Cover Image

Latent Concept Disentanglement in Transformer-based Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Guan Zhe, Vasudeva, Bhavya, Sharan, Vatsal, Rashtchian, Cyrus, Raghavan, Prabhakar, Panigrahy, Rina
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
by: Hong, Guan Zhe, et al.
Published: (2024)

Limitations on Accurate, Trusted, Human-level Reasoning
by: Panigrahy, Rina, et al.
Published: (2025)

Transformers Learn Low Sensitivity Functions: Investigations and Implications
by: Vasudeva, Bhavya, et al.
Published: (2024)

Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge
by: Vasudeva, Bhavya, et al.
Published: (2026)

In-Context Occam's Razor: How Transformers Prefer Simpler Hypotheses on the Fly
by: Deora, Puneesh, et al.
Published: (2025)

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
by: Zhang, Jianyi, et al.
Published: (2024)

Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression
by: Fu, Deqing, et al.
Published: (2023)

Convergent Evolution: How Different Language Models Learn Similar Number Representations
by: Fu, Deqing, et al.
Published: (2026)

Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks
by: Vatsal, Shubham, et al.
Published: (2025)

Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models
by: Ramjee, Sharan
Published: (2026)

The Rich and the Simple: On the Implicit Bias of Adam and SGD
by: Vasudeva, Bhavya, et al.
Published: (2025)

How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data
by: Vasudeva, Bhavya, et al.
Published: (2025)

Emotion Classification in Low and Moderate Resource Languages
by: Tafreshi, Shabnam, et al.
Published: (2024)

AI-rithmetic
by: Bie, Alex, et al.
Published: (2026)

Variational Language Concepts for Interpreting Foundation Language Models
by: Wang, Hengyi, et al.
Published: (2024)

Simple Mechanisms for Representing, Indexing and Manipulating Concepts
by: Li, Yuanzhi, et al.
Published: (2023)

StagFormer: Time Staggering Transformer Decoding for RunningLayers In Parallel
by: Cutler, Dylan, et al.
Published: (2025)

Can GPT Redefine Medical Understanding? Evaluating GPT on Biomedical Machine Reading Comprehension
by: Vatsal, Shubham, et al.
Published: (2024)

Revisiting the Shape Convention of Transformer Language Models
by: Liao, Feng-Ting, et al.
Published: (2026)

Disentangling Exploration of Large Language Models by Optimal Exploitation
by: Grams, Tim, et al.
Published: (2025)

Fair In-Context Learning via Latent Concept Variables
by: Bhaila, Karuna, et al.
Published: (2024)

Luna-2: Scalable Single-Token Evaluation with Small Language Models
by: Goel, Vatsal, et al.
Published: (2026)

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
by: Mueller, Aaron, et al.
Published: (2025)

Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods
by: Blum, Avrim, et al.
Published: (2025)

Can GPT Improve the State of Prior Authorization via Guideline Based Automated Question Answering?
by: Vatsal, Shubham, et al.
Published: (2024)

Fast Byte Latent Transformer
by: Kallini, Julie, et al.
Published: (2026)

LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback
by: Mura, Raffaele, et al.
Published: (2025)

Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities
by: Hua, Wenyue, et al.
Published: (2024)

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
by: Su, Jingtong, et al.
Published: (2025)

Large Language Models Explore by Latent Distilling
by: Zeng, Yuanhao, et al.
Published: (2026)

Causal Language Modeling Can Elicit Search and Reasoning Capabilities on Logic Puzzles
by: Shah, Kulin, et al.
Published: (2024)

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
by: Jin, Mingyu, et al.
Published: (2024)

The Geometry of Categorical and Hierarchical Concepts in Large Language Models
by: Park, Kiho, et al.
Published: (2024)

Latent Principle Discovery for Language Model Self-Improvement
by: Ramji, Keshav, et al.
Published: (2025)

Discovering Latent Knowledge in Language Models Without Supervision
by: Burns, Collin, et al.
Published: (2022)

Eliciting Latent Knowledge from Quirky Language Models
by: Mallen, Alex, et al.
Published: (2023)

Patch-Level Tokenization with CNN Encoders and Attention for Improved Transformer Time-Series Forecasting
by: Nagrath, Saurish, et al.
Published: (2026)

Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
by: Duan, Jinhao, et al.
Published: (2023)

Reasoning with Latent Thoughts: On the Power of Looped Transformers
by: Saunshi, Nikunj, et al.
Published: (2025)

Cross-Layer Discrete Concept Discovery for Interpreting Language Models
by: Garg, Ankur, et al.
Published: (2025)