This paper presents our system description and error analysis of our entry for NLLP 2024 shared task on Legal Natural Language Inference (L-NLI). The task required classifying these relationships as entailed, contradicted, or neutral, indicating any association between the review and the complaint. Our system emerged as the winning submission, significantly outperforming other entries with a substantial margin and demonstrating the effectiveness of our approach in legal text analysis. We provide a detailed analysis of the strengths and limitations of each model and approach tested, along with a thorough error analysis and suggestions for future improvements. This paper aims to contribute to the growing field of legal NLP by offering insights into advanced techniques for natural language inference in legal contexts, making it accessible to both experts and newcomers in the field.

This paper presents a detailed system description of our entry which finished 1st with a large lead at WASSA 2024 Task 2, focused on cross-lingual emotion detection. We utilized a combination of large language models (LLMs) and their ensembles to effectively understand and categorize emotions across different languages. Our approach not only outperformed other submissions with a large margin, but also demonstrated the strength of integrating multiple models to enhance performance. Additionally, We conducted a thorough comparison of the benefits and limitations of each model used. An error analysis is included along with suggested areas for future improvement. This paper aims to offer a clear and comprehensive understanding of advanced techniques in emotion detection, making it accessible even to those new to the field.

With increasing usage of generative models for text generation and widespread use of machine generated texts in various domains, being able to distinguish between human written and machine generated texts is a significant challenge. While existing models and proprietary systems focus on identifying whether given text is entirely human written or entirely machine generated, only a few systems provide insights at sentence or paragraph level at likelihood of being machine generated at a non reliable accuracy level, working well only for a set of domains and generators. This paper introduces few reliable approaches for the novel task of identifying which part of a given text is machine generated at a word level while comparing results from different approaches and methods. We present a comparison with proprietary systems , performance of our model on unseen domains’ and generators’ texts. The findings reveal significant improvements in detection accuracy along with comparison on other aspects of detection capabilities. Finally we discuss potential avenues for improvement and implications of our work. The proposed model is also well suited for detecting which parts of a text are machine generated in outputs of Instruct variants of many LLMs.

This paper presents a study on using the RoBERTa language model for emotion classification of essays as part of the ‘Shared Task on Empathy Detection, Emotion Classification and Personality Detection in Interactions’ organized as part of ‘WASSA 2023’ at ‘ACL 2023’. Emotion classification is a challenging task in natural language processing, and imbalanced datasets further exacerbate this challenge. In this study, we explore the use of various data balancing techniques in combination with RoBERTa to improve the classification performance. We evaluate the performance of our approach (denoted by adityapatkar on Codalab) on a benchmark multi-label dataset of essays annotated with eight emotion categories, provided by the Shared Task organizers. Our results show that the proposed approach achieves the best macro F1 score in the competition’s training and evaluation phase. Our study provides insights into the potential of RoBERTa for handling imbalanced data in emotion classification. The results can have implications for the natural language processing tasks related to emotion classification.