Cover Image

Language Models Encode the Value of Numbers Linearly

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Fangwei, Dai, Damai, Sui, Zhifang
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exploring Activation Patterns of Parameters in Language Models
by: Wang, Yudong, et al.
Published: (2024)

CoLT: Reasoning with Chain of Latent Tool Calls
by: Zhu, Fangwei, et al.
Published: (2026)

Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning
by: Yang, Zhe, et al.
Published: (2023)

Reducing Hallucinations in Entity Abstract Summarization with Facts-Template Decomposition
by: Zhu, Fangwei, et al.
Published: (2024)

Chain-of-Thought Tokens are Computer Program Variables
by: Zhu, Fangwei, et al.
Published: (2025)

Chip-Tuning: Classify Before Language Models Say
by: Zhu, Fangwei, et al.
Published: (2024)

Large Language Models Struggle with Unreasonability in Math Problems
by: Ma, Jingyuan, et al.
Published: (2024)

RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection
by: Yang, Yixin, et al.
Published: (2025)

PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization
by: Meng, Xiangdi, et al.
Published: (2024)

Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
by: Wang, Peiyi, et al.
Published: (2023)

Emergence of Linear Truth Encodings in Language Models
by: Ravfogel, Shauli, et al.
Published: (2025)

Self-Boosting Large Language Models with Synthetic Preference Data
by: Dong, Qingxiu, et al.
Published: (2024)

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
by: Dai, Damai, et al.
Published: (2024)

Towards Harmonized Uncertainty Estimation for Large Language Models
by: Li, Rui, et al.
Published: (2025)

Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens
by: Luo, Weiyao, et al.
Published: (2024)

Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models
by: Wang, Zihan, et al.
Published: (2024)

Can Large Multimodal Models Uncover Deep Semantics Behind Images?
by: Yang, Yixin, et al.
Published: (2024)

Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?
by: Yang, Zhe, et al.
Published: (2024)

HistLens: Mapping Idea Change across Concepts and Corpora
by: Jing, Yi, et al.
Published: (2026)

Towards Better RL Training Data Utilization via Second-Order Rollout
by: Yang, Zhe, et al.
Published: (2026)

CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games
by: Xu, Shuhang, et al.
Published: (2025)

Confabulation: The Surprising Value of Large Language Model Hallucinations
by: Sui, Peiqi, et al.
Published: (2024)

Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts
by: Wang, Lean, et al.
Published: (2024)

A Survey on In-context Learning
by: Dong, Qingxiu, et al.
Published: (2022)

Large Language Models Encode Semantics and Alignment in Linearly Separable Representations
by: Saglam, Baturay, et al.
Published: (2025)

Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
by: Xia, Heming, et al.
Published: (2024)

Plug-and-Play Training Framework for Preference Optimization
by: Ma, Jingyuan, et al.
Published: (2024)

Enhancing Reliability across Short and Long-Form QA via Reinforcement Learning
by: Wang, Yudong, et al.
Published: (2025)

LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking
by: Xin, Amy, et al.
Published: (2024)

CtrlRAG: Black-box Document Poisoning Attacks for Retrieval-Augmented Generation of Large Language Models
by: Sui, Runqi
Published: (2025)

Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution
by: Zhang, Long, et al.
Published: (2026)

NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoning
by: Schwartz, Eli, et al.
Published: (2024)

Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs
by: Yang, Zhe, et al.
Published: (2024)

Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming
by: Li, Rui, et al.
Published: (2025)

A Probabilistic Inference Scaling Theory for LLM Self-Correction
by: Yang, Zhe, et al.
Published: (2025)

Time is Encoded in the Weights of Finetuned Language Models
by: Nylund, Kai, et al.
Published: (2023)

From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling
by: Chen, Zhengyu, et al.
Published: (2025)

HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Models
by: Dai, Chang, et al.
Published: (2025)

Long-Context Language Modeling with Parallel Context Encoding
by: Yen, Howard, et al.
Published: (2024)

CoUDA: Coherence Evaluation via Unified Data Augmentation
by: Zhu, Dawei, et al.
Published: (2024)