Author name cluster

Jinyoung Yeo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

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

Yeongbin Seo
Dongha Lee
Jaehyung Kim
Jinyoung Yeo

Autoregressive (AR) language models generate text one token at a time, which limits their inference speed. Diffusion-based language models offer a promising alternative, as they can decode multiple tokens in parallel. However, we identify a key bottleneck in current diffusion LMs: the \textbf{long decoding-window problem}, where tokens generated far from the input context often become irrelevant or repetitive. Previous solutions like semi-autoregressive address this issue by splitting windows into blocks (sacrificing bidirectionality), but we find that this also leads to \textbf{time-interval expansion problem}, sacrificing the speed. Therefore, semi-AR eliminates the main advantages of diffusion models. To overcome this, we propose Convolutional decoding (\textit{Conv}), a normalization-based method that narrows the decoding window without hard segmentation, leading to better fluency and flexibility. Additionally, we introduce Rejecting Rule-based Fine-Tuning (R2FT), a post-hoc training scheme that better aligns tokens at positions far from context. Our methods achieve state-of-the-art results on open-ended generation benchmarks (e. g. , AlpacaEval) among diffusion LM baselines, with significantly lower step size than previous works, demonstrating both speed and quality improvements. The code is available online (\url{https: //github. com/ybseo-ac/Conv}).

PDF Details

ICLR Conference 2025 Conference Paper

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

Hyungjoo Chae
Namyoung Kim
Kai Tzu-iunn Ong
Minju Gwak
Gwanwoo Song
Jihoon Kim
Sunghwan Kim 0005
Dongha Lee 0003

Large language models (LLMs) have recently gained much attention in building autonomous agents. However, performance of current LLM-based web agents in long-horizon tasks is far from optimal, often yielding errors such as repeatedly buying a non-refundable flight ticket. By contrast, humans can avoid such an irreversible mistake, as we have an awareness of the potential outcomes (e.g., losing money) of our actions, also known as the "world model". Motivated by this, our study first starts with preliminary analyses, confirming the absence of world models in current LLMs (e.g., GPT-4o, Claude-3.5-Sonnet, etc.). Then, we present a World-model-augmented (WMA) web agent, which simulates the outcomes of its actions for better decision-making. To overcome the challenges in training LLMs as world models predicting next observations, such as repeated elements across observations and long HTML inputs, we propose a transition-focused observation abstraction, where the prediction objectives are free-form natural language descriptions exclusively highlighting important state differences between time steps. Experiments on WebArena and Mind2Web show that our world models improve agents' policy selection without training and demonstrate our agents' cost- and time-efficiency compared to recent tree-search-based agents.

Details

NeurIPS Conference 2025 Conference Paper

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

Hyungjoo Chae
Seonghwan Kim
Junhee Cho
Seungone Kim
Seungjun Moon
Gyeom Hwangbo
Dongha Lim
Minjin Kim

Web navigation is a unique domain that can automate many repetitive real-life tasks and is challenging as it requires long-horizon sequential decision making beyond typical multimodal large language model (MLLM) tasks. Yet, specialized reward models for web navigation that can be utilized during both training and test-time have been absent until now. Despite the importance of speed and cost-effectiveness, prior works have utilized MLLMs as reward models, which poses significant constraints for real-world deployment. To address this, in this work, we propose the first process reward model (PRM) called Web-Shepherd which could assess web navigation trajectories in a step-level. To achieve this, we first construct the WebPRM Collection, a large-scale dataset with 40K step-level preference pairs and annotated checklists spanning diverse domains and difficulty levels. Next, we also introduce the WebRewardBench, the first meta-evaluation benchmark for evaluating PRMs. In our experiments, we observe that our Web-Shepherd achieves about 30 points better accuracy compared to using GPT-4o on WebRewardBench. Furthermore, when testing on WebArena-lite by using GPT-4o-mini as the policy and Web-Shepherd as the verifier, we achieve 10. 9 points better performance, in 10x less cost compared to using GPT-4o-mini as the verifier. Our model, dataset, and code are publicly available at https: //github. com/kyle8581/Web-Shepherd.

