Woomyoung Park, Nako Sung
| Challenge: | GPT-3 has been used to train large-scale language models on hundreds of billion scale data. |
| Approach: | They propose a Korean variant of GPT-3 that uses Korean tokens to train in-context models. |
| Outcome: | The proposed method shows state-of-the-art zero-shot and few-shot learning on downstream tasks in Korean. |
Aligning Large Language Models by On-Policy Self-Judgment (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model for on-policy learning. |
| Approach: | They propose a new alignment framework that does on-policy learning and is parameter efficient . they propose Judge-augmented Supervised Fine-Tuning to train a single model to act as a policy and a judge. |
| Outcome: | The proposed framework outperforms baselines in preference benchmarks and rejecting sampling by itself improves performance without additional evaluator. |
Instruction Tuning with Human Curriculum (2024.findings-naacl)
Copied to clipboard
| Challenge: | a recent study shows that human curriculum-inspired strategies can enhance performance of large language models. |
| Approach: | They propose a method for generating instruction-response datasets that emulate human learning . they find that substantial improvements can be achieved through curriculum ordering . |
| Outcome: | The proposed method achieves performance improvements on truthfulQA, MMLU, OpenbookQA, and ARC-hard benchmarks without additional computational costs. |
Enhancing Hallucination Detection via Future Context (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are widely used to generate plausible text on online platforms, without revealing the generation process. |
| Approach: | They propose a framework for detection of hallucinations in black-box generators by analyzing future contexts. |
| Outcome: | The proposed framework improves on existing methods and demonstrates that it is feasible to integrate it with other models. |
Critic-Guided Decoding for Controlled Text Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent work has demonstrated reinforcement learning and weighted decoding as effective approaches to achieve a higher level of language control and quality with pros and cons. |
| Approach: | They propose a method that combines reinforcement learning and weighted decoding to train a critic from reward models. |
| Outcome: | The proposed method generates more coherent and well-controlled texts than previous methods on three controlled generation tasks, topic control, sentiment control, and detoxification. |
Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience. |
| Approach: | They propose a framework that encourages intermediate features to learn layer-specialized representations and assembles them implicitly into a single representation to absorb rich information in the pre-trained language model. |
| Outcome: | The proposed framework is significantly more effective than previous studies in intent classification and OOD datasets. |
ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown impressive performance on downstream tasks, but if they cannot be fully described in prompts, they could fail to perform the task. |
| Approach: | They propose a method to contextualize a task toward a large language model (LLM) they use open-ended zero-shot inference from the entire dataset to aggregate the inference results and incorporate the aggregated meta-information for the actual task. |
| Outcome: | The proposed method improves text clustering tasks and improves on several datasets. |
ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing iterative refinement strategies that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. |
| Approach: | They propose a reinforcement learning framework that internalizes the structured reasoning trajectory directly into the model’s weights. |
| Outcome: | The proposed framework achieves 94.51% (87.20%) on HumanEval, 81.80% (78.57%) on MBPP, 35.00% on BigCodeBench, 52.21% on LiveCodeBech, and 37.34% on CodeForces in a single-attempt setting. |
AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models (2022.findings-emnlp)
Copied to clipboard
Se Jung Kwon, Jeonghoon Kim, Jeongin Bae, Kang Min Yoo, Jin-Hwa Kim, Baeseong Park, Byeongwook Kim, Jung-Woo Ha, Nako Sung, Dongsoo Lee
| Challenge: | Existing approaches to improve inference efficiency by accelerating model fine-tuning have not been thoroughly explored. |
| Approach: | They propose to combine parameter-efficient adaptation and model compression to accelerate model . they propose to freeze binary parameters and scale scaling factors for target tasks . |
| Outcome: | The proposed algorithm achieves >10x compression ratio under 4-bit quantization and >1,000x reduction in trainable parameters. |
Self-Guided Contrastive Learning for BERT Sentence Representations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to derive sentence embeddings from pre-trained Transformers are unclear . a self-guided training method is used to fine-tune BERT in a supervised fashion . |
| Approach: | They propose a contrastive learning method that utilizes self-guidance to improve BERT sentence representations. |
| Outcome: | The proposed method is more effective than baselines on diverse sentence-related tasks and robust to domain shifts. |
GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies report that prompt-based direct classification eliminates the need for fine-tuning but lacks data and inference scalability. |
| Approach: | They propose a data augmentation technique that leverages large-scale language models to generate real text samples from a mixture of real samples. |
| Outcome: | The proposed method outperforms existing methods on diverse classification tasks. |
Don’t Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja (D19-1)
Copied to clipboard
| Challenge: | Existing knowledge of Korean and Chinese is based on cultural and historical reasons. |
| Approach: | They propose a method for improving Korean word representations using additional linguistic annotation by leveraging the fact that Hanja is closely related to Chinese. |
| Outcome: | The proposed approach improves representations on a novel Korean news headline generation task. |
Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency Checking (2022.findings-naacl)
Copied to clipboard
| Challenge: | Abstractive summarization systems generate paraphrases, but they often contain information inconsistent with the source text. |
| Approach: | They propose to generate factually inconsistent summaries using source texts and reference summary with key information masked to train a factual consistency classifier. |
| Outcome: | The proposed method outperforms existing models and shows a competitive correlation with human judgments. |
Probing Out-of-Distribution Robustness of Language Models with Parameter-Efficient Transfer Learning (2023.starsem-1)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are gaining popularity on many benchmarks, but it is uncertain whether they can handle inputs that have been distributionally shifted. |
| Approach: | They evaluated various PETL techniques to detect out-of-distribution changes as the size of the PLM grows or the transfer methods are altered. |
| Outcome: | The proposed methods can detect out-of-distribution changes as the size of the PLM grows or the transfer methods are altered. |
HyperT5: Towards Compute-Efficient Korean Language Modeling (2023.acl-industry)
Copied to clipboard
| Challenge: | Pretraining and fine-tuning language models is a common practice in NLP, but deploying general-purpose language models without the abundant computation or data resources is proving difficult. |
| Approach: | They propose a sequence-to-sequence language model architecture that can be more practical and compute-efficient than the decoder-oriented approach. |
| Outcome: | The proposed language model outperforms competing models in Korean benchmarks and is more efficient in low-resource settings. |
Attribute Injection for Pretrained Language Models: A New Benchmark and an Efficient Method (2022.coling-1)
Copied to clipboard
| Challenge: | Recent models rely on pretrained language models that use metadata as inputs . however, these methods are either nontrivial or cost-ineffective . |
| Approach: | They propose a benchmark for evaluating attribute injection models using eight datasets . they extend adapters to include attributes independently of or jointly with the text . |
| Outcome: | The proposed method outperforms previous methods and achieves state-of-the-art performance on all datasets. |
LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for quantizing weights and activations of large language models suffer from non-negligible accuracy drops, especially on massive multitask language understanding. |
| Approach: | They propose a weight-activation quantization method that reconstructs the outputs of an intermediate Transformer block by leveraging low-rank weight-scaling matrices. |
| Outcome: | The proposed method reduces the complexity of the weight-activation quantization techniques while achieving high throughput and reducing inference costs. |
Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that generative data augmentation, where synthetic samples generated from deep generative models complement the training dataset, benefit NLP tasks. |
| Approach: | They propose a Variational Hierarchical Dialog Autoencoder for modeling the complete aspects of goal-oriented dialogs using inter-connected latent variables and learns to generate coherent dialogs from the latent spaces. |
| Outcome: | The proposed model outperforms previous strong baselines on dialog response generation and user simulation tasks. |