Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Rapheal, Guo, Weilong
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

LoRA Learns Less and Forgets Less
di: Biderman, Dan, et al.
Pubblicazione: (2024)

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

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

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

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

More Compute Is What You Need
di: Guo, Zhen
Pubblicazione: (2024)

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

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

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

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

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

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