Image de couverture de livre

Predicting LLM Output Length via Entropy-Guided Representations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xie, Huanyi, Chen, Yubin, Wang, Liangyu, Hu, Lijie, Wang, Di
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PAHQ: Accelerating Automated Circuit Discovery through Mixed-Precision Inference Optimization
par: Wang, Xinhai, et autres
Publié: (2025)

Attributing Data for Sharpness-Aware Minimization
par: Ren, Chenyang, et autres
Publié: (2025)

Dissecting Representation Misalignment in Contrastive Learning via Influence Function
par: Hu, Lijie, et autres
Publié: (2024)

Evaluating Data Influence in Meta Learning
par: Ren, Chenyang, et autres
Publié: (2025)

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
par: Jiang, Xinyan, et autres
Publié: (2026)

Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment
par: Xie, Huanyi, et autres
Publié: (2025)

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint
par: Sun, Yi, et autres
Publié: (2025)

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning
par: Zhang, Lin, et autres
Publié: (2025)

Semi-supervised Concept Bottleneck Models
par: Hu, Lijie, et autres
Publié: (2024)

Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
par: Jiang, Xinyan, et autres
Publié: (2025)

Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost
par: Nayab, Sania, et autres
Publié: (2024)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
par: Jiang, Xinyan, et autres
Publié: (2026)

DistZO2: High-Throughput and Memory-Efficient Zeroth-Order Fine-tuning LLMs with Distributed Parallel Computing
par: Wang, Liangyu, et autres
Publié: (2025)

Understanding the Dynamics of Demonstration Conflict in In-Context Learning
par: Jiao, Difan, et autres
Publié: (2026)

Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding
par: Jing, Zihao, et autres
Publié: (2026)

Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
par: Zhang, Jiaming, et autres
Publié: (2026)

Multi-Adapter Representation Interventions via Energy Calibration
par: Yu, Manjiang, et autres
Publié: (2026)

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
par: Yang, Qishun, et autres
Publié: (2026)

Learning Compact Representations of LLM Abilities via Item Response Theory
par: Chen, Jianhao, et autres
Publié: (2025)

Controlling Repetition in Protein Language Models
par: Zhang, Jiahao, et autres
Publié: (2026)

BioELX: Cross-lingual Biomedical Entity Linking via Alias-based Retrieval and LLM Ranking
par: Wang, Yi, et autres
Publié: (2026)

Modification and Generated-Text Detection: Achieving Dual Detection Capabilities for the Outputs of LLM by Watermark
par: Cai, Yuhang, et autres
Publié: (2025)

Text Guided Image Editing with Automatic Concept Locating and Forgetting
par: Li, Jia, et autres
Publié: (2024)

FITRep: Attention-Guided Item Representation via MLLMs
par: Zhang, Guoxiao, et autres
Publié: (2025)

REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature
par: Wu, Wenhan, et autres
Publié: (2025)

Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation
par: Wang, Ziyao, et autres
Publié: (2025)

In-Run Data Shapley for Adam Optimizer
par: Ding, Meng, et autres
Publié: (2026)

Private Language Models via Truncated Laplacian Mechanism
par: Huang, Tianhao, et autres
Publié: (2024)

Perspective Dial: Measuring Perspective of Text and Guiding LLM Outputs
par: Kim, Taejin, et autres
Publié: (2025)

Partitioner Guided Modal Learning Framework
par: Hu, Guimin, et autres
Publié: (2025)

Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
par: Zhang, Xiaoyun, et autres
Publié: (2025)

Neural Combinatorial Optimization Algorithms for Solving Vehicle Routing Problems: A Comprehensive Survey with Perspectives
par: Wu, Xuan, et autres
Publié: (2024)

When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs
par: Zhang, Zhuoran, et autres
Publié: (2025)

Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval
par: Wang, Linlin, et autres
Publié: (2026)

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
par: Xing, Wenpeng, et autres
Publié: (2025)

Geometry Guided Self-Consistency for Physical AI
par: Dai, Yinwei, et autres
Publié: (2026)

PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration
par: Yu, Manjiang, et autres
Publié: (2025)

CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing
par: Wang, Zixia, et autres
Publié: (2025)

EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentation
par: Li, Zihang, et autres
Publié: (2026)

LengthLogD: A Length-Stratified Ensemble Framework for Enhanced Peptide Lipophilicity Prediction via Multi-Scale Feature Integration
par: Wu, Shuang, et autres
Publié: (2025)