Imagen de Portada

Stop Jostling: Adaptive Negative Sampling Reduces the Marginalization of Low-Resource Language Tokens by Cross-Entropy Loss

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Turumtaev, Galim
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reducing Tokenization Premiums for Low-Resource Languages
por: Churchill, Geoffrey, et al.
Publicado: (2026)

Exploiting All Samples in Low-Resource Sentence Classification: Early Stopping and Initialization Parameters
por: Choi, Hongseok, et al.
Publicado: (2021)

Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning
por: Quamar, Mohammad Atif, et al.
Publicado: (2025)

Comparative Analysis of Tokenization Algorithms for Low-Resource Language Dzongkha
por: Wangchuk, Tandin, et al.
Publicado: (2025)

Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP
por: Remy, François, et al.
Publicado: (2024)

Just on Time: Token-Level Early Stopping for Diffusion Language Models
por: Kohut, Zahar, et al.
Publicado: (2026)

Cross-Lingual Transfer for Low-Resource Natural Language Processing
por: García-Ferrero, Iker
Publicado: (2025)

Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
por: Sun, Renliang, et al.
Publicado: (2025)

AdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower Bound on Token Acceptance Probability
por: Agrawal, Sudhanshu, et al.
Publicado: (2024)

Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models
por: Wu, Jialiang, et al.
Publicado: (2025)

EGAD: Entropy-Guided Adaptive Distillation for Token-Level Knowledge Transfer
por: Zhang, Hao, et al.
Publicado: (2026)

Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
por: Wen, Zichen, et al.
Publicado: (2025)

Spoken Language Identification with Pre-trained Models and Margin Loss
por: Fang, Zhihua, et al.
Publicado: (2026)

Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
por: Boizard, Nicolas, et al.
Publicado: (2024)

EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
por: Cheong, Minsoo, et al.
Publicado: (2026)

VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models
por: Liu, Chonghan, et al.
Publicado: (2026)

Tokenization Strategies for Low-Resource Agglutinative Languages in Word2Vec: Case Study on Turkish and Finnish
por: Hu, Jinfan Frank
Publicado: (2025)

Translation Errors Significantly Impact Low-Resource Languages in Cross-Lingual Learning
por: Agrawal, Ashish Sunil, et al.
Publicado: (2024)

Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages
por: Gupta, Shivanshu, et al.
Publicado: (2023)

ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
por: Chen, Shuang, et al.
Publicado: (2025)

Token-Level Marginalization for Multi-Label LLM Classifiers
por: Praharaj, Anjaneya, et al.
Publicado: (2025)

Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models
por: Alqahtani, Sawsan, et al.
Publicado: (2026)

Left Behind: Cross-Lingual Transfer as a Bridge for Low-Resource Languages in Large Language Models
por: Beibitkhan, Abdul-Salem
Publicado: (2026)

Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding
por: Oba, Daisuke, et al.
Publicado: (2026)

Linguistic Entity Masking to Improve Cross-Lingual Representation of Multilingual Language Models for Low-Resource Languages
por: Fernando, Aloka, et al.
Publicado: (2025)

When Every Token Counts: Optimal Segmentation for Low-Resource Language Models
por: Raj, Bharath, et al.
Publicado: (2024)

Unified Interpretation of Smoothing Methods for Negative Sampling Loss Functions in Knowledge Graph Embedding
por: Feng, Xincan, et al.
Publicado: (2024)

Token-Level Entropy Reveals Demographic Disparities in Language Models
por: Lee, Messi H. J.
Publicado: (2025)

No More Distractions: an Adaptive Up-Sampling Algorithm to Reduce Data Artifacts
por: Chen, Han
Publicado: (2024)

Safe at the Margins: A General Approach to Safety Alignment in Low-Resource English Languages -- A Singlish Case Study
por: Lim, Isaac, et al.
Publicado: (2025)

SSP: Self-Supervised Prompting for Cross-Lingual Transfer to Low-Resource Languages using Large Language Models
por: Rathore, Vipul, et al.
Publicado: (2024)

Are More Tokens Rational? Inference-Time Scaling in Language Models as Adaptive Resource Rationality
por: Hu, Zhimin, et al.
Publicado: (2026)

Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models
por: Park, Gyutae, et al.
Publicado: (2024)

CUTE: A Multilingual Dataset for Enhancing Cross-Lingual Knowledge Transfer in Low-Resource Languages
por: Zhuang, Wenhao, et al.
Publicado: (2025)

UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages
por: Pham, Trinh, et al.
Publicado: (2024)

Commonsense Knowledge with Negation: A Resource to Enhance Negation Understanding
por: Wang, Zijie, et al.
Publicado: (2026)

AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment
por: Deng, Ruibo, et al.
Publicado: (2025)

Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling
por: Ganescu, Bianca-Mihaela, et al.
Publicado: (2025)

Adaptive Stopping for Multi-Turn LLM Reasoning
por: Zhou, Xiaofan, et al.
Publicado: (2026)

Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data
por: Wang, Jiapeng, et al.
Publicado: (2025)