Imagen de Portada

Input-Time Scaling: Adding Noise and Irrelevance into Less-Is-More Drastically Improves Reasoning Performance and Efficiency

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Rapheal, Guo, Weilong
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification
por: Guo, Yiju, et al.
Publicado: (2026)

LIMR: Less is More for RL Scaling
por: Li, Xuefeng, et al.
Publicado: (2025)

Less is More for Improving Automatic Evaluation of Factual Consistency
por: Wang, Tong, et al.
Publicado: (2024)

How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark
por: Yang, Minglai, et al.
Publicado: (2025)

Less is More: Improving LLM Alignment via Preference Data Selection
por: Deng, Xun, et al.
Publicado: (2025)

Improving Faithfulness of Abstractive Summarization by Controlling Confounding Effect of Irrelevant Sentences
por: Ghoshal, Asish, et al.
Publicado: (2022)

Supernova: Achieving More with Less in Transformer Architectures
por: Tanase, Andrei-Valentin, et al.
Publicado: (2025)

Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
por: Nahin, Shahriar Kabir, et al.
Publicado: (2025)

Explain Less, Understand More: Jargon Detection via Personalized Parameter-Efficient Fine-tuning
por: Wu, Bohao, et al.
Publicado: (2025)

When More is Less: Understanding Chain-of-Thought Length in LLMs
por: Wu, Yuyang, et al.
Publicado: (2025)

Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generation
por: Zheng, Yilun, et al.
Publicado: (2025)

Less is More: Local Intrinsic Dimensions of Contextual Language Models
por: Ruppik, Benjamin Matthias, et al.
Publicado: (2025)

Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation
por: Riaz, Haris, et al.
Publicado: (2025)

Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning
por: Sondej, Filip, et al.
Publicado: (2025)

Should We Attend More or Less? Modulating Attention for Fairness
por: Zayed, Abdelrahman, et al.
Publicado: (2023)

Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM
por: Liu, Yibai, et al.
Publicado: (2025)

Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs
por: Zhang, Yifei, et al.
Publicado: (2024)

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
por: Yang, Zhen, et al.
Publicado: (2025)

Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky
por: Hathidara, Ashutosh, et al.
Publicado: (2025)

Crosslingual Reasoning through Test-Time Scaling
por: Yong, Zheng-Xin, et al.
Publicado: (2025)

MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets
por: Wei, Lai, et al.
Publicado: (2023)

When Less is Enough: Efficient Inference via Collaborative Reasoning
por: Chen, Yilei, et al.
Publicado: (2026)

Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
por: Wang, Jian, et al.
Publicado: (2025)

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

Parallel Test-Time Scaling for Latent Reasoning Models
por: You, Runyang, et al.
Publicado: (2025)

LIMO: Less is More for Reasoning
por: Ye, Yixin, et al.
Publicado: (2025)

More Thinking, More Bias: Length-Driven Position Bias in Reasoning Models
por: Wang, Xiao
Publicado: (2026)

Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements
por: Zhao, Guangxiang, et al.
Publicado: (2025)

LoRA Learns Less and Forgets Less
por: Biderman, Dan, et al.
Publicado: (2024)

Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation
por: Wang, Zixin, et al.
Publicado: (2024)

Improving Reasoning Performance in Large Language Models via Representation Engineering
por: Højer, Bertram, et al.
Publicado: (2025)

Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models
por: Bazaga, Adrián, et al.
Publicado: (2025)

Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation
por: Chen, Peter Baile, et al.
Publicado: (2025)

More Compute Is What You Need
por: Guo, Zhen
Publicado: (2024)

Once Upon an Input: Reasoning via Per-Instance Program Synthesis
por: Stein, Adam, et al.
Publicado: (2025)

Less Peaky and More Accurate CTC Forced Alignment by Label Priors
por: Huang, Ruizhe, et al.
Publicado: (2024)

Efficient Test-Time Scaling via Self-Calibration
por: Huang, Chengsong, et al.
Publicado: (2025)

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage
por: Hu, Junhao, et al.
Publicado: (2026)

Baby Scale: Investigating Models Trained on Individual Children's Language Input
por: Feng, Steven Y., et al.
Publicado: (2026)

Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet
por: Zhao, James Xu, et al.
Publicado: (2025)