We introduce a multi-stage prompting approach (MSP) for the generation of multiple choice questions (MCQs), harnessing the capabilities of GPT models such as text-davinci-003 and GPT-4, renowned for their excellence across various NLP tasks. Our approach incorporates the innovative concept of chain-of-thought prompting, a progressive technique in which the GPT model is provided with a series of interconnected cues to guide the MCQ generation process. Automated evaluations consistently demonstrate the superiority of our proposed MSP method over the traditional single-stage prompting (SSP) baseline, resulting in the production of high-quality distractors. Furthermore, the one-shot MSP technique enhances automatic evaluation results, contributing to improved distractor generation in multiple languages, including English, German, Bengali, and Hindi. In human evaluations, questions generated using our approach exhibit superior levels of grammaticality, answerability, and difficulty, highlighting its efficacy in various languages.
Vaccination is important to minimize the risk and spread of various diseases. In recent years, vaccination has been a key step in countering the COVID-19 pandemic. However, many people are skeptical about the use of vaccines for various reasons, including the politics involved, the potential side effects of vaccines, etc. The goal in this task is to build an effective multi-label classifier to label a social media post (particularly, a tweet) according to the specific concern(s) towards vaccines as expressed by the author of the post. We tried three different models-(a) Supervised BERT-large-uncased, (b) Supervised HateXplain model, and (c) Zero-Shot GPT-3.5 Turbo model. The Supervised BERT-large-uncased model performed best in our case. We achieved a macro-F1 score of 0.66, a Jaccard similarity score of 0.66, and received the sixth rank among other submissions. Code is available at-https://github.com/anonmous1981/AISOME
This study addresses the critical issue of factual inaccuracies in machine-generated text summaries, an increasingly prevalent issue in information dissemination. Recognizing the potential of such errors to compromise information reliability, we investigate the nature of factual inconsistencies across machine-summarized content. We introduce a prompt-based classification system that categorizes errors into four distinct types: misrepresentation, inaccurate quantities or measurements, false attribution, and fabrication. The participants are tasked with evaluating a corpus of machine-generated summaries against their original articles. Our methodology employs qualitative judgements to identify the occurrence of factual distortions. The results show that our prompt-based approaches are able to detect the type of errors in the summaries to some extent, although there is scope for improvement in our classification systems.
Designing high-quality educational questions is a challenging and time-consuming task. In this work, we propose a novel approach that utilizes prompt-based techniques to generate descriptive and reasoning-based questions. However, current question-answering (QA) datasets are inadequate for conducting our experiments on prompt-based question generation (QG) in an educational setting. Therefore, we curate a new QG dataset called EduProbe for school-level subjects, by leveraging the rich content of NCERT textbooks. We carefully annotate this dataset as quadruples of 1) Context: a segment upon which the question is formed; 2) Long Prompt: a long textual cue for the question (i.e., a longer sequence of words or phrases, covering the main theme of the context); 3) Short Prompt: a short textual cue for the question (i.e., a condensed representation of the key information or focus of the context); 4) Question: a deep question that aligns with the context and is coherent with the prompts. We investigate several prompt-based QG methods by fine-tuning pre-trained transformer-based large language models (LLMs), namely PEGASUS, T5, MBART, and BART. Moreover, we explore the performance of two general-purpose pre-trained LLMs such as Text-Davinci-003 and GPT-3.5-Turbo without any further training. By performing automatic evaluation, we show that T5 (with long prompt) outperforms all other models, but still falls short of the human baseline. Under human evaluation criteria, TextDavinci-003 usually shows better results than other models under various prompt settings. Even in the case of human evaluation criteria, QG models mostly fall short of the human baseline. Our code and dataset are available at: https://github.com/my625/PromptQG
The evolution of legal datasets and the advent of large language models (LLMs) have significantly transformed the legal field, particularly in the generation of case judgment summaries. However, a critical concern arises regarding the potential biases embedded within these summaries. This study scrutinizes the biases present in case judgment summaries produced by legal datasets and large language models. The research aims to analyze the impact of biases on legal decision making. By interrogating the accuracy, fairness, and implications of biases in these summaries, this study contributes to a better understanding of the role of technology in legal contexts and the implications for justice systems worldwide. In this study, we investigate biases wrt Gender-related keywords, Race-related keywords, Keywords related to crime against women, Country names and religious keywords. The study shows interesting evidences of biases in the outputs generated by the large language models and pre-trained abstractive summarization models. The reasoning behind these biases needs further studies.