Cover Image

Vector Arithmetic in Concept and Token Subspaces

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feucht, Sheridan, Wallace, Byron, Bau, David
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
by: Feucht, Sheridan, et al.
Published: (2024)

The Dual-Route Model of Induction
by: Feucht, Sheridan, et al.
Published: (2025)

Erasing Conceptual Knowledge from Language Models
by: Gandikota, Rohit, et al.
Published: (2024)

Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
by: Pal, Koyena, et al.
Published: (2023)

In-Context Learning Without Copying
by: Sahin, Kerem, et al.
Published: (2025)

Function Vectors in Large Language Models
by: Todd, Eric, et al.
Published: (2023)

Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
by: Ahsan, Hiba, et al.
Published: (2025)

Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
by: Feucht, Sheridan, et al.
Published: (2026)

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
by: Zhao, Haiyan, et al.
Published: (2024)

Can SAEs reveal and mitigate racial biases of LLMs in healthcare?
by: Ahsan, Hiba, et al.
Published: (2025)

Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation
by: Ramprasad, Sanjana, et al.
Published: (2024)

Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic
by: Reif, Yuval, et al.
Published: (2025)

Unsupervised Concept Vector Extraction for Bias Control in LLMs
by: Cyberey, Hannah, et al.
Published: (2025)

Circuit Distillation
by: Wadhwa, Somin, et al.
Published: (2025)

Revisiting Relation Extraction in the era of Large Language Models
by: Wadhwa, Somin, et al.
Published: (2023)

Investigating Mysteries of CoT-Augmented Distillation
by: Wadhwa, Somin, et al.
Published: (2024)

Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic
by: Zbeeb, Mohammad, et al.
Published: (2025)

Locating and Editing Factual Associations in Mamba
by: Sharma, Arnab Sen, et al.
Published: (2024)

Who Taught You That? Tracing Teachers in Model Distillation
by: Wadhwa, Somin, et al.
Published: (2025)

Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical Study
by: Sun, Zhaoyue, et al.
Published: (2024)

Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach
by: Shirafuji, Daiki, et al.
Published: (2024)

Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits
by: Zhang, Xiang, et al.
Published: (2025)

Beyond Tokens: Concept-Level Training Objectives for LLMs
by: Iyer, Laya, et al.
Published: (2026)

Measuring AI "Slop" in Text
by: Shaib, Chantal, et al.
Published: (2025)

Detection and Measurement of Syntactic Templates in Generated Text
by: Shaib, Chantal, et al.
Published: (2024)

Language Models Implement Simple Word2Vec-style Vector Arithmetic
by: Merullo, Jack, et al.
Published: (2023)

Breaking Token Into Concepts: Exploring Extreme Compression in Token Representation Via Compositional Shared Semantics
by: R V, Kavin, et al.
Published: (2025)

Automatically Extracting Numerical Results from Randomized Controlled Trials with Large Language Models
by: Yun, Hye Sun, et al.
Published: (2024)

Controlling Large Language Models Through Concept Activation Vectors
by: Zhang, Hanyu, et al.
Published: (2025)

[b]=[d]-[t]+[p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic
by: Choi, Kwanghee, et al.
Published: (2026)

Learning from Natural Language Explanations for Generalizable Entity Matching
by: Wadhwa, Somin, et al.
Published: (2024)

Do explanations generalize across large reasoning models?
by: Pal, Koyena, et al.
Published: (2026)

From Tokens to Concepts: Leveraging SAE for SPLADE
by: Zong, Yuxuan, et al.
Published: (2026)

Compared to What? Baselines and Metrics for Counterfactual Prompting
by: Yang, Zihao, et al.
Published: (2026)

Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank
by: Roy, Debjyoti Saha, et al.
Published: (2024)

StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis
by: Tang, Zecheng, et al.
Published: (2024)

Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors
by: Lyngbaek, Laurits, et al.
Published: (2026)

Concept Tokens: Learning Behavioral Embeddings Through Concept Definitions
by: Sastre, Ignacio, et al.
Published: (2026)

Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models
by: Zhang, Christine, et al.
Published: (2026)

Rethinking the Role of Token Retrieval in Multi-Vector Retrieval
by: Lee, Jinhyuk, et al.
Published: (2023)