·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models23m◆Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing23m◆Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders23m◆Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms23m◆Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA23m◆Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models23m◆On Improving Faithfulness of Podcasts from Documents23m◆Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings23m◆MoE$^2$-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation23m◆Analyzing Toxic Behavior and Its Impact on the Mastodon Community23m◆J-CoT: Chain-of-Thought in J-Space23m◆Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study23m◆DWT-Fusion: A Signal-Based Framework for Training-Free LLM-Generated Text Detection23m◆Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs23m◆Developing and Validating the Spanish Version of the Large Language Models Dependency Scale (LLM-D12-SP)23m◆Scaling Native Multimodal Pre-Training From Scratch23m◆Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination23m◆FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts23m◆MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond23m◆Dynamic Commonsense Coordination for Empathetic Response Generation23m◆A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models23m◆Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing23m◆Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders23m◆Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms23m◆Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA23m◆Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models23m◆On Improving Faithfulness of Podcasts from Documents23m◆Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings23m◆MoE$^2$-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation23m◆Analyzing Toxic Behavior and Its Impact on the Mastodon Community23m◆J-CoT: Chain-of-Thought in J-Space23m◆Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study23m◆DWT-Fusion: A Signal-Based Framework for Training-Free LLM-Generated Text Detection23m◆Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs23m◆Developing and Validating the Spanish Version of the Large Language Models Dependency Scale (LLM-D12-SP)23m◆Scaling Native Multimodal Pre-Training From Scratch23m◆Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination23m◆FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts23m◆MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond23m◆Dynamic Commonsense Coordination for Empathetic Response Generation23m◆
News/Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study
arxiv
PublishedJuly 27, 2026 at 4:00 AM

Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study

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

arXiv:2607.21988v1 Announce Type: new Abstract: Self-harm content is particularly challenging to detect using NLP techniques, and is also a high-stakes task which requires the highest accuracy to enable timely intervention or flagging at-risk users. We therefore present an analysis of how LLMs repre

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
arxivA Consensus-Based Framework for Relative Preference Evaluation of Large Language Models23marxivHumanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing23marxivProbing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders23marxivKhondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms23m
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