·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models36m◆Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing36m◆Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders36m◆Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms36m◆Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA36m◆Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models36m◆On Improving Faithfulness of Podcasts from Documents36m◆Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings36m◆MoE$^2$-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation36m◆Analyzing Toxic Behavior and Its Impact on the Mastodon Community36m◆J-CoT: Chain-of-Thought in J-Space36m◆Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study36m◆DWT-Fusion: A Signal-Based Framework for Training-Free LLM-Generated Text Detection36m◆Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs36m◆Developing and Validating the Spanish Version of the Large Language Models Dependency Scale (LLM-D12-SP)36m◆Scaling Native Multimodal Pre-Training From Scratch36m◆Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination36m◆FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts36m◆MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond36m◆Dynamic Commonsense Coordination for Empathetic Response Generation36m◆A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models36m◆Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing36m◆Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders36m◆Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms36m◆Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA36m◆Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models36m◆On Improving Faithfulness of Podcasts from Documents36m◆Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings36m◆MoE$^2$-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation36m◆Analyzing Toxic Behavior and Its Impact on the Mastodon Community36m◆J-CoT: Chain-of-Thought in J-Space36m◆Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study36m◆DWT-Fusion: A Signal-Based Framework for Training-Free LLM-Generated Text Detection36m◆Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs36m◆Developing and Validating the Spanish Version of the Large Language Models Dependency Scale (LLM-D12-SP)36m◆Scaling Native Multimodal Pre-Training From Scratch36m◆Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination36m◆FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts36m◆MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond36m◆Dynamic Commonsense Coordination for Empathetic Response Generation36m◆
News/Human-Centric Topic Modeling with Goal-Prompted Contrastive Learning and Optimal Transport
arxiv
PublishedApril 16, 2026 at 4:00 AM
▲bullish

Human-Centric Topic Modeling with Goal-Prompted Contrastive Learning and Optimal Transport

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

arXiv:2604.12663v1 Announce Type: new Abstract: Existing topic modeling methods, from LDA to recent neural and LLM-based approaches, which focus mainly on statistical coherence, often produce redundant or off-target topics that miss the user's underlying intent. We introduce Human-centric Topic Mode

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Mentioned models
02
  • 01
    GCTM-OT
  • 02
    LLM
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#topic-modeling#natural-language-processing#artificial-intelligence#human-centric

No replies yet. Be first.

Mentioned models
02
  • 01
    GCTM-OT
  • 02
    LLM
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#topic-modeling#natural-language-processing#artificial-intelligence#human-centric

Related coverage

More from ARXIV
arxivA Consensus-Based Framework for Relative Preference Evaluation of Large Language Models36marxivHumanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing36marxivProbing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders36marxivKhondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms36m
The Bubble Brief
WEEKLY

Read topic-modeling insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews