Syn-QA2: Evaluating False Assumptions in Long-tail Questions with Synthetic QA Datasets

• URL: http://arxiv.org/abs/2403.12145v1
• Date: Mon, 18 Mar 2024 18:01:26 GMT
• Title: Syn-QA2: Evaluating False Assumptions in Long-tail Questions with Synthetic QA Datasets
• Authors: Ashwin Daswani, Rohan Sawant, Najoung Kim,
• Abstract summary: We introduce Syn-(QA)$2$, a set of two synthetically generated question-answering (QA) datasets. We find that false assumptions in QA are challenging, echoing the findings of prior work. The detection task is more challenging with long-tail questions compared to naturally occurring questions.
• Score: 7.52684798377727
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Sensitivity to false assumptions (or false premises) in information-seeking questions is critical for robust question-answering (QA) systems. Recent work has shown that false assumptions in naturally occurring questions pose challenges to current models, with low performance on both generative QA and simple detection tasks (Kim et al. 2023). However, the focus of existing work on naturally occurring questions leads to a gap in the analysis of model behavior on the long tail of the distribution of possible questions. To this end, we introduce Syn-(QA)$^2$, a set of two synthetically generated QA datasets: one generated using perturbed relations from Wikidata, and the other by perturbing HotpotQA (Yang et al. 2018). Our findings from evaluating a range of large language models are threefold: (1) false assumptions in QA are challenging, echoing the findings of prior work, (2) the binary detection task is challenging even compared to the difficulty of generative QA itself, possibly due to the linguistic structure of the problem, and (3) the detection task is more challenging with long-tail questions compared to naturally occurring questions, highlighting the utility of our synthetic datasets and generation method.

Related papers

• DEXTER: A Benchmark for open-domain Complex Question Answering using LLMs [3.24692739098077]
  Open-domain complex Question Answering (QA) is a difficult task with challenges in evidence retrieval and reasoning. We evaluate state-of-the-art pre-trained dense and sparse retrieval models in an open-domain setting. We observe that late interaction models and surprisingly lexical models like BM25 perform well compared to other pre-trained dense retrieval models.
  arXiv  Detail & Related papers  (2024-06-24T22:09:50Z)
• Synthetic Context Generation for Question Generation [6.226609932118123]
  This paper investigates training QG models using synthetic contexts generated by large language models. We find that contexts are essential for QG tasks, even if they are synthetic.
  arXiv  Detail & Related papers  (2024-06-19T03:37:52Z)
• Automatic Question-Answer Generation for Long-Tail Knowledge [65.11554185687258]
  We propose an automatic approach to generate specialized QA datasets for tail entities. We conduct extensive experiments by employing pretrained LLMs on our newly generated long-tail QA datasets.
  arXiv  Detail & Related papers  (2024-03-03T03:06:31Z)
• QASnowball: An Iterative Bootstrapping Framework for High-Quality Question-Answering Data Generation [67.27999343730224]
  We introduce an iterative bootstrapping framework for QA data augmentation (named QASnowball) QASnowball can iteratively generate large-scale high-quality QA data based on a seed set of supervised examples. We conduct experiments in the high-resource English scenario and the medium-resource Chinese scenario, and the experimental results show that the data generated by QASnowball can facilitate QA models.
  arXiv  Detail & Related papers  (2023-09-19T05:20:36Z)
• An Empirical Comparison of LM-based Question and Answer Generation Methods [79.31199020420827]
  Question and answer generation (QAG) consists of generating a set of question-answer pairs given a context. In this paper, we establish baselines with three different QAG methodologies that leverage sequence-to-sequence language model (LM) fine-tuning. Experiments show that an end-to-end QAG model, which is computationally light at both training and inference times, is generally robust and outperforms other more convoluted approaches.
  arXiv  Detail & Related papers  (2023-05-26T14:59:53Z)
• Modern Question Answering Datasets and Benchmarks: A Survey [5.026863544662493]
  Question Answering (QA) is one of the most important natural language processing (NLP) tasks. It aims using NLP technologies to generate a corresponding answer to a given question based on the massive unstructured corpus. In this paper, we investigate influential QA datasets that have been released in the era of deep learning.
  arXiv  Detail & Related papers  (2022-06-30T05:53:56Z)
• ASQA: Factoid Questions Meet Long-Form Answers [35.11889930792675]
  This work focuses on factoid questions that are ambiguous, that is, have different correct answers depending on interpretation. Answers to ambiguous questions should synthesize factual information from multiple sources into a long-form summary. We use this notion of correctness to define an automated metric of performance for ASQA.
  arXiv  Detail & Related papers  (2022-04-12T21:58:44Z)
• Improving Unsupervised Question Answering via Summarization-Informed Question Generation [47.96911338198302]
  Question Generation (QG) is the task of generating a plausible question for a passage, answer> pair. We make use of freely available news summary data, transforming declarative sentences into appropriate questions using dependency parsing, named entity recognition and semantic role labeling. The resulting questions are then combined with the original news articles to train an end-to-end neural QG model.
  arXiv  Detail & Related papers  (2021-09-16T13:08:43Z)
• Understanding Unnatural Questions Improves Reasoning over Text [54.235828149899625]
  Complex question answering (CQA) over raw text is a challenging task. Learning an effective CQA model requires large amounts of human-annotated data. We address the challenge of learning a high-quality programmer (parser) by projecting natural human-generated questions into unnatural machine-generated questions.
  arXiv  Detail & Related papers  (2020-10-19T10:22:16Z)
• Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs [62.71505254770827]
  We propose a conditional variational autoencoder (HCVAE) for generating QA pairs given unstructured texts as contexts. Our model obtains impressive performance gains over all baselines on both tasks, using only a fraction of data for training.
  arXiv  Detail & Related papers  (2020-05-28T08:26:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.