Article

Exploring Robustness of Multilingual LLMs on Real-World Noisy Data

2025-02-14

Abstract excerpt

Large Language Models (LLMs) are trained on Web data that might contain spelling errors made by humans. But do they become robust to similar real-world noise? In this paper, we investigate the effect of real-world spelling mistakes on the performance of 9 language models, with parameters ranging from 0.2B to 13B, in 3 different NLP tasks, namely Natural Language Inference (NLI), Name Entity Recognition (NER), and...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 48b694b2-6fa8-5447-bb10-16b302895cbd
DOI: 10.32388/3x6cxv

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Exploring Robustness of Multilingual LLMs on Real-World Noisy DataDOI 10.32388/3x6cxvRead

Large Language Models Robustness Against PerturbationSemantic proximity Read

SuperGLUE: The AI raceSemantic proximity Read

Unified Efficient Fine-Tuning Techniques for Open-Source Large Language ModelsSemantic proximity Read

Mitigate Large Language Model Hallucinations with Probabilistic Inference in Graph Neural NetworksSemantic proximity Read

Upscaling A Smaller LLM to More Parameters via Manual Regressive DistillationSemantic proximity Read

Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and StereotypesSemantic proximity Read

Anchoring Bias in Large Language Models: An Experimental StudySemantic proximity Read

IRIS: Iterative Improvement of Distantly Supervised Named Entity AnnotationsSemantic proximity Read

Cross-LLM Paraphrase Laundering: A Register-Controlled Evaluation of Fake-News DetectorsSemantic proximity Read

Enhancements to Large Language Models: Introducing Dynamic Syntactic Insertion for Improved Model Robustness and GeneralizationSemantic proximity Read

Dynamic Contextual Interpolation for More Efficient Model Generalization in Large Language ModelsSemantic proximity Read

Teacher-Student Framework for Short-Context Classification with Domain Adaptation and Data AugmentationSemantic proximity Read