Image de couverture de livre

Optimizing Korean-Centric LLMs via Token Pruning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kim, Hoyeol, Kim, Hyeonwoo
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Open Ko-LLM Leaderboard2: Bridging Foundational and Practical Evaluation for Korean LLMs
par: Kim, Hyeonwoo, et autres
Publié: (2024)

Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark
par: Park, Chanjun, et autres
Publié: (2024)

Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification
par: Yun, Jungmin, et autres
Publié: (2024)

Understanding LLM Development Through Longitudinal Study: Insights from the Open Ko-LLM Leaderboard
par: Park, Chanjun, et autres
Publié: (2024)

Thunder-LLM: Efficiently Adapting LLMs to Korean with Minimal Resources
par: Kim, Jinpyo, et autres
Publié: (2025)

Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset
par: Yu, Seunguk, et autres
Publié: (2025)

Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues
par: Kim, Eunsu, et autres
Publié: (2025)

Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean
par: Kim, SungHo, et autres
Publié: (2025)

Steering LLMs toward Korean Local Speech: Iterative Refinement Framework for Faithful Dialect Translation
par: Park, Keunhyeung, et autres
Publié: (2025)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
par: Zhong, Yiwu, et autres
Publié: (2024)

Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching
par: Kim, Seoyeon, et autres
Publié: (2024)

How Language Directions Align with Token Geometry in Multilingual LLMs
par: Kim, JaeSeong, et autres
Publié: (2025)

Leveraging KV Similarity for Online Structured Pruning in LLMs
par: Lee, Jungmin, et autres
Publié: (2025)

sDPO: Don't Use Your Data All at Once
par: Kim, Dahyun, et autres
Publié: (2024)

PHISH in MESH: Korean Adversarial Phonetic Substitution and Phonetic-Semantic Feature Integration Defense
par: Kim, Byungjun, et autres
Publié: (2025)

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation
par: Chen, Xinrui, et autres
Publié: (2025)

SLM-Based Agentic AI with P-C-G: Optimized for Korean Tool Use
par: Jeon, Changhyun, et autres
Publié: (2025)

HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models
par: Son, Guijin, et autres
Publié: (2023)

Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Education
par: Kim, Seungyoon, et autres
Publié: (2024)

KoSimpleQA: A Korean Factuality Benchmark with an Analysis of Reasoning LLMs
par: Ko, Donghyeon, et autres
Publié: (2025)

SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models
par: Kim, Hyeonwoo, et autres
Publié: (2024)

ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
par: Hou, Bairu, et autres
Publié: (2025)

A Character-Centric Creative Story Generation via Imagination
par: Park, Kyeongman, et autres
Publié: (2024)

SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
par: Ji, Yicheng, et autres
Publié: (2025)

How does a Language-Specific Tokenizer affect LLMs?
par: Seo, Jean, et autres
Publié: (2025)

KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge
par: Lee, Jiyoung, et autres
Publié: (2024)

KoACD: The First Korean Adolescent Dataset for Cognitive Distortion Analysis via Role-Switching Multi-LLM Negotiation
par: Kim, JunSeo, et autres
Publié: (2025)

From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented Languages
par: Kiulian, Artur, et autres
Publié: (2024)

Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study
par: Lim, Junghwan, et autres
Publié: (2025)

VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models
par: Ju, Jeongho, et autres
Publié: (2024)

Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning
par: Guo, Yiju, et autres
Publié: (2025)

GECKO: Generative Language Model for English, Code and Korean
par: Oh, Sungwoo, et autres
Publié: (2024)

Federated Learning for Face Recognition via Intra-subject Self-supervised Learning
par: Kim, Hansol, et autres
Publié: (2024)

Learning to Insert [PAUSE] Tokens for Better Reasoning
par: Kim, Eunki, et autres
Publié: (2025)

KMMLU: Measuring Massive Multitask Language Understanding in Korean
par: Son, Guijin, et autres
Publié: (2024)

KoCoNovel: Annotated Dataset of Character Coreference in Korean Novels
par: Kim, Kyuhee, et autres
Publié: (2024)

KOMBO: Korean Character Representations Based on the Combination Rules of Subcharacters
par: Kim, SungHo, et autres
Publié: (2026)

Making Qwen3 Think in Korean with Reinforcement Learning
par: Lee, Jungyup, et autres
Publié: (2025)

Enhancing Korean Dependency Parsing with Morphosyntactic Features
par: Park, Jungyeul, et autres
Publié: (2025)

SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning
par: Long, Lingkun, et autres
Publié: (2025)