·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
OpenAI faces 30 more lawsuits tied to Tumbler Ridge shooting1h◆The Curse of Multilinguality in Lexical Normalization9h◆MaskCode: Mask Transformer for Feedback-Assisted Coding With Linear Block Codes9h◆Accelerating Chemical Kinetics for Exoplanet Atmospheres using Neural Networks9h◆DynaNDE: Dynamic Near-Data Expert Scheduling for Batched MoE Inference9h◆Agentic Empirical Asset Pricing: Methodological Foundations9h◆Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement9h◆Can LLMs Discover Scientific Laws in Real and Parallel Worlds?9h◆Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random9h◆Automated Tree Knowledge Graph Construction using Ontology Expansion and Retrieval from Vietnamese History Textbooks9h◆Workload Identification with Physical Side Channels for AI Governance9h◆ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs9h◆Different representation learning objectives recover distinct latent structures from the same psychometric data9h◆Hidden State Poisoning Attacks against Mamba-based Language Models9h◆Energy-Based Transformers as Predictors of Reading Difficulty9h◆BOW: Training Language Models to Reason Over Plausible Next Words9h◆Graph Evidence Is Not Enough: Diagnosing Native Decoder Use in Graph-Augmented LLMs9h◆Topological Steering9h◆Modelpedia: A Catalog of Model Findings for the Meta-Science of AI9h◆SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning9h◆OpenAI faces 30 more lawsuits tied to Tumbler Ridge shooting1h◆The Curse of Multilinguality in Lexical Normalization9h◆MaskCode: Mask Transformer for Feedback-Assisted Coding With Linear Block Codes9h◆Accelerating Chemical Kinetics for Exoplanet Atmospheres using Neural Networks9h◆DynaNDE: Dynamic Near-Data Expert Scheduling for Batched MoE Inference9h◆Agentic Empirical Asset Pricing: Methodological Foundations9h◆Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement9h◆Can LLMs Discover Scientific Laws in Real and Parallel Worlds?9h◆Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random9h◆Automated Tree Knowledge Graph Construction using Ontology Expansion and Retrieval from Vietnamese History Textbooks9h◆Workload Identification with Physical Side Channels for AI Governance9h◆ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs9h◆Different representation learning objectives recover distinct latent structures from the same psychometric data9h◆Hidden State Poisoning Attacks against Mamba-based Language Models9h◆Energy-Based Transformers as Predictors of Reading Difficulty9h◆BOW: Training Language Models to Reason Over Plausible Next Words9h◆Graph Evidence Is Not Enough: Diagnosing Native Decoder Use in Graph-Augmented LLMs9h◆Topological Steering9h◆Modelpedia: A Catalog of Model Findings for the Meta-Science of AI9h◆SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning9h◆
News/Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B
arxiv
PublishedApril 29, 2026 at 4:00 AM
—neutral

Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2604.24070v1 Announce Type: cross Abstract: Small instruct-tuned LLMs produce degenerate verbal confidence under minimal elicitation: ceiling rates above 95%, near-chance Type-2 AUROC, and Invalid validity profiles. We test whether confidence-conditioned supervised fine-tuning (CSFT) with self

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivThe Curse of Multilinguality in Lexical Normalization9harxivMaskCode: Mask Transformer for Feedback-Assisted Coding With Linear Block Codes9harxivAccelerating Chemical Kinetics for Exoplanet Atmospheres using Neural Networks9harxivDynaNDE: Dynamic Near-Data Expert Scheduling for Batched MoE Inference9h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews