Imagen de Portada

Scaling up Discovery of Latent Concepts in Deep NLP Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hawasly, Majd, Dalvi, Fahim, Durrani, Nadir
Formato:	Preprint
Publicado:	2023
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing
por: Boughorbel, Sabri, et al.
Publicado: (2025)

Discovering Salient Neurons in Deep NLP Models
por: Durrani, Nadir, et al.
Publicado: (2022)

Latent Concept-based Explanation of NLP Models
por: Yu, Xuemin, et al.
Publicado: (2024)

Exploring Alignment in Shared Cross-lingual Spaces
por: Mousi, Basel, et al.
Publicado: (2024)

Editing Across Languages: A Survey of Multilingual Knowledge Editing
por: Durrani, Nadir, et al.
Publicado: (2025)

An Exploration of Knowledge Editing for Arabic
por: Mousi, Basel, et al.
Publicado: (2025)

There Is More to Refusal in Large Language Models than a Single Direction
por: Joad, Faaiz, et al.
Publicado: (2026)

Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models
por: Mousi, Basel, et al.
Publicado: (2026)

From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models
por: Ersoy, Asım, et al.
Publicado: (2025)

Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis
por: Boughorbel, Sabri, et al.
Publicado: (2024)

LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking
por: Dalvi, Fahim, et al.
Publicado: (2023)

LAraBench: Benchmarking Arabic AI with Large Language Models
por: Abdelali, Ahmed, et al.
Publicado: (2023)

The Landscape of Arabic Large Language Models (ALLMs): A New Era for Arabic Language Technology
por: Al-Khalifa, Shahad, et al.
Publicado: (2025)

Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision
por: Xie, Zhouhang, et al.
Publicado: (2025)

AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs
por: Mousi, Basel, et al.
Publicado: (2024)

Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
por: Saparkhan, Raman, et al.
Publicado: (2026)

PalmX 2025: The First Shared Task on Benchmarking LLMs on Arabic and Islamic Culture
por: Alwajih, Fakhraddin, et al.
Publicado: (2025)

Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
por: Yu, Xuemin, et al.
Publicado: (2026)

Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction
por: Altinisik, Enes, et al.
Publicado: (2026)

Large Language Models on Wikipedia-Style Survey Generation: an Evaluation in NLP Concepts
por: Gao, Fan, et al.
Publicado: (2023)

Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education
por: Yang, Rui, et al.
Publicado: (2024)

When Reasoning Beats Scale: A 1.5B Reasoning Model Outranks 13B LLMs as Discriminator
por: Anjum, Md Fahim
Publicado: (2025)

Cross-Demographic Portability of Deep NLP-Based Depression Models
por: Rutowski, Tomek, et al.
Publicado: (2024)

OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA
por: Alam, Firoj, et al.
Publicado: (2025)

Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA
por: Abbas, Ummar, et al.
Publicado: (2026)

Towards Open-Ended Discovery for Low-Resource NLP
por: Dossou, Bonaventure F. P., et al.
Publicado: (2025)

DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages
por: Faisal, Fahim, et al.
Publicado: (2024)

Anatomy of Neural Language Models
por: Saleh, Majd, et al.
Publicado: (2024)

NLP for Knowledge Discovery and Information Extraction from Energetics Corpora
por: VanGessel, Francis G., et al.
Publicado: (2024)

From Code-Centric to Concept-Centric: Teaching NLP with LLM-Assisted "Vibe Coding"
por: Al-Khalifa, Hend
Publicado: (2026)

DiscoveryBench: Towards Data-Driven Discovery with Large Language Models
por: Majumder, Bodhisattwa Prasad, et al.
Publicado: (2024)

An Efficient Approach for Studying Cross-Lingual Transfer in Multilingual Language Models
por: Faisal, Fahim, et al.
Publicado: (2024)

TurkicNLP: An NLP Toolkit for Turkic Languages
por: Hakimov, Sherzod
Publicado: (2026)

The Nature of NLP: Analyzing Contributions in NLP Papers
por: Pramanick, Aniket, et al.
Publicado: (2024)

Exploring transfer learning for Deep NLP systems on rarely annotated languages
por: Yadav, Dipendra, et al.
Publicado: (2024)

Clinical NLP with Attention-Based Deep Learning for Multi-Disease Prediction
por: Xu, Ting, et al.
Publicado: (2025)

Fanar 2.0: Arabic Generative AI Stack
por: FANAR TEAM, et al.
Publicado: (2026)

Large Language Models for Page Stream Segmentation
por: Heidenreich, Hunter, et al.
Publicado: (2024)

Latent Structure Modulation in Large Language Models Through Stochastic Concept Embedding Transitions
por: Whitaker, Stefan, et al.
Publicado: (2025)

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
por: Geiping, Jonas, et al.
Publicado: (2025)