Cover Image

Causal Evidence that Language Models use Confidence to Drive Behavior

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kumaran, Dharshan, Daw, Nathaniel, Osindero, Simon, Veličković, Petar, Patraucean, Viorica
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals
by: Kumaran, Dharshan, et al.
Published: (2026)

How do LLMs Compute Verbal Confidence
by: Kumaran, Dharshan, et al.
Published: (2026)

How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models
by: Kumaran, Dharshan, et al.
Published: (2025)

Perplexity Cannot Always Tell Right from Wrong
by: Veličković, Petar, et al.
Published: (2026)

Transformers need glasses! Information over-squashing in language tasks
by: Barbero, Federico, et al.
Published: (2024)

Leveraging Classical Algorithms for Graph Neural Networks
by: Wu, Jason, et al.
Published: (2025)

Recurrent Aggregators in Neural Algorithmic Reasoning
by: Xu, Kaijia, et al.
Published: (2024)

Parallel Algorithms Align with Neural Execution
by: Engelmayer, Valerie, et al.
Published: (2023)

Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmark
by: Heyward, Joseph, et al.
Published: (2024)

Latent Space Representations of Neural Algorithmic Reasoners
by: Mirjanić, Vladimir V., et al.
Published: (2023)

Commute-Time-Optimised Graphs for GNNs
by: Sterner, Igor, et al.
Published: (2024)

Cayley Graph Propagation
by: Wilson, JJ, et al.
Published: (2024)

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

TRecViT: A Recurrent Video Transformer
by: Pătrăucean, Viorica, et al.
Published: (2024)

KNARsack: Teaching Neural Algorithmic Reasoners to Solve Pseudo-Polynomial Problems
by: Požgaj, Stjepan, et al.
Published: (2025)

Wanting to be Understood
by: Fernando, Chrisantha, et al.
Published: (2025)

Softmax is not Enough (for Sharp Size Generalisation)
by: Veličković, Petar, et al.
Published: (2024)

Temporal Graph Rewiring with Expander Graphs
by: Petrović, Katarina, et al.
Published: (2024)

NAR-*ICP: Neural Execution of Classical ICP-based Pointcloud Registration Algorithms
by: Panagiotaki, Efimia, et al.
Published: (2024)

Asynchronous Algorithmic Alignment with Cocycles
by: Dudzik, Andrew, et al.
Published: (2023)

What makes a good feedforward computational graph?
by: Vitvitskyi, Alex, et al.
Published: (2025)

Mining Generalizable Activation Functions
by: Vitvitskyi, Alex, et al.
Published: (2026)

The Illusion of Stochasticity in LLMs
by: Gu, Xiangming, et al.
Published: (2026)

Filter Equivariant Functions: A symmetric account of length-general extrapolation on lists
by: Lewis, Owen, et al.
Published: (2025)

Program-Based Strategy Induction for Reinforcement Learning
by: Correa, Carlos G., et al.
Published: (2024)

Language models show human-like content effects on reasoning tasks
by: Dasgupta, Ishita, et al.
Published: (2022)

How does over-squashing affect the power of GNNs?
by: Di Giovanni, Francesco, et al.
Published: (2023)

Positional Attention: Expressivity and Learnability of Algorithmic Computation
by: de Luca, Artur Back, et al.
Published: (2024)

Are UFOs Driving Innovation? The Illusion of Causality in Large Language Models
by: Carro, María Victoria, et al.
Published: (2024)

CATTO: Balancing Preferences and Confidence in Language Models
by: Parikh, Nisarg, et al.
Published: (2026)

Dagma-DCE: Interpretable, Non-Parametric Differentiable Causal Discovery
by: Waxman, Daniel, et al.
Published: (2024)

Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical Systems
by: Butler, Kurt, et al.
Published: (2024)

Confidence Calibration in Large Language Models
by: Michael, Noam, et al.
Published: (2026)

Confidence in the Reasoning of Large Language Models
by: Pawitan, Yudi, et al.
Published: (2024)

Confidence Calibration in Vision-Language-Action Models
by: Zollo, Thomas P, et al.
Published: (2025)

Modeling Personalized Difficulty of Rehabilitation Exercises Using Causal Trees
by: Dennler, Nathaniel, et al.
Published: (2025)

Confidence Regularized Masked Language Modeling using Text Length
by: Ji, Seunghyun, et al.
Published: (2025)

Structural Causal Bottleneck Models
by: Bing, Simon, et al.
Published: (2026)

Confidence over Time: Confidence Calibration with Temporal Logic for Large Language Model Reasoning
by: Mao, Zhenjiang, et al.
Published: (2026)

MaD Physics: Evaluating information seeking under constraints in physical environments
by: Jain, Moksh, et al.
Published: (2026)