Imagen de Portada

Reasoning Shift: How Context Silently Shortens LLM Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Rodionov, Gleb
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Discrete Neural Algorithmic Reasoning
por: Rodionov, Gleb, et al.
Publicado: (2024)

Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning
por: Shi, Zeru, et al.
Publicado: (2025)

Contextual Drag: How Errors in the Context Affect LLM Reasoning
por: Cheng, Yun, et al.
Publicado: (2026)

Sequence Shortening for Context-Aware Machine Translation
por: Mąka, Paweł, 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)

CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
por: Sun, Ke, et al.
Publicado: (2026)

The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
por: Yin, Chenlong, et al.
Publicado: (2025)

Evaluating Long-Context Reasoning in LLM-Based WebAgents
por: Chung, Andy, et al.
Publicado: (2025)

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
por: Rodionov, Gleb, et al.
Publicado: (2025)

When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning
por: Sahoo, Subramanyam, et al.
Publicado: (2026)

Directional Attractors in LLM Reasoning: How Similarity Retrieval Steers Iterative Summarization Based Reasoning
por: Tekin, Cagatay, et al.
Publicado: (2025)

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning
por: Zhai, Zhiyuan, et al.
Publicado: (2026)

Privacy Reasoning in Ambiguous Contexts
por: Yi, Ren, et al.
Publicado: (2025)

The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility
por: Pape, David, et al.
Publicado: (2026)

Task Diversity Shortens the ICL Plateau
por: Kim, Jaeyeon, et al.
Publicado: (2024)

When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity
por: Feuer, Benjamin, et al.
Publicado: (2025)

GeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding
por: Yan, Yibo, et al.
Publicado: (2024)

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
por: Wang, Yaxuan, et al.
Publicado: (2025)

Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning
por: Wang, Jingyao, et al.
Publicado: (2026)

Is More Context Always Better? Examining LLM Reasoning Capability for Time Interval Prediction
por: Cao, Yanan, et al.
Publicado: (2026)

Not All LLM Reasoners Are Created Equal
por: Hosseini, Arian, et al.
Publicado: (2024)

Exploring Silent Data Corruption as a Reliability Challenge in LLM Training
por: Altenbernd, Anton, et al.
Publicado: (2026)

Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning
por: Mei, Tiehua, et al.
Publicado: (2026)

RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction
por: Ko, Hanbum, et al.
Publicado: (2026)

The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning
por: Zhuang, Ren, et al.
Publicado: (2026)

RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning
por: Hu, Junhao, et al.
Publicado: (2025)

$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
por: Wang, Peihao, et al.
Publicado: (2026)

Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge
por: Vasudeva, Bhavya, et al.
Publicado: (2026)

How do Transformers Learn Implicit Reasoning?
por: Ye, Jiaran, et al.
Publicado: (2025)

ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning
por: Potamitis, Nearchos, et al.
Publicado: (2025)

Nudging the Boundaries of LLM Reasoning
por: Chen, Justin Chih-Yao, et al.
Publicado: (2025)

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training
por: Matsutani, Kohsei, et al.
Publicado: (2026)

Understanding Silent Data Corruption in LLM Training
por: Ma, Jeffrey, et al.
Publicado: (2025)

Differentiable Conformal Training for LLM Reasoning Factuality
por: Hittesdorf, Nathan, et al.
Publicado: (2026)

Step-wise Rubric Rewards for LLM Reasoning
por: Xie, Weichu, et al.
Publicado: (2026)

Towards Understanding Self-play for LLM Reasoning
por: Chae, Justin Yang, et al.
Publicado: (2025)

Enhancing RL Safety with Counterfactual LLM Reasoning
por: Gross, Dennis, et al.
Publicado: (2024)

TabReason: A Reinforcement Learning-Enhanced Reasoning LLM for Explainable Tabular Data Prediction
por: Xu, Tommy, et al.
Publicado: (2025)

Multipole Attention for Efficient Long Context Reasoning
por: Hooper, Coleman, et al.
Publicado: (2025)

Simple Mechanistic Explanations for Out-Of-Context Reasoning
por: Wang, Atticus, et al.
Publicado: (2025)