Copertina

Tracing Uncertainty in Language Model "Reasoning"

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Grünefeld, Nils, Højer, Bertram, Mondorf, Philipp, Plank, Barbara, Rogers, Anna, Hardmeier, Christian, Heinrich, Stefan, Frellsen, Jes
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms
di: Grünefeld, Nils, et al.
Pubblicazione: (2026)

Improving Reasoning Performance in Large Language Models via Representation Engineering
di: Højer, Bertram, et al.
Pubblicazione: (2025)

Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning
di: Mondorf, Philipp, et al.
Pubblicazione: (2024)

Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
di: Mondorf, Philipp, et al.
Pubblicazione: (2024)

On the Notion that Language Models Reason
di: Højer, Bertram
Pubblicazione: (2025)

LogicSkills: A Structured Benchmark for Formal Reasoning in Large Language Models
di: Rabern, Brian, et al.
Pubblicazione: (2026)

The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It
di: Bertolazzi, Leonardo, et al.
Pubblicazione: (2025)

Language Models Learn Universal Representations of Numbers and Here's Why You Should Care
di: Štefánik, Michal, et al.
Pubblicazione: (2025)

Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models
di: Mondorf, Philipp, et al.
Pubblicazione: (2024)

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
di: Mondorf, Philipp, et al.
Pubblicazione: (2024)

Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing
di: Ulmer, Dennis, et al.
Pubblicazione: (2025)

Compositional-ARC: Assessing Systematic Generalization in Abstract Spatial Reasoning
di: Mondorf, Philipp, et al.
Pubblicazione: (2025)

Research Community Perspectives on "Intelligence" and Large Language Models
di: Højer, Bertram, et al.
Pubblicazione: (2025)

Fast Sampling for Flows and Diffusions with Lazy and Point Mass Stochastic Interpolants
di: Damsholt, Gabriel, et al.
Pubblicazione: (2026)

If Probable, Then Acceptable? Understanding Conditional Acceptability Judgments in Large Language Models
di: Orth, Jasmin, et al.
Pubblicazione: (2025)

Reason to Rote: Rethinking Memorization in Reasoning
di: Du, Yupei, et al.
Pubblicazione: (2025)

Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models
di: Cheng, Xinyuan, et al.
Pubblicazione: (2026)

Variance reduction of diffusion model's gradients with Taylor approximation-based control variate
di: Jeha, Paul, et al.
Pubblicazione: (2024)

TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
di: Zhang, Tunyu, et al.
Pubblicazione: (2025)

Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
di: Baan, Joris, et al.
Pubblicazione: (2026)

Explainability as statistical inference
di: Senetaire, Hugo Henri Joseph, et al.
Pubblicazione: (2022)

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
di: Deng, Xinle, et al.
Pubblicazione: (2026)

How Uncertainty Estimation Scales with Sampling in Reasoning Models
di: Del, Maksym, et al.
Pubblicazione: (2026)

Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies between Model Predictions and Human Responses in VQA
di: Lan, Jian, et al.
Pubblicazione: (2024)

Interpreting Language Models Through Concept Descriptions: A Survey
di: Feldhus, Nils, et al.
Pubblicazione: (2025)

Anatomy of an Idiom: Tracing Non-Compositionality in Language Models
di: Gomes, Andrew
Pubblicazione: (2025)

Simplifying Outcomes of Language Model Component Analyses with ELIA
di: Eidt, Aaron Louis, et al.
Pubblicazione: (2026)

Perceptions of Linguistic Uncertainty by Language Models and Humans
di: Belem, Catarina G, et al.
Pubblicazione: (2024)

Language over Content: Tracing Cultural Understanding in Multilingual Large Language Models
di: Cho, Seungho, et al.
Pubblicazione: (2025)

Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
di: Damianos, Dimitrios, et al.
Pubblicazione: (2026)

Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
di: Hu, Zhiyuan, et al.
Pubblicazione: (2024)

Variational Reasoning for Language Models
di: Zhou, Xiangxin, et al.
Pubblicazione: (2025)

Reasoning Planning for Language Models
di: Nguyen, Bao, et al.
Pubblicazione: (2025)

Large Language and Reasoning Models are Shallow Disjunctive Reasoners
di: Khalid, Irtaza, et al.
Pubblicazione: (2025)

Revisiting Uncertainty Estimation and Calibration of Large Language Models
di: Tao, Linwei, et al.
Pubblicazione: (2025)

The Consistency Hypothesis in Uncertainty Quantification for Large Language Models
di: Xiao, Quan, et al.
Pubblicazione: (2025)

Uncertainty in Language Models: Assessment through Rank-Calibration
di: Huang, Xinmeng, et al.
Pubblicazione: (2024)

Tracing the Representation Geometry of Language Models from Pretraining to Post-training
di: Li, Melody Zixuan, et al.
Pubblicazione: (2025)

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

Large Language Model Reasoning Failures
di: Song, Peiyang, et al.
Pubblicazione: (2026)