·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction7h◆UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering7h◆Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection7h◆INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning7h◆How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution7h◆Trajectory-Level Speculative Decoding for Diffusion Language Models7h◆Below the Noise Floor: Bimodal Seed Collapse and Distinct Failure Modes in Small-Model Knowledge Distillation7h◆Load-Bearing Context: The Question Damage Score for Evaluating Context Reliance in Linguistic Reasoning7h◆Informational Antilocality and the Locality Bias in LLMs7h◆EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion7h◆OpenStamp: A Watermark for Open-Source Language Models7h◆Lexically conditioned realization ambiguity in Korean predicate morphology7h◆QUORUM: QUality-Optimized Routing Using Multiple annotators7h◆Predicting Turn-Taking Outcomes in Multi-Party Conversation: Interpretable Modelling of Speech and Gaze Dynamics with Interpersonal Closeness7h◆When Linguistic and Internal Confidence Diverge in Large Language Models7h◆CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia7h◆A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring7h◆PACE: Publisher-Adaptive Content Extraction via Agentic Automation7h◆Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction7h◆Quantifying Affective Bias in Low-Resource Media: Large-Scale Emotion Profiling of Bengali Headlines7h◆SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction7h◆UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering7h◆Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection7h◆INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning7h◆How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution7h◆Trajectory-Level Speculative Decoding for Diffusion Language Models7h◆Below the Noise Floor: Bimodal Seed Collapse and Distinct Failure Modes in Small-Model Knowledge Distillation7h◆Load-Bearing Context: The Question Damage Score for Evaluating Context Reliance in Linguistic Reasoning7h◆Informational Antilocality and the Locality Bias in LLMs7h◆EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion7h◆OpenStamp: A Watermark for Open-Source Language Models7h◆Lexically conditioned realization ambiguity in Korean predicate morphology7h◆QUORUM: QUality-Optimized Routing Using Multiple annotators7h◆Predicting Turn-Taking Outcomes in Multi-Party Conversation: Interpretable Modelling of Speech and Gaze Dynamics with Interpersonal Closeness7h◆When Linguistic and Internal Confidence Diverge in Large Language Models7h◆CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia7h◆A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring7h◆PACE: Publisher-Adaptive Content Extraction via Agentic Automation7h◆Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction7h◆Quantifying Affective Bias in Low-Resource Media: Large-Scale Emotion Profiling of Bengali Headlines7h◆
News/When Linguistic and Internal Confidence Diverge in Large Language Models
arxiv
PublishedAugust 31, 2026 at 4:00 AM
—neutral

When Linguistic and Internal Confidence Diverge in Large Language Models

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

arXiv:2608.28382v1 Announce Type: new Abstract: Users often ask large language models (LLMs) to report how confident they are, but it is unclear whether such linguistic confidence tracks the model's internal confidence. We study this question across 8 classification tasks, 2 generation tasks and 30

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
arxivSciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction7harxivUIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering7harxivSelect, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection7harxivINSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning7h
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