·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Here comes new Siri again1h◆Persona Atlas: Mapping How Famous Minds Think1h◆Vision Hopfield Memory Networks9h◆Stable Deep Reinforcement Learning via Isotropic Gaussian Representations9h◆Insurance of Agentic AI9h◆Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safety9h◆Bidirectional Search for Longest Paths: Case for Front-to-Front Heuristics9h◆CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model9h◆Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads9h◆Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents9h◆MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery9h◆TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management9h◆Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement9h◆From Attack Simulation to SIEM Rule: Deterministic Detection-as-Code Synthesis with Probe-Level Traceability9h◆Compositional Boundaries for Density Fusion9h◆UniVoice: A Unified Model for Speech and Singing Voice Generation9h◆Severity-Aware Curriculum Learning with Multi-Model Response Selection for Medical Text Generation9h◆Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack9h◆FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG9h◆PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation9h◆Here comes new Siri again1h◆Persona Atlas: Mapping How Famous Minds Think1h◆Vision Hopfield Memory Networks9h◆Stable Deep Reinforcement Learning via Isotropic Gaussian Representations9h◆Insurance of Agentic AI9h◆Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safety9h◆Bidirectional Search for Longest Paths: Case for Front-to-Front Heuristics9h◆CogManip: Benchmarking Manipulative Behavior in Multi-Turn Interactions with Large Language Model9h◆Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads9h◆Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents9h◆MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery9h◆TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management9h◆Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement9h◆From Attack Simulation to SIEM Rule: Deterministic Detection-as-Code Synthesis with Probe-Level Traceability9h◆Compositional Boundaries for Density Fusion9h◆UniVoice: A Unified Model for Speech and Singing Voice Generation9h◆Severity-Aware Curriculum Learning with Multi-Model Response Selection for Medical Text Generation9h◆Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack9h◆FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG9h◆PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation9h◆
News/ECI: Effective Contrastive Information to Evaluate Hard-Negatives
arxiv
PublishedJune 6, 2026 at 4:00 AM
—neutral

ECI: Effective Contrastive Information to Evaluate Hard-Negatives

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

arXiv:2603.20990v2 Announce Type: replace-cross Abstract: Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation. We propose Effective Contrastive Information (ECI), a training-free diagnostic that ranks candidate negative sources using

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
arxivVision Hopfield Memory Networks9harxivStable Deep Reinforcement Learning via Isotropic Gaussian Representations9harxivInsurance of Agentic AI9harxivOutput Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safety9h
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