PDF Details

AAAI Conference 2024 Conference Paper

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

Taeyoon Kwon
Kai Tzu-iunn Ong
Dongjin Kang
Seungjun Moon
Jeong Ryong Lee
Dosik Hwang
Beomseok Sohn
Yongsik Sim

Machine reasoning has made great progress in recent years owing to large language models (LLMs). In the clinical domain, however, most NLP-driven projects mainly focus on clinical classification or reading comprehension, and under-explore clinical reasoning for disease diagnosis due to the expensive rationale annotation with clinicians. In this work, we present a "reasoning-aware" diagnosis framework that rationalizes the diagnostic process via prompt-based learning in a time- and labor-efficient manner, and learns to reason over the prompt-generated rationales. Specifically, we address the clinical reasoning for disease diagnosis, where the LLM generates diagnostic rationales providing its insight on presented patient data and the reasoning path towards the diagnosis, namely Clinical Chain-of-Thought (Clinical CoT). We empirically demonstrate LLMs/LMs' ability of clinical reasoning via extensive experiments and analyses on both rationale generation and disease diagnosis in various settings. We further propose a novel set of criteria for evaluating machine-generated rationales' potential for real-world clinical settings, facilitating and benefiting future research in this area.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

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

Yeongbin Seo
Dongha Lee
Jinyoung Yeo

Previous studies on continual knowledge learning (CKL) in large language models (LLMs) have predominantly focused on approaches such as regularization, architectural modifications, and rehearsal techniques to mitigate catastrophic forgetting. However, these methods naively inherit the inefficiencies of standard training procedures, indiscriminately applying uniform weight across all tokens, which can lead to unnecessary parameter updates and increased forgetting. To address these shortcomings, we propose a novel CKL approach termed Train-Attention-Augmented Language Model (TAALM), which enhances learning efficiency by dynamically predicting and applying weights to tokens based on their usefulness. This method employs a meta-learning framework that optimizes token importance predictions, facilitating targeted knowledge updates and minimizing forgetting. Also, we observe that existing benchmarks do not clearly exhibit the trade-off between learning and retaining, therefore we propose a new benchmark, LAMA-ckl, to address this issue. Through experiments conducted on both newly introduced and established CKL benchmarks, TAALM proves the state-of-the-art performance upon the baselines, and also shows synergistic compatibility when integrated with previous CKL approaches. The code and the dataset are available online.

PDF Details DOI

AAAI Conference 2023 System Paper

TUTORING: Instruction-Grounded Conversational Agent for Language Learners

Hyungjoo Chae
Minjin Kim
Chaehyeong Kim
Wonseok Jeong
Hyejoong Kim
Junmyung Lee
Jinyoung Yeo

In this paper, we propose Tutoring bot, a generative chatbot trained on a large scale of tutor-student conversations for English-language learning. To mimic a human tutor's behavior in language education, the tutor bot leverages diverse educational instructions and grounds to each instruction as additional input context for the tutor response generation. As a single instruction generally involves multiple dialogue turns to give the student sufficient speaking practice, the tutor bot is required to monitor and capture when the current instruction should be kept or switched to the next instruction. For that, the tutor bot is learned to not only generate responses but also infer its teaching action and progress on the current conversation simultaneously by a multi-task learning scheme. Our Tutoring bot is deployed under a non-commercial use license at https://tutoringai.com.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Dual Task Framework for Improving Persona-Grounded Dialogue Dataset

Minju Kim
Beong-woo Kwak
Youngwook Kim
Hong-in Lee
Seung-won Hwang
Jinyoung Yeo

This paper introduces a simple yet effective data-centric approach for the task of improving persona-conditioned dialogue agents. Prior model-centric approaches unquestioningly depend on the raw crowdsourced benchmark datasets such as Persona-Chat. In contrast, we aim to fix annotation artifacts in benchmarking, which is orthogonally applicable to any dialogue model. Specifically, we augment relevant personas to improve dialogue dataset/agent, by leveraging the primal-dual structure of the two tasks, predicting dialogue responses and personas based on each other. Experiments on Persona-Chat show that our approach outperforms pretrained LMs by an 11. 7 point gain in terms of accuracy.

