·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
OpenAI bets on families as ChatGPT goes deeper into households10h◆Svarna: An Open Corpus Workbench for Modern Greek20h◆PLURAL: A Global Dataset for Value Alignment20h◆Validating LLMs in social science: Epistemic threats and emerging norms20h◆How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism20h◆WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search20h◆Temporal Preference Concepts and their Functions in a Large Language Model20h◆UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks20h◆When Synthetic Speech Is All You Have: Better Call GRPO20h◆ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation20h◆Towards Isolated Interventions via Almost Orthogonal Features in Language Models20h◆MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction20h◆Peer-Predictive Self-Training for Language Model Reasoning20h◆DeepTutor: Towards Agentic Personalized Tutoring20h◆COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation20h◆Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator20h◆CausalDS: Benchmarking Causal Reasoning in Data-Science Agents20h◆Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization20h◆Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition20h◆Where do LLMs Fall Short in CBT-Guided Affective Reasoning?20h◆OpenAI bets on families as ChatGPT goes deeper into households10h◆Svarna: An Open Corpus Workbench for Modern Greek20h◆PLURAL: A Global Dataset for Value Alignment20h◆Validating LLMs in social science: Epistemic threats and emerging norms20h◆How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism20h◆WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search20h◆Temporal Preference Concepts and their Functions in a Large Language Model20h◆UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks20h◆When Synthetic Speech Is All You Have: Better Call GRPO20h◆ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation20h◆Towards Isolated Interventions via Almost Orthogonal Features in Language Models20h◆MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction20h◆Peer-Predictive Self-Training for Language Model Reasoning20h◆DeepTutor: Towards Agentic Personalized Tutoring20h◆COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation20h◆Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator20h◆CausalDS: Benchmarking Causal Reasoning in Data-Science Agents20h◆Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization20h◆Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition20h◆Where do LLMs Fall Short in CBT-Guided Affective Reasoning?20h◆
News/The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning
arxiv
PublishedJune 30, 2026 at 4:00 AM
—neutral

The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

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

arXiv:2606.28843v1 Announce Type: cross Abstract: Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task. However, prior work has shown that this increase in capability comes with a cost: it can increase a model's tendency to respond to u

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
arxivSvarna: An Open Corpus Workbench for Modern Greek20harxivPLURAL: A Global Dataset for Value Alignment20harxivValidating LLMs in social science: Epistemic threats and emerging norms20harxivHow Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism20h
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