Cover Image

Instance-level Randomization: Toward More Stable LLM Evaluations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yiyang, Wu, Yonghuang, Luo, Ying, Sun, Liangtai, Qin, Zishu, Qiu, Lin, Cao, Xuezhi, Cai, Xunliang
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM Agents
by: Guo, Zhengkang, et al.
Published: (2026)

AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
by: Jiayang, Cheng, et al.
Published: (2026)

OIBench: Benchmarking Strong Reasoning Models with Olympiad in Informatics
by: Zhu, Yaoming, et al.
Published: (2025)

CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments
by: Fu, Lingyue, et al.
Published: (2025)

META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI
by: Sun, Liangtai, et al.
Published: (2022)

MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models
by: Yan, Siyu, et al.
Published: (2025)

MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures
by: Qin, Jiayu, et al.
Published: (2025)

Making Mathematical Reasoning Adaptive
by: Lai, Zhejian, et al.
Published: (2025)

General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks
by: Liu, Junlin, et al.
Published: (2026)

Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation
by: Wong, Yutszyuk, et al.
Published: (2026)

AMO-Bench: Large Language Models Still Struggle in High School Math Competitions
by: An, Shengnan, et al.
Published: (2025)

A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification
by: Niimi, Junichiro
Published: (2025)

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
by: Lu, Yi, et al.
Published: (2025)

MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents
by: Tan, Haoran, et al.
Published: (2025)

Towards Evaluation for Real-World LLM Unlearning
by: Miao, Ke, et al.
Published: (2025)

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
by: Che, Zora, et al.
Published: (2025)

Toward a More Complete OMR Solution
by: Yang, Guang, et al.
Published: (2024)

MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
by: Fu, Xiaoliang, et al.
Published: (2026)

Cross-Patient Pseudo Bags Generation and Curriculum Contrastive Learning for Imbalanced Multiclassification of Whole Slide Image
by: Wu, Yonghuang, et al.
Published: (2024)

Prompt Group-Aware Training for Robust Text-Guided Nuclei Segmentation
by: Wu, Yonghuang, et al.
Published: (2026)

UNO-Bench: A Unified Benchmark for Exploring the Compositional Law Between Uni-modal and Omni-modal in Omni Models
by: Chen, Chen, et al.
Published: (2025)

Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration
by: Zhang, Shao, et al.
Published: (2025)

AutoContext: Instance-Level Context Learning for LLM Agents
by: Cai, Kuntai, et al.
Published: (2025)

Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
by: Xu, Yang, et al.
Published: (2026)

C2T: A Classifier-Based Tree Construction Method in Speculative Decoding
by: Huo, Feiye, et al.
Published: (2025)

Neural Network Optimal Power Flow via Energy Gradient Flow and Unified Dynamics
by: Liu, Xuezhi
Published: (2025)

Physics-Constrained Neural Dynamics: A Unified Manifold Framework for Large-Scale Power Flow Computation
by: Liu, Xuezhi
Published: (2025)

Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents
by: Wang, Shouju, et al.
Published: (2025)

Evaluative Fingerprints: Stable and Systematic Differences in LLM Evaluator Behavior
by: Nasser, Wajid
Published: (2026)

AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition
by: Wang, Ruipeng, et al.
Published: (2026)

S^3cMath: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners
by: Yan, Yuchen, et al.
Published: (2024)

FeatBench: Towards More Realistic Evaluation of Feature-level Code Generation
by: Chen, Haorui, et al.
Published: (2025)

Look Before You Leap: Autonomous Exploration for LLM Agents
by: Ye, Ziang, et al.
Published: (2026)

Interactive Learning for LLM Reasoning
by: Lin, Hehai, et al.
Published: (2025)

Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO
by: Yang, Xin, et al.
Published: (2026)

Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations
by: Gong, Nanxu, et al.
Published: (2026)

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
by: Fan, Siqi, et al.
Published: (2025)

Not All Instances Are Equally Valuable: Towards Influence-Weighted Dataset Distillation
by: Deng, Qiyan, et al.
Published: (2025)

Bridging Synthetic and Real Routing Problems via LLM-Guided Instance Generation and Progressive Adaptation
by: Zhu, Jianghan, et al.
Published: (2025)

Understanding and Optimizing Agentic Workflows via Shapley value
by: Yang, Yingxuan, et al.
Published: (2025)