Imagen de Portada

Disentangling Latent Shifts of In-Context Learning with Weak Supervision

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jukić, Josip, Šnajder, Jan
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

From Robustness to Improved Generalization and Calibration in Pre-trained Language Models
por: Jukić, Josip, et al.
Publicado: (2024)

Context Parametrization with Compositional Adapters
por: Jukić, Josip, et al.
Publicado: (2025)

Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness
por: Jelenić, Fran, et al.
Publicado: (2023)

Improving Data and Parameter Efficiency of Neural Language Models Using Representation Analysis
por: Jukić, Josip
Publicado: (2025)

Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detection
por: Dukić, David, et al.
Publicado: (2023)

Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement
por: Sheth, Paras, et al.
Publicado: (2024)

Supervised In-Context Fine-Tuning for Generative Sequence Labeling
por: Dukić, David, et al.
Publicado: (2025)

CrEst: Credibility Estimation for Contexts in LLMs via Weak Supervision
por: Adila, Dyah, et al.
Publicado: (2025)

How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
por: Cui, Yingqian, et al.
Publicado: (2026)

Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision
por: Su, Jinyan, et al.
Publicado: (2024)

DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling
por: Lemercier, Jean-Marie, et al.
Publicado: (2026)

Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings
por: Dukić, David, et al.
Publicado: (2025)

Causal Fine-Tuning under Latent Confounded Shift
por: Yu, Jialin, et al.
Publicado: (2024)

Vocabulary-Defined Semantics: Latent Space Clustering for Improving In-Context Learning
por: Gu, Jian, et al.
Publicado: (2024)

STENCIL: Submodular Mutual Information Based Weak Supervision for Cold-Start Active Learning
por: Beck, Nathan, et al.
Publicado: (2024)

How to Train Text Summarization Model with Weak Supervisions
por: Wang, Yanbo, et al.
Publicado: (2024)

Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation
por: Lin, Ci-Siang, et al.
Publicado: (2024)

Latent Concept Disentanglement in Transformer-based Language Models
por: Hong, Guan Zhe, et al.
Publicado: (2025)

Fair In-Context Learning via Latent Concept Variables
por: Bhaila, Karuna, et al.
Publicado: (2024)

Auto-ICL: In-Context Learning without Human Supervision
por: Yang, Jinghan, et al.
Publicado: (2023)

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
por: Le, Khoi, et al.
Publicado: (2026)

Boosting In-Context Learning in LLMs Through the Lens of Classical Supervised Learning
por: Gundem, Korel, et al.
Publicado: (2025)

MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications
por: Vinayagame, Vishnou, et al.
Publicado: (2024)

Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries
por: Vodrahalli, Kiran, et al.
Publicado: (2024)

Meta-Sel: Efficient Demonstration Selection for In-Context Learning via Supervised Meta-Learning
por: Wang, Xubin, et al.
Publicado: (2026)

A Weakly Supervised Transformer for Rare Disease Diagnosis and Subphenotyping from EHRs with Pulmonary Case Studies
por: Greco, Kimberly F., et al.
Publicado: (2025)

Latent Context Compilation: Distilling Long Context into Compact Portable Memory
por: Li, Zeju, et al.
Publicado: (2026)

Continual Learning Under Language Shift
por: Gogoulou, Evangelia, et al.
Publicado: (2023)

Discovering Latent Knowledge in Language Models Without Supervision
por: Burns, Collin, et al.
Publicado: (2022)

Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities
por: Hua, Wenyue, et al.
Publicado: (2024)

Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals
por: Leite, João A., et al.
Publicado: (2023)

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher
por: Uzunoglu, Arda, et al.
Publicado: (2026)

Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling
por: Cai, Jianfeng, et al.
Publicado: (2025)

Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs
por: Qin, Yijian, et al.
Publicado: (2023)

Claim Check-Worthiness Detection: How Well do LLMs Grasp Annotation Guidelines?
por: Majer, Laura, et al.
Publicado: (2024)

Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling
por: Dukić, David, et al.
Publicado: (2024)

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
por: Liu, Sheng, et al.
Publicado: (2023)

Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
por: Wang, Xinyi, et al.
Publicado: (2023)

Brewing Knowledge in Context: Distillation Perspectives on In-Context Learning
por: Li, Chengye, et al.
Publicado: (2025)

Numerical Claim Detection in Finance: A New Financial Dataset, Weak-Supervision Model, and Market Analysis
por: Shah, Agam, et al.
Publicado: (2024)