·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning3h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks3h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts3h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning3h◆FrontierChallenge: Evaluating Scientific Workflow Completion3h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier3h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising3h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic3h◆Omni Interaction Agent Technical Report3h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification3h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability3h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization3h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding3h◆Tracing Computation Density in LLMs3h◆Cultural Binding Heads in Language Models3h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training3h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models3h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning3h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection3h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation3h◆Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning3h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks3h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts3h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning3h◆FrontierChallenge: Evaluating Scientific Workflow Completion3h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier3h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising3h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic3h◆Omni Interaction Agent Technical Report3h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification3h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability3h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization3h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding3h◆Tracing Computation Density in LLMs3h◆Cultural Binding Heads in Language Models3h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training3h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models3h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning3h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection3h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation3h◆
News/Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry
arxiv
PublishedMay 1, 2026 at 4:00 AM
—neutral

Dynamic Adversarial Fine-Tuning Reorganizes Refusal Geometry

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

arXiv:2604.27019v1 Announce Type: cross Abstract: Safety-aligned language models must refuse harmful requests without collapsing into broad over-refusal, but the training-time mechanisms behind this tradeoff remain unclear. Prior work characterizes refusal directions and jailbreak robustness, yet do

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 →
Tags
04
#safety#language-models#adversarial-training#fine-tuning

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#safety#language-models#adversarial-training#fine-tuning

Related coverage

More from ARXIV
arxivBringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning3harxivSubagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks3harxivDistribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts3harxivIn RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning3h
The Bubble Brief
WEEKLY

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

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

Originally published on arxiv ↗
HomeModelsNews