Work

Representation-Aware Prompting for Zero-Shot Marathi Text Classification: IPA, Romanization, Repetition

Year: 2026

Type: conference-paper

Abstract: Large language models (LLMs) often underperform in zero-shot text classification for lowresource, non-Latin languages due to script and tokenization mismatches.We propose representation-aware prompting for Marathi that augments the original script with International Phonetic Alphabet (IPA) transcriptions, romanization, or a repetition-based fallback when external converters are unavailable.Experiments with two instruction-tuned LLMs on Marathi sentiment analysis and hate detection show consistent gains over script-only prompting (up to +2.6 accuracy points).We further find that the most effective augmentation is model-dependent, and that combining all variants is not consistently beneficial, suggesting that concise, targeted cues are preferable in zero-shot settings.

Source: Workshop on Language Models for Low-Resource Languages (LoResLM)

DOI: 10.18653/v1/2026.loreslm-1.37

Authors: Van-Hien Tran, Huy Hien Vu, Hideki Tanaka, Masao Utiyama

Institution: National Institute of Information and Communications Technology

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7140124453

FWCI:

Cites:

Cited by:

Related to: 10