·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models1m◆Discrete-Time MDP Modeling for Multi-Item Capacitated Lot Sizing with Stochastic Demand Timing1m◆Incremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models1m◆Long-Horizon State Tracking in LLMs: Executing MD5 through a Deep Sequence of Dependent Tool Calls1m◆OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets1m◆SCAFFOLD: A Large-Scale Structured Dataset of Computer Science Research Figures with Diagram QA and Chain-of-Thought Reasoning Traces1m◆UI-Venus-2 Technical Report1m◆EULER: Exploring Underused Links with Evidence-Checked Return for Multi-Agent Mathematical Discovery1m◆When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal Estimation1m◆MiNER: Fine-Tuned Biomedical Natural Language Processing for Malaria Disease Entity Recognition in Clinical Texts1m◆AI Morbidity and Mortality: A Framework for Clinical AI Failure Review1m◆Different representation learning objectives recover distinct latent structures from the same psychometric data1m◆Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm Operations1m◆Recursive Criticality of AI Self-Improvement1m◆IMPACT: Attention Is the Interaction Map for Scalable Interaction-Aware World Model Training1m◆Asymmetries in Spontaneous and Instructed Deception1m◆LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark1m◆ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation1m◆AI Should Not Only Be Helpful. It Should Be Contingent. Artificial Intimacy, Sycophancy, and the Future of Social Learning1m◆ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback1m◆I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models1m◆Discrete-Time MDP Modeling for Multi-Item Capacitated Lot Sizing with Stochastic Demand Timing1m◆Incremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models1m◆Long-Horizon State Tracking in LLMs: Executing MD5 through a Deep Sequence of Dependent Tool Calls1m◆OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets1m◆SCAFFOLD: A Large-Scale Structured Dataset of Computer Science Research Figures with Diagram QA and Chain-of-Thought Reasoning Traces1m◆UI-Venus-2 Technical Report1m◆EULER: Exploring Underused Links with Evidence-Checked Return for Multi-Agent Mathematical Discovery1m◆When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal Estimation1m◆MiNER: Fine-Tuned Biomedical Natural Language Processing for Malaria Disease Entity Recognition in Clinical Texts1m◆AI Morbidity and Mortality: A Framework for Clinical AI Failure Review1m◆Different representation learning objectives recover distinct latent structures from the same psychometric data1m◆Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm Operations1m◆Recursive Criticality of AI Self-Improvement1m◆IMPACT: Attention Is the Interaction Map for Scalable Interaction-Aware World Model Training1m◆Asymmetries in Spontaneous and Instructed Deception1m◆LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark1m◆ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation1m◆AI Should Not Only Be Helpful. It Should Be Contingent. Artificial Intimacy, Sycophancy, and the Future of Social Learning1m◆ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback1m◆
News/Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models
arxiv
PublishedSeptember 1, 2026 at 4:00 AM

Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models

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

arXiv:2608.28924v1 Announce Type: new Abstract: Linguistic theory has long recognized cross-linguistic syntactic regularities, leading to claims that these similar structures are processed by similar mechanisms. However, this hypothesis has been difficult to test empirically due to our lack of fine-

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
arxivI-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models1marxivDiscrete-Time MDP Modeling for Multi-Item Capacitated Lot Sizing with Stochastic Demand Timing1marxivIncremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models1marxivLong-Horizon State Tracking in LLMs: Executing MD5 through a Deep Sequence of Dependent Tool Calls1m
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