Image de couverture de livre

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mondorf, Philipp, Wold, Sondre, Plank, Barbara
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models
par: Mondorf, Philipp, et autres
Publié: (2024)

BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
par: Mondorf, Philipp, et autres
Publié: (2025)

Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning
par: Mondorf, Philipp, et autres
Publié: (2024)

Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
par: Mondorf, Philipp, et autres
Publié: (2024)

LogicSkills: A Structured Benchmark for Formal Reasoning in Large Language Models
par: Rabern, Brian, et autres
Publié: (2026)

Reason to Rote: Rethinking Memorization in Reasoning
par: Du, Yupei, et autres
Publié: (2025)

If Probable, Then Acceptable? Understanding Conditional Acceptability Judgments in Large Language Models
par: Orth, Jasmin, et autres
Publié: (2025)

Tracing Uncertainty in Language Model "Reasoning"
par: Grünefeld, Nils, et autres
Publié: (2026)

The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It
par: Bertolazzi, Leonardo, et autres
Publié: (2025)

Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models
par: Cheng, Xinyuan, et autres
Publié: (2026)

Rehearsal-Free Modular and Compositional Continual Learning for Language Models
par: Wang, Mingyang, et autres
Publié: (2024)

To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity
par: Sedova, Anastasiia, et autres
Publié: (2024)

More Room for Language: Investigating the Effect of Retrieval on Language Models
par: Samuel, David, et autres
Publié: (2024)

Circuit Component Reuse Across Tasks in Transformer Language Models
par: Merullo, Jack, et autres
Publié: (2023)

Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination
par: Chen, Qiqi, et autres
Publié: (2024)

Systematic Generalization in Language Models Scales with Information Entropy
par: Wold, Sondre, et autres
Publié: (2025)

Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate
par: Bochkov, A.
Publié: (2025)

From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits
par: Saraipour, Karim, et autres
Publié: (2025)

Compositional Generalization with Grounded Language Models
par: Wold, Sondre, et autres
Publié: (2024)

Estimating Lexical Complexity from Document-Level Distributions
par: Wold, Sondre, et autres
Publié: (2024)

ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior
par: Eichin, Florian, et autres
Publié: (2025)

Composition of Experts: A Modular Compound AI System Leveraging Large Language Models
par: Jain, Swayambhoo, et autres
Publié: (2024)

Language Models Learn Universal Representations of Numbers and Here's Why You Should Care
par: Štefánik, Michal, et autres
Publié: (2025)

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
par: Zhang, Zhongwang, et autres
Publié: (2025)

Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
par: Ahmad, Areeb, et autres
Publié: (2025)

Scalable Data Ablation Approximations for Language Models through Modular Training and Merging
par: Na, Clara, et autres
Publié: (2024)

Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models
par: O'Neill, Charles, et autres
Publié: (2024)

AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models
par: Lyngkhoi, R E Zera Marveen, et autres
Publié: (2026)

Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
par: Baan, Joris, et autres
Publié: (2026)

Discursive Circuits: How Do Language Models Understand Discourse Relations?
par: Miao, Yisong, et autres
Publié: (2025)

Modeling Bilingual Sentence Processing: Evaluating RNN and Transformer Architectures for Cross-Language Structural Priming
par: Zhang, Demi, et autres
Publié: (2024)

Exploring Modularity of Agentic Systems for Drug Discovery
par: van Weesep, Laura, et autres
Publié: (2025)

Learnable Permutation for Structured Sparsity on Transformer Models
par: Li, Zekai, et autres
Publié: (2026)

Large Language Model Agent for Modular Task Execution in Drug Discovery
par: Ock, Janghoon, et autres
Publié: (2025)

What's the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns
par: Hedderich, Michael A., et autres
Publié: (2025)

Exploring Activation Patterns of Parameters in Language Models
par: Wang, Yudong, et autres
Publié: (2024)

Anatomical Heterogeneity in Transformer Language Models
par: Wietrzykowski, Tomasz
Publié: (2026)

Transformer Circuit Faithfulness Metrics are not Robust
par: Miller, Joseph, et autres
Publié: (2024)

Compositional Instruction Following with Language Models and Reinforcement Learning
par: Cohen, Vanya, et autres
Publié: (2025)

CSP-Atlas: Concept-Specific Neural Circuits in a Sparse Python Transformer
par: Wilam, Piotr
Publié: (2026)