LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement

Transforming unstructured text into structured data is a complex task, requiring semantic understanding, reasoning, and structural comprehension. While Large Language Models (LLMs) offer potential, they often struggle with handling ambiguous or domain-specific data, maintaining table structure, managing long inputs, and addressing numerical reasoning. This paper proposes an efficient system for LLM-driven text-to-table generation that leverages novel prompting techniques. Specifically, the system incorporates two key strategies: breaking down the text-to-table task into manageable, guided sub-tasks and refining the generated tables through iterative self-feedback. We show that this custom task decomposition allows the model to address the problem in a stepwise manner and improves the quality of the generated table. Furthermore, we discuss the benefits and potential risks associated with iterative self-feedback on the generated tables while highlighting the trade-offs between enhanced performance and computational cost. Our methods achieve strong results compared to baselines on two complex text-to-table generation datasets available in the public domain.

CASE: Curricular Data Pre-training for Building Generative and Discriminative Assistive Psychology Expert Models

The limited availability of psychologists necessitates efficient identification of individuals requiring urgent mental healthcare. This study explores the use of Natural Language Processing (NLP) pipelines to analyze text data from online mental health forums used for consultations. By analyzing forum posts, these pipelines can flag users who may require immediate professional attention. A crucial challenge in this domain is data privacy and scarcity. To address this, we propose utilizing readily available curricular texts used in institutes specializing in mental health for pre-training the NLP pipelines. This helps us mimic the training process of a psychologist. Our work presents two models: a discriminative BERT-based model called CASE-BERT that flags potential mental health disorders based on forum text, and a generative model called CASE-Gemma that extracts key features for a preliminary diagnosis. CASE-BERT demonstrates superior performance compared to existing methods, achieving an f1 score of 0.91 for Depression and 0.88 for Anxiety, two of the most commonly reported mental health disorders. CASE-Gemma can achieve a BERT Score of 0.849 on generating diagnoses based on forum text. The effectiveness of CASE-Gemma is evaluated through both human evaluation and qualitative methods, with the collaboration of clinical psychologists who provide us with a set of annotated data for fine-tuning and evaluation. Our code is available at https://github.com/sarthakharne/CASE