·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Neocloud Lambda secures $1B in debt to buy more chips6h◆An Anthropic researcher just gave us a peek at self-improving AI7h◆Open-weight AI companies are the Valley’s hottest acquisition targets8h◆Trump’s EPA wants to let data centers hide their air pollution10h◆Anthropic gets its first court win over the Pentagon’s supply-chain risk label13h◆Meta executive leaves for OpenAI as the social media giant faces growing scrutiny in India14h◆Our decision on Cursor following its acquisition by SpaceX20h◆Fine-Tuning of Transformer models with Frames22h◆Feature Transformation Enhanced Jacobi Polynomial Graph Filtering for Graph Anomaly Detection22h◆Naive Prompt Optimization: Rethinking the Need for Complex Prompt Search22h◆TRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction22h◆Syntax vs. Semantics: How Transformers Learn Deep Dependencies22h◆NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation22h◆Data-driven Koopman mode approximation: A neural power iteration algorithm22h◆FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets22h◆You Don't Need to Run Every Eval22h◆Unsupervised Post-Training of Foundation Models: A Survey22h◆Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating22h◆Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement22h◆Provable one-poison backdoor attacks on linear models and ReLU neural networks22h◆Neocloud Lambda secures $1B in debt to buy more chips6h◆An Anthropic researcher just gave us a peek at self-improving AI7h◆Open-weight AI companies are the Valley’s hottest acquisition targets8h◆Trump’s EPA wants to let data centers hide their air pollution10h◆Anthropic gets its first court win over the Pentagon’s supply-chain risk label13h◆Meta executive leaves for OpenAI as the social media giant faces growing scrutiny in India14h◆Our decision on Cursor following its acquisition by SpaceX20h◆Fine-Tuning of Transformer models with Frames22h◆Feature Transformation Enhanced Jacobi Polynomial Graph Filtering for Graph Anomaly Detection22h◆Naive Prompt Optimization: Rethinking the Need for Complex Prompt Search22h◆TRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction22h◆Syntax vs. Semantics: How Transformers Learn Deep Dependencies22h◆NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation22h◆Data-driven Koopman mode approximation: A neural power iteration algorithm22h◆FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets22h◆You Don't Need to Run Every Eval22h◆Unsupervised Post-Training of Foundation Models: A Survey22h◆Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating22h◆Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement22h◆Provable one-poison backdoor attacks on linear models and ReLU neural networks22h◆
News/Training-Time Explainability for Multilingual Hate Speech Detection: Aligning Model Reasoning with Human Rationales
arxiv
PublishedAugust 28, 2026 at 4:00 AM
—neutral

Training-Time Explainability for Multilingual Hate Speech Detection: Aligning Model Reasoning with Human Rationales

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

arXiv:2608.26125v1 Announce Type: cross Abstract: Online hate against Muslim communities often appears in culturally coded, multilingual forms that evade conventional AI moderation. Such systems, though accurate, remain opaque and risk bias, over-censorship, or under-moderation, particularly when de

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
arxivFine-Tuning of Transformer models with Frames22harxivFeature Transformation Enhanced Jacobi Polynomial Graph Filtering for Graph Anomaly Detection22harxivNaive Prompt Optimization: Rethinking the Need for Complex Prompt Search22harxivTRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction22h
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