Imagen de Portada

SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hou, Shuyang, Hu, Yi, Zhang, Muhan
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Number Cookbook: Number Understanding of Language Models and How to Improve It
por: Yang, Haotong, et al.
Publicado: (2024)

Empowering Character-level Text Infilling by Eliminating Sub-Tokens
por: Ren, Houxing, et al.
Publicado: (2024)

LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?
por: He, Ziyuan, et al.
Publicado: (2025)

PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice
por: Shi, Yuzhen, et al.
Publicado: (2026)

Case-Based or Rule-Based: How Do Transformers Do the Math?
por: Hu, Yi, et al.
Publicado: (2024)

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction
por: Bian, Haonan, et al.
Publicado: (2026)

BRIDGE: Benchmarking Large Language Models for Understanding Real-world Clinical Practice Text
por: Wu, Jiageng, et al.
Publicado: (2025)

LooGLE: Can Long-Context Language Models Understand Long Contexts?
por: Li, Jiaqi, et al.
Publicado: (2023)

COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens
por: Kwek, Eugene, et al.
Publicado: (2025)

DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail Domain
por: Borkakoty, Hsuvas, et al.
Publicado: (2026)

ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding
por: Li, Xiaozhe, et al.
Publicado: (2025)

AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
por: Ruan, Jianhao, et al.
Publicado: (2026)

Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty
por: Wu, Peilin, et al.
Publicado: (2025)

D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies
por: Chen, Sen, et al.
Publicado: (2025)

You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs
por: Xu, Yijie, et al.
Publicado: (2025)

LIFT: Improving Long Context Understanding Through Long Input Fine-Tuning
por: Mao, Yansheng, et al.
Publicado: (2024)

AnomaLLMy -- Detecting anomalous tokens in black-box LLMs through low-confidence single-token predictions
por: Witold, Waligóra
Publicado: (2024)

Can Large Language Models Understand Real-World Complex Instructions?
por: He, Qianyu, et al.
Publicado: (2023)

MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use
por: Lei, Fei, et al.
Publicado: (2025)

Sub-token ViT Embedding via Stochastic Resonance Transformers
por: Lao, Dong, et al.
Publicado: (2023)

RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking
por: Yang, Shuo, et al.
Publicado: (2025)

From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MARKERGEN
por: Yuan, Peiwen, et al.
Publicado: (2025)

SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
por: Ma, Jiefeng, et al.
Publicado: (2024)

RadReason: Radiology Report Evaluation Metric with Reasons and Sub-Scores
por: Li, Yingshu, et al.
Publicado: (2025)

QuarkMedBench: A Real-World Scenario Driven Benchmark for Evaluating Large Language Models
por: Wu, Yao, et al.
Publicado: (2026)

RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios
por: Zhou, Ruiwen, et al.
Publicado: (2024)

$τ$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
por: Yao, Shunyu, et al.
Publicado: (2024)

TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios
por: Wei, Shaohang, et al.
Publicado: (2025)

WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
por: Hou, Yufang, et al.
Publicado: (2024)

From Words to Worlds: Benchmarking Cross-Cultural Cultural Understanding in Machine Translation
por: Han, Bangju, et al.
Publicado: (2026)

Jacobian Scopes: token-level causal attributions in LLMs
por: Liu, Toni J. B., et al.
Publicado: (2026)

Prediction hubs are context-informed frequent tokens in LLMs
por: Nielsen, Beatrix M. G., et al.
Publicado: (2025)

CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge
por: Ismayilzada, Mete, et al.
Publicado: (2026)

DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
por: Wu, Junchao, et al.
Publicado: (2024)

Beyond SELECT: A Comprehensive Taxonomy-Guided Benchmark for Real-World Text-to-SQL Translation
por: Wang, Hao, et al.
Publicado: (2025)

LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability
por: Xiao, Zikai, et al.
Publicado: (2025)

HalluMix: A Task-Agnostic, Multi-Domain Benchmark for Real-World Hallucination Detection
por: Emery, Deanna, et al.
Publicado: (2025)

LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement
por: C, Rajmohan, et al.
Publicado: (2025)

GenKnowSub: Improving Modularity and Reusability of LLMs through General Knowledge Subtraction
por: Bagherifard, Mohammadtaha, et al.
Publicado: (2025)

CSV-Decode: Certifiable Sub-Vocabulary Decoding for Efficient Large Language Model Inference
por: Liu, Dong, et al.
Publicado: (2025)