Papers with Information Parity
Information Parity: Measuring and Predicting the Multilingual Capabilities of Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly used in user-facing applications worldwide, necessitating handling multiple languages across various tasks. |
| Approach: | They propose a metric called Information Parity (IP) that can predict an LLM’s capabilities across multiple languages in a task-agnostic manner. |
| Outcome: | The proposed metric can predict LLM’s capabilities across multiple languages in a task-agnostic manner. |
Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) pre-trained on massive text data in many languages are preferred solution for various Natural Language processing tasks. |
| Approach: | They compare tokenization parity and information parity as representational biases in pre-trained models . they find TP is better predictor of performance on tasks reliant on syntactic and morphological cues . |
| Outcome: | The proposed model improves on dialect classification, topic classification, and extractive question answering tasks. |