Cross-Lingual Emotion Recognition (CLER) remains a formidable challenge for ultra-low-resource languages like Balinese due to the scarcity of high-quality annotated data and the performance limitations of traditional multilingual models. This study addresses these gaps through two primary contributions. First, we present a newly created multi-label Balinese emotion dataset annotated by a panel of experts in Balinese linguistics and psychology. Second, we propose the Multi-Agent Peer Collaboration (MAPC) framework, which transforms the multi-label classification problem into a series of independent binary tasks to leverage the collaborative reasoning of Large Language Models (LLMs). We evaluated the framework against the LaBSE multilingual model and three LLMs of varying scales under zero-shot and few-shot settings using the Macro-F1 measure. The experimental results showed that LLMs significantly outperform traditional Pre-trained Language Models (PLMs). MAPC achieved an overall macro F₁-score of 63.95, which was higher than the individual baselines in both zero-shot and few-shot settings. Analysis shows that while some models exhibit sensitivity to few-shot prompting in low-resource contexts, the MAPC review and revision process consistently improves individual reasoning and provides a more accurate final classification.

This research aims to explore the intersection of Large Language Models and confidence calibration in Entity Matching. To this end, we perform an empirical study to compare baseline RoBERTa confidences for an Entity Matching task against confidences that are calibrated using Temperature Scaling, Monte Carlo Dropout and Ensembles. We use the Abt-Buy, DBLP-ACM, iTunes-Amazon and Company datasets. The findings indicate that the proposed modified RoBERTa model exhibits a slight overconfidence, with Expected Calibration Error scores ranging from 0.0043 to 0.0552 across datasets. We find that this overconfidence can be mitigated using Temperature Scaling, reducing Expected Calibration Error scores by up to 23.83%.

Recommendation systems, for documents, have become tools for finding relevant content on the Web. However, these systems have limitations when it comes to recommending documents in languages different from the query language, which means they might overlook resources in non-native languages. This research focuses on representing documents across languages by using Transformer Leveraged Document Representations (TLDRs) that are mapped to a cross-lingual domain. Four multilingual pre-trained transformer models (mBERT, mT5 XLM RoBERTa, ErnieM) were evaluated using three mapping methods across 20 language pairs representing combinations of five selected languages of the European Union. Metrics like Mate Retrieval Rate and Reciprocal Rank were used to measure the effectiveness of mapped TLDRs compared to non-mapped ones. The results highlight the power of cross-lingual representations achieved through pre-trained transformers and mapping approaches suggesting a promising direction for expanding beyond language connections, between two specific languages.

In this work, we explore different linear mapping techniques to learn cross-lingual document representations from pre-trained multilingual large language models for low-resource languages. Three different mapping techniques namely Linear Concept Approximation (LCA), Linear Concept Compression (LCC), and Neural Concept Approximation (NCA) and four multilingual language models such as mBERT, mT5, XLM-R, and ErnieM were used to extract embeddings. The inter-lingual representations were created mappings the monolingual representation extracted from multilingual language models. The experimental results showed that LCA and LCC significantly outperform NCA, with models like ErnieM achieving the highest alignment quality. Language pairs exhibit variable performance, influenced by linguistic similarity and data availability, with the Amharic-English pair yielding particularly high scores. The results showed the utility of LCA and LCC in enabling cross-lingual tasks for low-resource languages.

This study investigates the effectiveness of the action score, a metric originally developed for computer vision tasks, in estimating sample difficulty across various natural language processing (NLP) tasks. Using transformer-based models, the action score is applied to sentiment analysis, natural language inference, and abstractive text summarization. The results demonstrate that the action score can effectively identify challenging samples in sentiment analysis and natural language inference, often capturing difficult instances that are missed by more established metrics like entropy. However, the effectiveness of the action score appears to be task-dependent, as evidenced by its performance in the abstractive text summarization task, where it exhibits a nearly linear relationship with entropy. The findings suggest that the action score can provide valuable insights into the characteristics of challenging samples in NLP tasks, particularly in classification settings. However, its application should be carefully considered in the context of each specific task and in light of emerging research on the potential value of hard samples in machine learning.