Copertina

Let's Think Dot by Dot: Hidden Computation in Transformer Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Pfau, Jacob, Merrill, William, Bowman, Samuel R.
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence I.2.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Training Language Models to Win Debates with Self-Play Improves Judge Accuracy
di: Arnesen, Samuel, et al.
Pubblicazione: (2024)

Point of Order: Action-Aware LLM Persona Modeling for Realistic Civic Simulation
di: Merrill, Scott, et al.
Pubblicazione: (2025)

Towards Understanding Sycophancy in Language Models
di: Sharma, Mrinank, et al.
Pubblicazione: (2023)

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models
di: Young, Richard J.
Pubblicazione: (2026)

Categorical Perception in Large Language Model Hidden States: Structural Warping at Digit-Count Boundaries
di: Cacioli, Jon-Paul
Pubblicazione: (2026)

Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models
di: Singh, Arth
Pubblicazione: (2026)

Machine Unlearning for Masked Diffusion Language Models
di: Lee, Georu, et al.
Pubblicazione: (2026)

Truth as a Compression Artifact in Language Model Training
di: Krestnikov, Konstantin
Pubblicazione: (2026)

Intention Collapse: Intention-Level Metrics for Reasoning in Language Models
di: Vera, Patricio
Pubblicazione: (2026)

Prototype Transformer: Towards Language Model Architectures Interpretable by Design
di: Yordanov, Yordan, et al.
Pubblicazione: (2026)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
di: Fadli, Samih
Pubblicazione: (2025)

Distributed Multi-Layer Editing for Rule-Level Knowledge in Large Language Models
di: Wang, Yating, et al.
Pubblicazione: (2026)

Assessing Large Language Models on Islamic Legal Reasoning: Evidence from Inheritance Law Evaluation
di: Bouchekif, Abdessalam, et al.
Pubblicazione: (2025)

Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence
di: Ren, Wanying, et al.
Pubblicazione: (2026)

SECURA: Sigmoid-Enhanced CUR Decomposition with Uninterrupted Retention and Low-Rank Adaptation in Large Language Models
di: Zhang, Yuxuan
Pubblicazione: (2025)

RMGAP: Benchmarking the Generalization of Reward Models across Diverse Preferences
di: Zhou, Yangyang, et al.
Pubblicazione: (2026)

MeMo: Towards Language Models with Associative Memory Mechanisms
di: Zanzotto, Fabio Massimo, et al.
Pubblicazione: (2025)

ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law
di: Shportun, Nazarii
Pubblicazione: (2026)

CRAFT: Clustered Regression for Adaptive Filtering of Training data
di: Panda, Parthasarathi, et al.
Pubblicazione: (2026)

Mitigating Hallucinations in Zero-Shot Scientific Summarisation: A Pilot Study
di: Jaaouine, Imane, et al.
Pubblicazione: (2025)

EMA Is Not All You Need: Mapping the Boundary Between Structure and Content in Recurrent Context
di: Singh, Arth
Pubblicazione: (2026)

Graph Memory Transformer (GMT)
di: Zanarini, Nicola, et al.
Pubblicazione: (2026)

Towards Ontology-Enhanced Representation Learning for Large Language Models
di: Ronzano, Francesco, et al.
Pubblicazione: (2024)

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
di: Zhang, Gongbo, et al.
Pubblicazione: (2026)

Evaluating Large Language Models for IUCN Red List Species Information
di: Uryu, Shinya
Pubblicazione: (2025)

Thinker: Learning to Think Fast and Slow
di: Chung, Stephen, et al.
Pubblicazione: (2025)

Domain-Specific Pretraining of Language Models: A Comparative Study in the Medical Field
di: Kerner, Tobias
Pubblicazione: (2024)

Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop Reasoning
di: Adapala, Sai Teja Reddy
Pubblicazione: (2025)

Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models
di: Cui, Sasha, et al.
Pubblicazione: (2025)

No Free Swap: Protocol-Dependent Layer Redundancy in Transformers
di: Garcia, Gabriel
Pubblicazione: (2026)

Weakly Supervised Distillation of Hallucination Signals into Transformer Representations
di: Salehmohamed, Shoaib Sadiq, et al.
Pubblicazione: (2026)

Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B
di: Cacioli, Jon-Paul
Pubblicazione: (2026)

Exemplar Retrieval Without Overhypothesis Induction: Limits of Distributional Sequence Learning in Early Word Learning
di: Cacioli, Jon-Paul
Pubblicazione: (2026)

Align and Shine: Building High-Quality Sentence-Aligned Corpora for Multilingual Text Simplification
di: Hilasaca, Kenji, et al.
Pubblicazione: (2026)

Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs
di: Keeman, Michael
Pubblicazione: (2026)

KAConvText: Novel Approach to Burmese Sentence Classification using Kolmogorov-Arnold Convolution
di: Thu, Ye Kyaw, et al.
Pubblicazione: (2025)

When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR)
di: Agarwal, Mahak, et al.
Pubblicazione: (2025)

The Pragmatic Persona: Discovering LLM Persona through Bridging Inference
di: Yang, Jisoo, et al.
Pubblicazione: (2026)

A Hierarchical Error Framework for Reliable Automated Coding in Communication Research: Applications to Health and Political Communication
di: Zhao, Zhilong, et al.
Pubblicazione: (2025)

Bridging the Reasoning Gap: Small LLMs Can Plan with Generalised Strategies
di: Borro, Andrey, et al.
Pubblicazione: (2025)