·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning8h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks8h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts8h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning8h◆FrontierChallenge: Evaluating Scientific Workflow Completion8h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier8h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising8h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic8h◆Omni Interaction Agent Technical Report8h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification8h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability8h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization8h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding8h◆Tracing Computation Density in LLMs8h◆Cultural Binding Heads in Language Models8h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training8h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models8h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning8h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection8h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation8h◆Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning8h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks8h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts8h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning8h◆FrontierChallenge: Evaluating Scientific Workflow Completion8h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier8h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising8h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic8h◆Omni Interaction Agent Technical Report8h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification8h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability8h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization8h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding8h◆Tracing Computation Density in LLMs8h◆Cultural Binding Heads in Language Models8h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training8h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models8h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning8h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection8h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation8h◆
Tag

#nlp

20 articles tagged #nlp

arxivJul 31bullish

NorBERTo: A ModernBERT Model Trained for Portuguese with 331 Billion Tokens Corpus

arXiv:2605.00086v2 Announce Type: replace Abstract: High-quality corpora are essential for advancing Natural Language Processing (NLP) in Portuguese. Building on previous encoder-only models such as BERTimbau and Albertina PT-BR, we introduce NorBERTo, a modern encoder based on the ModernBERT archit

NOBEAL5 models · +2#nlp#portuguese#language-modelsRead on arxiv →
arxivJul 31

Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer

arXiv:2606.11018v3 Announce Type: replace Abstract: Measuring subjective constructs in naturally occurring social media text requires annotation procedures that are theoretically grounded, empirically validated, and transferable to an encoder model for scalable prediction. Using posts annotated acco

LL1 model#annotation#nlp#evaluationRead on arxiv →
arxivJul 31

Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors

arXiv:2607.25335v2 Announce Type: replace-cross Abstract: Prompt compression shortens LLM input to reduce inference cost, yet existing methods score token importance through LM forward passes. It remains questionable whether such nuanced, costly token selection is necessary. Compression requires ide

#compression#llm#optimizationRead on arxiv →
arxivJul 27

Evaluation design conditions the expert-vs-auto MeSH gap: a controlled comparison of bag-of-words and BiomedBERT on the Cohen benchmark

arXiv:2607.21685v1 Announce Type: new Abstract: A systematic review begins with someone reading thousands of abstracts to identify the few that are relevant, and classifiers are used to prioritise that reading. Their inputs are often augmented with Medical Subject Headings (MeSH), assigned either by

DMBA2 models#benchmark#evaluation#classificationRead on arxiv →
arxivJul 23bullish

Sentence Splitter: Uncovering Latent Factual Structure for Self-Supervised Learning

arXiv:2607.19845v1 Announce Type: cross Abstract: This paper introduces Sentence Splitter, a self-supervised framework built upon a T5-based encoder--decoder architecture for uncovering the latent factual structure of natural language sentences. The proposed method identifies the semantic boundary b

T51 model#nlp#self-supervised#knowledge-graphRead on arxiv →
arxivJul 16

The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline

arXiv:2607.12079v1 Announce Type: new Abstract: Decoding continuous language from fMRI signals remains a core challenge in non-invasive brain-computer interface research. We present two complementary investigations. First, we improve the Huth et al. ridge regression encoding pipeline through expande

GPGPDE3 models#nlp#brain-computer-interfaces#neural-decodingRead on arxiv →
arxivJun 25

Graph-Based Phonetic Error Correction of Noisy ASR

arXiv:2606.24889v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems, despite low overall word error rates, produce residual lexical errors that disproportionately affect semantically critical tokens such as named entities, negations, and sentiment-bearing words. These errors a

G-GRMA4 models · +1#asr#speech-recognition#nlpRead on arxiv →
arxivJun 25

Overview of HIPE-2026: Person-Place Relation Extraction from Multilingual Historical Texts

arXiv:2606.25935v1 Announce Type: new Abstract: Was this person ever at that place, and if so, when? Answering such questions from noisy, multilingual historical documents is the central challenge of HIPE-2026, the third edition of the HIPE evaluation series. Moving from named entity recognition and

#historical-documents#relation-extraction#evaluationRead on arxiv →
arxivJun 19

CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges

arXiv:2606.20369v1 Announce Type: new Abstract: Online hate speech and misinformation frequently overlap, yet NLP research has mainly treated them in isolation. While LLMs represent a scalable solution for assisting humans in the generation of counterspeech for both threats, zero-shot models frequen

