1 citations · 2 across the 18 of their papers we have counts for
20 papers
Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval
JungMin Yun, YoungBin Kim
Retrieval-augmented generation (RAG) critically depends on retrieving the evidence necessary for effective reasoning. However, this remains particularly challenging in multi-hop qu…
ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives
Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim +1
Safety alignment is essential for deploying large language models, requiring systems to prevent harmful compliance while preserving helpfulness on benign requests. Activation steer…
Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines
Minkyu Kim, Juhwan Choi, YoungBin Kim
Text-to-image (T2I) safety guardrails fail to generalize equitably to non-standard dialects. Evaluating 23,080 paired prompts across five English dialects, we formalize this failur…
IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering
JungMin Yun, YoungBin Kim
Multi-hop question answering requires complex reasoning across multiple evidence segments, which often overwhelms retrieval-augmented generation systems with lengthy and noisy cont…
CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps
JungMin Yun, JuneHyoung Kwon, YoungBin Kim
Evaluating the multi-hop reasoning capabilities of large language models remains a significant challenge. Although current models achieve strong results on existing multi-hop quest…
Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks
JuneHyoung Kwon, MiHyeon Kim, Eunju Lee +3
While Large Vision-Language Models (LVLMs) offer powerful capabilities, they pose privacy risks by unintentionally memorizing sensitive personal information. Current unlearning ben…
Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models
JuneHyoung Kwon, JungMin Yun, YoungBin Kim
Large Vision-Language Models (LVLMs), trained on web-scale data, risk memorizing and regenerating copyrighted visual content such as characters and logos, creating significant chal…
Aligning with Your Own Voice: Self-Corrected Preference Learning for Hallucination Mitigation in LVLMs
Byeonggeuk Lim, JungMin Yun, Junehyoung Kwon +2
Large Vision-Language Models (LVLMs) frequently suffer from hallucinations. Existing preference learning-based approaches largely rely on proprietary models to construct preference…
HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
Eunju Lee, MiHyeon Kim, JuneHyoung Kwon +4
Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) methods assume homogeneous domains a…
Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias
JuneHyoung Kwon, MiHyeon Kim, Eunju Lee +3
Machine unlearning, which enables a model to forget specific data, is crucial for ensuring data privacy and model reliability. However, its effectiveness can be severely undermined…
Position on LLM-Assisted Peer Review: Addressing Reviewer Gap through Mentoring and Feedback
JungMin Yun, JuneHyoung Kwon, MiHyeon Kim +1
The rapid expansion of AI research has intensified the Reviewer Gap, threatening the peer-review sustainability and perpetuating a cycle of low-quality evaluations. This position p…
Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset
Seunguk Yu, Kyeonghyun Kim, Jungmin Yun +1
Although LLMs have made significant progress in various languages, there are still concerns about their effectiveness with low-resource agglutinative languages compared to language…
Proceedings of 1st Workshop on Advancing Artificial Intelligence through Theory of Mind
Mouad Abrini, Omri Abend, Dina Acklin +105
This volume includes a selection of papers presented at the Workshop on Advancing Artificial Intelligence through Theory of Mind held at AAAI 2025 in Philadelphia US on 3rd March 2…
See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
JuneHyoung Kwon, MiHyeon Kim, Eunju Lee +2
Vision-language (VL) models have demonstrated strong performance across various tasks. However, these models often rely on a specific modality for predictions, leading to "dominant…
Rank-O-ToM: Unlocking Emotional Nuance Ranking to Enhance Affective Theory-of-Mind
JiHyun Kim, JuneHyoung Kwon, MiHyeon Kim +2
Facial Expression Recognition (FER) plays a foundational role in enabling AI systems to interpret emotional nuances, a critical aspect of affective Theory of Mind (ToM). However, e…
DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation
Soojin Jang, Jungmin Yun, Junehyoung Kwon +2
Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due…
VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks
Juhwan Choi, Junehyoung Kwon, JungMin Yun +2
Domain generalizability is a crucial aspect of a deep learning model since it determines the capability of the model to perform well on data from unseen domains. However, research…
Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification
Jungmin Yun, Mihyeon Kim, Youngbin Kim
Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computati…
UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation
Juhwan Choi, Yeonghwa Kim, Seunguk Yu +2
Although pre-trained language models have exhibited great flexibility and versatility with prompt-based few-shot learning, they suffer from the extensive parameter size and limited…
Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation
Juhwan Choi, Jungmin Yun, Kyohoon Jin +1
The quality of the dataset is crucial for ensuring optimal performance and reliability of downstream task models. However, datasets often contain noisy data inadvertently included…