·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
This NAS company wants to run your local smart home31m◆Data from drones in Ukraine is fueling a new Wild West marketplace48m◆The sameness problem behind those unappetizing AI-generated menus5h◆CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning6h◆Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation6h◆X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System6h◆A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors6h◆Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach6h◆Subspace Inference Enables Efficient Active Reward Learning from Preferences6h◆Identifying AI Web Scrapers Using Canary Tokens6h◆PalmClaw: A Native On-Device Agent Framework for Mobile Phones6h◆Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognition6h◆MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval6h◆When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA6h◆ALRA: Adaptive Local Relational Alignment for Logit-Based Pre-training Distillation of Autoregressive Language Models6h◆VestigeKV: The NoPE-MLA KV Cache Carries Its Own Eviction Signal in a Vestigial Branch6h◆Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG6h◆ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval6h◆Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models6h◆The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models6h◆This NAS company wants to run your local smart home31m◆Data from drones in Ukraine is fueling a new Wild West marketplace48m◆The sameness problem behind those unappetizing AI-generated menus5h◆CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning6h◆Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation6h◆X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System6h◆A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors6h◆Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach6h◆Subspace Inference Enables Efficient Active Reward Learning from Preferences6h◆Identifying AI Web Scrapers Using Canary Tokens6h◆PalmClaw: A Native On-Device Agent Framework for Mobile Phones6h◆Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognition6h◆MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval6h◆When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QA6h◆ALRA: Adaptive Local Relational Alignment for Logit-Based Pre-training Distillation of Autoregressive Language Models6h◆VestigeKV: The NoPE-MLA KV Cache Carries Its Own Eviction Signal in a Vestigial Branch6h◆Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG6h◆ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval6h◆Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models6h◆The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models6h◆
News/ShriNep@EEUCA 2026: RAKSHAK - Multi-Task DeBERTa with Rationale Distillation and Jigsaw-Augmented Training for Toxic Intent Classification
arxiv
PublishedJuly 24, 2026 at 4:00 AM
—neutral

ShriNep@EEUCA 2026: RAKSHAK - Multi-Task DeBERTa with Rationale Distillation and Jigsaw-Augmented Training for Toxic Intent Classification

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

arXiv:2607.20450v1 Announce Type: new Abstract: This paper presents two systems for the GameTox Shared Task at the Workshop on EEUCA at ACL 2026, which requires classifying World of Tanks chat utterances into six fine-grained toxic intent categories (Labels 0-5). Severe class imbalance, domain-speci

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
arxivCulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning6harxivProactive Service Agents: A Unified Decision Framework, Methods, and Evaluation6harxivX-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System6harxivA Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors6h
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