LLRA2 models#nlp#counterspeech#misinformationRead on arxiv →
arxivMay 29

Slide Deck Q&A Quality Assurance App: A Multi-Stage Pipeline for Pedagogical Question Generation

arXiv:2605.26428v2 Announce Type: replace Abstract: Generating high-quality, pedagogically useful questions from lecture slide decks is difficult because important instructional content is distributed across both text and visual elements, and because useful questions must be scaffolded across the fl

#education#nlp#question-generationRead on arxiv →
arxivMay 26

Exploring Profiles of Cognitive Distortions Associated with Mental Health Disorders

arXiv:2605.24996v1 Announce Type: new Abstract: Cognitive distortions, distorted patterns of thinking, have been increasingly studied in computational mental health research. Although they are related to many, if not all, mental health disorders, most existing studies focus primarily on depression.

TR1 model#mental-health#research#nlpRead on arxiv →
arxivMay 21

Assessing socio-economic climate impacts from text data

arXiv:2605.20793v1 Announce Type: new Abstract: Recent advances in natural language processing (NLP) and large language models (LLMs) have enabled the systematic use of large-scale textual data from news, social media, and reports to create datasets with socio-economic impacts of climate hazards suc

#nlp#climate#disaster-riskRead on arxiv →
arxivMay 5

ViLegalNLI: Natural Language Inference for Vietnamese Legal Texts

arXiv:2605.00116v1 Announce Type: cross Abstract: In this article, we introduce ViLegalNLI, the first large-scale Vietnamese Natural Language Inference (NLI) dataset specifically constructed for the legal domain. The dataset consists of 42,012 premise-hypothesis pairs derived from official statutory

#nlp#dataset#legalRead on arxiv →
arxivMay 5bearish

Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs

arXiv:2605.01224v1 Announce Type: new Abstract: This paper argues that contemporary multilingual NLP has converged on a fragile and misleading paradigm of incidental multilingualism. Today's LLMs appear multilingual largely because they are trained on massive, uneven web corpora, not because multili

LL1 model#nlp#multilingualism#language-modelsRead on arxiv →
arxivMay 1

Supercharging Agenda Setting Research: The ParlaCAP Dataset of 28 European Parliaments and a Scalable Multilingual LLM-Based Classification

arXiv:2602.16516v2 Announce Type: replace Abstract: This paper introduces ParlaCAP, a large-scale dataset for analyzing parliamentary agenda setting across Europe, and proposes a cost-effective method for building domain-specific policy topic classifiers. Applying the Comparative Agendas Project (CA

PALA2 models#dataset#nlp#policyRead on arxiv →
arxivApr 28bullish

ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection

arXiv:2604.23585v1 Announce Type: new Abstract: Financial institutions must track over 60,000 regulatory events annually, overwhelming manual compliance teams; the industry has paid over USD 300 billion in fines and settlements since the 2008 financial crisis. We present ComplianceNLP, an end-to-end

COOPLE4 models · +1#compliance#regulatory#nlpRead on arxiv →
arxivApr 23

Structured Disagreement in Health-Literacy Annotation: Epistemic Stability, Conceptual Difficulty, and Agreement-Stratified Inference

arXiv:2604.19943v1 Announce Type: new Abstract: Annotation pipelines in Natural Language Processing (NLP) commonly assume a single latent ground truth per instance and resolve disagreement through label aggregation. Perspectivist approaches challenge this view by treating disagreement as potentially

#nlp#annotation#health-literacyRead on arxiv →
arxivApr 22bullish

Model-Agnostic Meta Learning for Class Imbalance Adaptation

arXiv:2604.18759v1 Announce Type: new Abstract: Class imbalance is a widespread challenge in NLP tasks, significantly hindering robust performance across diverse domains and applications. We introduce Hardness-Aware Meta-Resample (HAMR), a unified framework that adaptively addresses both class imbal

HA1 model#nlp#class-imbalance#resamplingRead on arxiv →
arxivApr 21

Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures

arXiv:2604.16042v2 Announce Type: cross Abstract: While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and safe deployment. Existing surveys in explainable AI largely focus on post-hoc explanation methods t

#explainability#nlp#researchRead on arxiv →
arxivApr 4

A Dynamic Atlas of Persian Poetic Symbolism: Families, Fields, and the Historical Rewiring of Meaning

arXiv:2604.01467v1 Announce Type: new Abstract: Persian poetry is often remembered through recurrent symbols before it is remembered through plot. Wine vessels, gardens, flames, sacred titles, bodily beauty, and courtly names return across centuries, yet computational work still tends to flatten thi

#poetry#nlp#corpus-analysisRead on arxiv →
HomeModelsNews