Cover Image

On the Predictive Power of Representation Dispersion in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yanhong, Li, Ming, Livescu, Karen, Zhou, Jiawei
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Chunk-Distilled Language Modeling
by: Li, Yanhong, et al.
Published: (2024)

OKBench: Democratizing LLM Evaluation with Fully Automated, On-Demand, Open Knowledge Benchmarking
by: Li, Yanhong, et al.
Published: (2025)

Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs
by: Li, Yanhong, et al.
Published: (2025)

Cross-Modal Taxonomic Generalization in (Vision-) Language Models
by: Xu, Tianyang, et al.
Published: (2026)

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
by: Li, Ming, et al.
Published: (2024)

Distilling to Hybrid Attention Models via KL-Guided Layer Selection
by: Li, Yanhong, et al.
Published: (2025)

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
by: Li, Ming, et al.
Published: (2025)

Towards Robust Speech Representation Learning for Thousands of Languages
by: Chen, William, et al.
Published: (2024)

SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale
by: Gueuwou, Shester, et al.
Published: (2024)

Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling
by: Chou, Ju-Chieh, et al.
Published: (2025)

Psychometric Predictive Power of Large Language Models
by: Kuribayashi, Tatsuki, et al.
Published: (2023)

Semantic Representation Attack against Aligned Large Language Models
by: Lian, Jiawei, et al.
Published: (2025)

N-gram Prediction and Word Difference Representations for Language Modeling
by: Heo, DongNyeong, et al.
Published: (2024)

Retrieval-based Disentangled Representation Learning with Natural Language Supervision
by: Zhou, Jiawei, et al.
Published: (2022)

PLDR-LLM: Large Language Model from Power Law Decoder Representations
by: Gokden, Burc
Published: (2024)

Active Use of Latent Constituency Representation in both Humans and Large Language Models
by: Liu, Wei, et al.
Published: (2024)

Unlocking the Power of Large Language Models for Entity Alignment
by: Jiang, Xuhui, et al.
Published: (2024)

Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models
by: Zhou, Andy
Published: (2025)

HintMR: Eliciting Stronger Mathematical Reasoning in Small Language Models
by: Hossain, Jawad, et al.
Published: (2026)

Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes
by: Li, Meng, et al.
Published: (2025)

Context Structure Reshapes the Representational Geometry of Language Models
by: Hosseini, Eghbal A., et al.
Published: (2026)

ElectriQ: A Benchmark for Assessing the Response Capability of Large Language Models in Power Marketing
by: Wang, Jinzhi, et al.
Published: (2025)

Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
by: Srey, Ponhvoan, et al.
Published: (2026)

DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
by: Sun, Jiashuo, et al.
Published: (2025)

Language Model Representations for Efficient Few-Shot Tabular Classification
by: Kang, Inwon, et al.
Published: (2026)

Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer
by: Liu, Boan, et al.
Published: (2023)

Research on Predicting Public Opinion Event Heat Levels Based on Large Language Models
by: Ren, Yi, et al.
Published: (2024)

Large Language Model Enhanced Knowledge Representation Learning: A Survey
by: Wang, Xin, et al.
Published: (2024)

GRAMMAR: Grounded and Modular Methodology for Assessment of Closed-Domain Retrieval-Augmented Language Model
by: Li, Xinzhe, et al.
Published: (2024)

Information Capacity: Evaluating the Efficiency of Large Language Models via Text Compression
by: Yuan, Cheng, et al.
Published: (2025)

METEOR: Evolutionary Journey of Large Language Models from Guidance to Self-Growth
by: Li, Jiawei, et al.
Published: (2024)

Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models
by: Feng, Yujie, et al.
Published: (2026)

Unveiling and Addressing Pseudo Forgetting in Large Language Models
by: Sun, Huashan, et al.
Published: (2024)

Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models
by: Icard, Benjamin, et al.
Published: (2025)

BeSimulator: A Large Language Model Powered Text-based Behavior Simulator
by: Wang, Jianan, et al.
Published: (2024)

Investigating Instruction Tuning Large Language Models on Graphs
by: Zhu, Kerui, et al.
Published: (2024)

Principled Detection of Hallucinations in Large Language Models via Multiple Testing
by: Li, Jiawei, et al.
Published: (2025)

Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective
by: Li, Tianlong, et al.
Published: (2024)

Hallucination Detection with Small Language Models
by: Cheung, Ming
Published: (2025)

Improving Contextual ASR via Multi-grained Fusion with Large Language Models
by: Zhou, Shilin, et al.
Published: (2025)