Buchumschlag

Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Nie, Ercong, Yuan, Shuzhou, Ma, Bolei, Schmid, Helmut, Färber, Michael, Kreuter, Frauke, Schütze, Hinrich
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks
von: Ma, Bolei, et al.
Veröffentlicht: (2024)

GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network
von: Yuan, Shuzhou, et al.
Veröffentlicht: (2024)

Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models
von: Yuan, Shuzhou, et al.
Veröffentlicht: (2025)

Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers
von: Yuan, Shuzhou, et al.
Veröffentlicht: (2024)

Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
von: Nie, Ercong, et al.
Veröffentlicht: (2025)

LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification
von: Yuan, Shuzhou, et al.
Veröffentlicht: (2025)

Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence
von: He, Linyang, et al.
Veröffentlicht: (2024)

CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation
von: Yuan, Shuzhou, et al.
Veröffentlicht: (2025)

BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning
von: Nie, Ercong, et al.
Veröffentlicht: (2024)

GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism
von: Yuan, Shuzhou, et al.
Veröffentlicht: (2024)

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
von: Wang, Mingyang, et al.
Veröffentlicht: (2025)

Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification
von: Im, Kyuri, et al.
Veröffentlicht: (2026)

Tracing Multilingual Factual Knowledge Acquisition in Pretraining
von: Liu, Yihong, et al.
Veröffentlicht: (2025)

Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs
von: Yuan, Shuzhou, et al.
Veröffentlicht: (2025)

From Monolingual to Bilingual: Investigating Language Conditioning in Large Language Models for Psycholinguistic Tasks
von: Yuan, Shuzhou, et al.
Veröffentlicht: (2025)

Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models
von: Liu, Yihong, et al.
Veröffentlicht: (2026)

XToM: Exploring the Multilingual Theory of Mind for Large Language Models
von: Chan, Chunkit, et al.
Veröffentlicht: (2025)

Decoding Probing: Revealing Internal Linguistic Structures in Neural Language Models using Minimal Pairs
von: He, Linyang, et al.
Veröffentlicht: (2024)

A Recipe of Parallel Corpora Exploitation for Multilingual Large Language Models
von: Lin, Peiqin, et al.
Veröffentlicht: (2024)

The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models
von: Ma, Bolei, et al.
Veröffentlicht: (2024)

PoeTone: A Framework for Constrained Generation of Structured Chinese Songci with LLMs
von: Qu, Zhan, et al.
Veröffentlicht: (2025)

Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation
von: Ma, Bolei, et al.
Veröffentlicht: (2025)

Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners
von: Liu, Yihong, et al.
Veröffentlicht: (2026)

Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors
von: Zhao, Raoyuan, et al.
Veröffentlicht: (2025)

XCOMPS: A Multilingual Benchmark of Conceptual Minimal Pairs
von: He, Linyang, et al.
Veröffentlicht: (2025)

DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
von: Wang, Zijing, et al.
Veröffentlicht: (2026)

Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-based Causal Discovery
von: Susanti, Yuni, et al.
Veröffentlicht: (2024)

TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models
von: Liu, Yihong, et al.
Veröffentlicht: (2024)

Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment
von: Xhelili, Orgest, et al.
Veröffentlicht: (2024)

TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data
von: Liu, Yihong, et al.
Veröffentlicht: (2024)

Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
von: Yuan, Chenchen, et al.
Veröffentlicht: (2026)

Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study
von: Ma, Bolei, et al.
Veröffentlicht: (2024)

Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication
von: Eckman, Stephanie, et al.
Veröffentlicht: (2025)

Language Model Re-rankers are Fooled by Lexical Similarities
von: Hagström, Lovisa, et al.
Veröffentlicht: (2025)

LangSAMP: Language-Script Aware Multilingual Pretraining
von: Liu, Yihong, et al.
Veröffentlicht: (2024)

Annotation Sensitivity: Training Data Collection Methods Affect Model Performance
von: Kern, Christoph, et al.
Veröffentlicht: (2023)

Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models
von: Ball, Sarah, et al.
Veröffentlicht: (2024)

Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models
von: Hakimi, Ahmad Dawar, et al.
Veröffentlicht: (2025)

Tracing Relational Knowledge Recall in Large Language Models
von: Popovič, Nicholas, et al.
Veröffentlicht: (2026)

The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing
von: Cao, Yuan, et al.
Veröffentlicht: (2026)