Cover Image

Not All Layers of LLMs Are Necessary During Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fan, Siqi, Jiang, Xin, Li, Xiang, Meng, Xuying, Han, Peng, Shang, Shuo, Sun, Aixin, Wang, Yequan, Wang, Zhongyuan
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
by: Fan, Siqi, et al.
Published: (2025)

FLM-101B: An Open LLM and How to Train It with $100K Budget
by: Li, Xiang, et al.
Published: (2023)

Sketch: A Toolkit for Streamlining LLM Operations
by: Jiang, Xin, et al.
Published: (2024)

The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models
by: Fan, Siqi, et al.
Published: (2025)

Toward Embodied AGI: A Review of Embodied AI and the Road Ahead
by: Wang, Yequan, et al.
Published: (2025)

GCRE-GPT: A Generative Model for Comparative Relation Extraction
by: Wang, Yequan, et al.
Published: (2023)

FLM-Audio: Natural Monologues Improves Native Full-Duplex Chatbots via Dual Training
by: Yao, Yiqun, et al.
Published: (2025)

EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Models
by: Yao, Yiqun, et al.
Published: (2025)

Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History
by: Zhong, Qishuai, et al.
Published: (2025)

nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales
by: Yao, Yiqun, et al.
Published: (2023)

Position-Aware Depth Decay Decoding ($D^3$): Boosting Large Language Model Inference Efficiency
by: Fan, Siqi, et al.
Published: (2025)

52B to 1T: Lessons Learned via Tele-FLM Series
by: Li, Xiang, et al.
Published: (2024)

Tele-FLM Technical Report
by: Li, Xiang, et al.
Published: (2024)

Commonsense Knowledge Editing Based on Free-Text in LLMs
by: Huang, Xiusheng, et al.
Published: (2024)

Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning
by: He, Guoxiu, et al.
Published: (2025)

RoboEgo System Card: An Omnimodal Model with Native Full Duplexity
by: Yao, Yiqun, et al.
Published: (2025)

Open-domain Implicit Format Control for Large Language Model Generation
by: Yao, Yiqun, et al.
Published: (2024)

Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language
by: Chen, Xi, et al.
Published: (2025)

NetGPT: Generative Pretrained Transformer for Network Traffic
by: Meng, Xuying, et al.
Published: (2023)

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
by: Chen, Yizhuo, et al.
Published: (2025)

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
by: Shu, Huizhen, et al.
Published: (2025)

Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
by: Li, Wu, et al.
Published: (2026)

Steering When Necessary: Flexible Steering Large Language Models with Backtracking
by: Cheng, Zifeng, et al.
Published: (2025)

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
by: Mu, Junjie, et al.
Published: (2025)

GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs
by: Huang, Wei, et al.
Published: (2026)

Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity
by: Zhang, Bowen, et al.
Published: (2026)

Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
by: Cheng, Sitao, et al.
Published: (2024)

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

All-in-One Tuning and Structural Pruning for Domain-Specific LLMs
by: Lu, Lei, et al.
Published: (2024)

PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator
by: Kong, Chuyi, et al.
Published: (2023)

Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
by: Zhou, Yigeng, et al.
Published: (2026)

Multimodal Reasoning with Multimodal Knowledge Graph
by: Lee, Junlin, et al.
Published: (2024)

Reasons and Solutions for the Decline in Model Performance after Editing
by: Huang, Xiusheng, et al.
Published: (2024)

Multi-View Attention Syntactic Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis
by: Huang, Xiang, et al.
Published: (2025)

Adaptive Layer-skipping in Pre-trained LLMs
by: Luo, Xuan, et al.
Published: (2025)

LLMs Are Prone to Fallacies in Causal Inference
by: Joshi, Nitish, et al.
Published: (2024)

Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!
by: Ma, Yubo, et al.
Published: (2023)

Measuring the Redundancy of Decoder Layers in SpeechLLMs
by: Moumen, Adel, et al.
Published: (2026)

Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
by: Yang, Wang, et al.
Published: (2025)

The Price of Format: Diversity Collapse in LLMs
by: Yun, Longfei, et al.
Published: (2025)