Imagen de Portada

Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fan, Sinan, Xie, Liang, Shen, Chen, Teng, Ge, Yuan, Xiaosong, Zhang, Xiaofeng, Huang, Chenxi, Wang, Wenxiao, He, Xiaofei, Ye, Jieping
Formato:	Preprint
Publicado:	2025
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

Instance-adaptive Zero-shot Chain-of-Thought Prompting
por: Yuan, Xiaosong, et al.
Publicado: (2024)

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
por: Zhang, Xiaofeng, et al.
Publicado: (2024)

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning
por: Xin, Yue, et al.
Publicado: (2025)

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning
por: Huang, Chenxi, et al.
Publicado: (2025)

Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models
por: Yan, Shaotian, et al.
Publicado: (2025)

Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
por: Wang, Bing, et al.
Publicado: (2026)

Concise and Organized Perception Facilitates Reasoning in Large Language Models
por: Liu, Junjie, et al.
Publicado: (2023)

On the Step Length Confounding in LLM Reasoning Data Selection
por: Wang, Bing, et al.
Publicado: (2026)

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models
por: Liu, Kaiyuan, et al.
Publicado: (2025)

Controlling Thinking Speed in Reasoning Models
por: Lin, Zhengkai, et al.
Publicado: (2025)

SciPIP: An LLM-based Scientific Paper Idea Proposer
por: Wang, Wenxiao, et al.
Publicado: (2024)

Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
por: Xiao, Yuxin, et al.
Publicado: (2024)

Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption
por: Wang, Wenxiao, et al.
Publicado: (2025)

ART: Attention Replacement Technique to Improve Factuality in LLMs
por: Luo, Ziqin, et al.
Publicado: (2026)

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
por: Yan, Shaotian, et al.
Publicado: (2026)

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs
por: Zhang, Xiaofeng, et al.
Publicado: (2024)

Towards Quantum Accelerated Large-scale Topology Optimization
por: Ye, Zisheng, et al.
Publicado: (2025)

Reasoning Fails Where Step Flow Breaks
por: Xu, Xiaoyu, et al.
Publicado: (2026)

Discrete Variable Topology Optimization Using Multi-Cut Formulation and Adaptive Trust Regions
por: Ye, Zisheng, et al.
Publicado: (2024)

URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View Clustering
por: Teng, Ge, et al.
Publicado: (2024)

InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
por: Li, Ke, et al.
Publicado: (2026)

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
por: Shen, Yifan, et al.
Publicado: (2025)

Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
por: Lin, Zhengkai, et al.
Publicado: (2024)

Hallucination Begins Where Saliency Drops
por: Zhang, Xiaofeng, et al.
Publicado: (2026)

Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
por: Wang, Bing, et al.
Publicado: (2026)

CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery
por: Zhang, Chenghao, et al.
Publicado: (2025)

PD-APE: A Parallel Decoding Framework with Adaptive Position Encoding for 3D Visual Grounding
por: Hou, Chenshu, et al.
Publicado: (2024)

Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs
por: Pan, Zhiyu, et al.
Publicado: (2026)

Trust Region Methods For Nonconvex Stochastic Optimization Beyond Lipschitz Smoothness
por: Xie, Chenghan, et al.
Publicado: (2023)

ChartBench: A Benchmark for Complex Visual Reasoning in Charts
por: Xu, Zhengzhuo, et al.
Publicado: (2023)

Prompt Stability in Code LLMs: Measuring Sensitivity across Emotion- and Personality-Driven Variations
por: Ma, Wei, et al.
Publicado: (2025)

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
por: Chen, Wei, et al.
Publicado: (2024)

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models
por: Zhao, Qiyan, et al.
Publicado: (2025)

Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger
por: Yang, Qi, et al.
Publicado: (2025)

Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
por: Cheng, Junhao, et al.
Publicado: (2025)

Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning
por: Rui, Shaohao, et al.
Publicado: (2025)

Visual prompting reimagined: The power of the Activation Prompts
por: Zhang, Yihua, et al.
Publicado: (2026)

HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
por: Shi, Zhiyuan, et al.
Publicado: (2026)

On the Vulnerability of FHE Computation to Silent Data Corruption
por: Mu, Jianan, et al.
Publicado: (2026)

NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior
por: Shi, Dongbo, et al.
Publicado: (2025)