Cover Image

ParaScopes: What do Language Models Activations Encode About Future Text?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pochinkov, Nicky, Volkova, Yulia, Vasileva, Anna, Chereddy, Sai V R
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Tokens in Language Models: Interpreting Activations through Text Genre Chunks
by: Benito-Rodriguez, Éloïse, et al.
Published: (2025)

Dissecting Language Models: Machine Unlearning via Selective Pruning
by: Pochinkov, Nicholas, et al.
Published: (2024)

Attention Gathers, MLPs Compose: A Causal Analysis of an Action-Outcome Circuit in VideoViT
by: Chereddy, Sai V R
Published: (2026)

Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning
by: Damirchi, Hamed, et al.
Published: (2026)

What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices
by: Noels, Sander, et al.
Published: (2025)

Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation
by: Messina, Pablo, et al.
Published: (2024)

SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation
by: Chereddy, Sathvik, et al.
Published: (2025)

Reducing the Scope of Language Models
by: Yunis, David, et al.
Published: (2024)

Investigating Neuron Ablation in Attention Heads: The Case for Peak Activation Centering
by: Pochinkov, Nicholas, et al.
Published: (2024)

Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts
by: Somayajula, Sai Ashish, et al.
Published: (2024)

Multilingual Language Models Encode Script Over Linguistic Structure
by: Verma, Aastha A K, et al.
Published: (2026)

PairBench: Are Vision-Language Models Reliable at Comparing What They See?
by: Feizi, Aarash, et al.
Published: (2025)

Massive Activations in Large Language Models
by: Sun, Mingjie, et al.
Published: (2024)

Steering Language Models With Activation Engineering
by: Turner, Alexander Matt, et al.
Published: (2023)

Language Models over Canonical Byte-Pair Encodings
by: Vieira, Tim, et al.
Published: (2025)

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

What Do Self-Supervised Speech Models Know About Words?
by: Pasad, Ankita, et al.
Published: (2023)

Round and Round We Go! What makes Rotary Positional Encodings useful?
by: Barbero, Federico, et al.
Published: (2024)

Spectral Editing of Activations for Large Language Model Alignment
by: Qiu, Yifu, et al.
Published: (2024)

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

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
by: Deng, Boyi, et al.
Published: (2026)

On the Semantic and Syntactic Information Encoded in Proto-Tokens for One-Step Text Reconstruction
by: Bondarenko, Ivan, et al.
Published: (2026)

Improved Out-of-Scope Intent Classification with Dual Encoding and Threshold-based Re-Classification
by: Zawbaa, Hossam M., et al.
Published: (2024)

First Activations Matter: Training-Free Methods for Dynamic Activation in Large Language Models
by: Ma, Chi, et al.
Published: (2024)

TextLap: Customizing Language Models for Text-to-Layout Planning
by: Chen, Jian, et al.
Published: (2024)

Still "Talking About Large Language Models": Some Clarifications
by: Shanahan, Murray
Published: (2024)

NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models
by: Liu, Weiqi, et al.
Published: (2026)

LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations
by: Lugoloobi, William, et al.
Published: (2026)

Spherical Steering: Geometry-Aware Activation Rotation for Language Models
by: You, Zejia, et al.
Published: (2026)

ActTail: Global Activation Sparsity in Large Language Models
by: Hou, Wenwen, et al.
Published: (2026)

Contextual Text Denoising with Masked Language Models
by: Sun, Yifu, et al.
Published: (2019)

Ensembling Finetuned Language Models for Text Classification
by: Arango, Sebastian Pineda, et al.
Published: (2024)

EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
by: Lee, Che Hyun, et al.
Published: (2025)

What Evidence Do Language Models Find Convincing?
by: Wan, Alexander, et al.
Published: (2024)

What is Wrong with Perplexity for Long-context Language Modeling?
by: Fang, Lizhe, et al.
Published: (2024)

MedSyn: LLM-based Synthetic Medical Text Generation Framework
by: Kumichev, Gleb, et al.
Published: (2024)

Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation
by: Li, Zhuohang, et al.
Published: (2024)

P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models
by: Liu, Yuhan, et al.
Published: (2023)

Distributional Surgery for Language Model Activations
by: Nguyen, Bao, et al.
Published: (2025)

Federated Large Language Models: Current Progress and Future Directions
by: Yao, Yuhang, et al.
Published: (2024)