·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Connected by Construction: Learning Tractable Near-Tour Marginals for Traveling Salesman Problems2h◆Good Benchmarks2h◆On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage2h◆How Many Tasks Are Enough for Agent Benchmark Decisions? A Replay Analysis of Public LLM Agent Benchmarks2h◆PM-Bench: Evaluating Prospective Memory in LLM Agents2h◆Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions2h◆Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models2h◆FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation2h◆Burst Spiking Neural Networks2h◆Gene Expression-Informed Jointly Controlled Generative Modeling for Precision Molecular Design2h◆Evaluating Nonuniform Dependability Across Response Conditions: A Conditional Generalizability Framework Illustrated in Automated Essay Scoring2h◆Removable Defects: The Economics and Limits of Deliberate Deficiency2h◆Sparse Inter-Layer Dependencies of Transformer FFN Neurons2h◆Mitigating The Effect of Class Imbalance in Data with Hierarchical and Dependable Structure2h◆Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs2h◆HPC-Enabled Video-based Coastal Wave Parameter Estimation Using V-JEPA and Deep Spatiotemporal Learning2h◆Sparse Autoencoders for Interpretable Out-of-Distribution Detection2h◆OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning2h◆Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities2h◆Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty2h◆Connected by Construction: Learning Tractable Near-Tour Marginals for Traveling Salesman Problems2h◆Good Benchmarks2h◆On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage2h◆How Many Tasks Are Enough for Agent Benchmark Decisions? A Replay Analysis of Public LLM Agent Benchmarks2h◆PM-Bench: Evaluating Prospective Memory in LLM Agents2h◆Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions2h◆Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models2h◆FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation2h◆Burst Spiking Neural Networks2h◆Gene Expression-Informed Jointly Controlled Generative Modeling for Precision Molecular Design2h◆Evaluating Nonuniform Dependability Across Response Conditions: A Conditional Generalizability Framework Illustrated in Automated Essay Scoring2h◆Removable Defects: The Economics and Limits of Deliberate Deficiency2h◆Sparse Inter-Layer Dependencies of Transformer FFN Neurons2h◆Mitigating The Effect of Class Imbalance in Data with Hierarchical and Dependable Structure2h◆Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs2h◆HPC-Enabled Video-based Coastal Wave Parameter Estimation Using V-JEPA and Deep Spatiotemporal Learning2h◆Sparse Autoencoders for Interpretable Out-of-Distribution Detection2h◆OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning2h◆Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities2h◆Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty2h◆
News/Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination
arxiv
PublishedJuly 2, 2026 at 4:00 AM
—neutral

Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination

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

arXiv:2607.00158v1 Announce Type: new Abstract: Hallucination remains one of the central obstacles to deploying medical LLMs. Yet, even when hallucination can be detected, it is still unclear whether the internal representations associated with it can be used for control rather than detection alone.

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
arxivConnected by Construction: Learning Tractable Near-Tour Marginals for Traveling Salesman Problems2harxivGood Benchmarks2harxivOn-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage2harxivHow Many Tasks Are Enough for Agent Benchmark Decisions? A Replay Analysis of Public LLM Agent Benchmarks2h
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