PDF Details

AAAI Conference 2022 Conference Paper

TrustAL: Trustworthy Active Learning Using Knowledge Distillation

Beong-woo Kwak
Youngwook Kim
Yu Jin Kim
Seung-won Hwang
Jinyoung Yeo

Active learning can be defined as iterations of data labeling, model training, and data acquisition, until sufficient labels are acquired. A traditional view of data acquisition is that, through iterations, knowledge from human labels and models is implicitly distilled to monotonically increase the accuracy and label consistency. Under this assumption, the most recently trained model is a good surrogate for the current labeled data, from which data acquisition is requested based on uncertainty/diversity. Our contribution is debunking this myth and proposing a new objective for distillation. First, we found example forgetting, which indicates the loss of knowledge learned across iterations. Second, for this reason, the last model is no longer the best teacher– For mitigating such forgotten knowledge, we select one of its predecessor models as a teacher, by our proposed notion of “consistency”. We show that this novel distillation is distinctive in the following three aspects; First, consistency ensures to avoid forgetting labels. Second, consistency improves both uncertainty/diversity of labeled data. Lastly, consistency redeems defective labels produced by human annotators.

PDF Details

AAAI Conference 2018 Conference Paper

Machine-Translated Knowledge Transfer for Commonsense Causal Reasoning

Jinyoung Yeo
Geungyu Wang
Hyunsouk Cho
Seungtaek Choi
Seung-won Hwang

This paper studies the problem of multilingual causal reasoning in resource-poor languages. Existing approaches, translating into the most probable resource-rich language such as English, suffer in the presence of translation and language gaps between different cultural area, which leads to the loss of causality. To overcome these challenges, our goal is thus to identify key techniques to construct a new causality network of cause-effect terms, targeted for the machinetranslated English, but without any language-speciﬁc knowledge of resource-poor languages. In our evaluations with three languages, Korean, Chinese, and French, our proposed method consistently outperforms all baselines, achieving upto 69. 0% reasoning accuracy, which is close to the state-ofthe-art accuracy 70. 2% achieved on English.

PDF Details

IJCAI Conference 2018 Conference Paper

Translations as Additional Contexts for Sentence Classification

Reinald Kim Amplayo
Kyungjae Lee
Jinyoung Yeo
Seung-won Hwang

In sentence classification tasks, additional contexts, such as the neighboring sentences, may improve the accuracy of the classifier. However, such contexts are domain-dependent and thus cannot be used for another classification task with an inappropriate domain. In contrast, we propose the use of translated sentences as domain-free context that is always available regardless of the domain. We find that naive feature expansion of translations gains only marginal improvements and may decrease the performance of the classifier, due to possible inaccurate translations thus producing noisy sentence vectors. To this end, we present multiple context fixing attachment (MCFA), a series of modules attached to multiple sentence vectors to fix the noise in the vectors using the other sentence vectors as context. We show that our method performs competitively compared to previous models, achieving best classification performance on multiple data sets. We are the first to use translations as domain-free contexts for sentence classification.

PDF Details

AAAI Conference 2016 Conference Paper

Understanding Emerging Spatial Entities

Jinyoung Yeo
Jin-woo Park
Seung-won Hwang

In Foursquare or Google+ Local, emerging spatial entities, such as new business or venue, are reported to grow by 1% every day. As information on such spatial entities is initially limited (e. g. , only name), we need to quickly harvest related information from social media such as Flickr photos. Especially, achieving high-recall in photo population is essential for emerging spatial entities, which suffer from data sparseness (e. g. , 71% restaurants of TripAdvisor in Seattle do not have any photo, as of Sep 03, 2015). Our goal is thus to address this limitation by identifying effective linking techniques for emerging spatial entities and photos. Compared with state-of-the-art baselines, our proposed approach improves recall and F1 score by up to 24% and 18%, respectively. To show the effectiveness and robustness of our approach, we have conducted extensive experiments in three different cities, Seattle, Washington D. C. , and Taipei, of varying characteristics such as geographical density and language.

PDF Details