Reading comprehension is a crucial skill in many aspects of education, including language learning, cognitive development, and fostering early literacy skills in children. Automated answer-aware reading comprehension question generation has significant potential to scale up learner support in educational activities. One key technical challenge in this setting is that there can be multiple questions, sometimes very different from each other, with the same answer; a trained question generation method may not necessarily know which question human educators would prefer. To address this challenge, we propose 1) a data augmentation method that enriches the training dataset with diverse questions given the same context and answer and 2) an overgenerate-and-rank method to select the best question from a pool of candidates. We evaluate our method on the FairytaleQA dataset, showing a 5% absolute improvement in ROUGE-L over the best existing method. We also demonstrate the effectiveness of our method in generating harder, "implicit" questions, where the answers are not contained in the context as text spans.
Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation. However, the compositional reasoning abilities of existing VLMs remains subpar. The root of this limitation lies in the inadequate alignment between the images and captions in the pretraining datasets. Additionally, the current contrastive learning objective fails to focus on fine-grained grounding components like relations, actions, and attributes, resulting in "bag-of-words" representations. We introduce a simple and effective method to improve compositional reasoning in VLMs. Our method better leverages available datasets by refining and expanding the standard image-text contrastive learning framework. Our approach does not require specific annotations and does not incur extra parameters. When integrated with CLIP, our technique yields notable improvement over state-of-the-art baselines across five vision-language compositional benchmarks. We open-source our code at https://github.com/lezhang7/Enhance-FineGrained.
The increasing reliance on Large Language Models (LLMs) across academia and industry necessitates a comprehensive understanding of their robustness to prompts. In response to this vital need, we introduce PromptRobust, a robustness benchmark designed to measure LLMs' resilience to adversarial prompts. This study uses a plethora of adversarial textual attacks targeting prompts across multiple levels: character, word, sentence, and semantic. The adversarial prompts, crafted to mimic plausible user errors like typos or synonyms, aim to evaluate how slight deviations can affect LLM outcomes while maintaining semantic integrity. These prompts are then employed in diverse tasks including sentiment analysis, natural language inference, reading comprehension, machine translation, and math problem-solving. Our study generates 4,788 adversarial prompts, meticulously evaluated over 8 tasks and 13 datasets. Our findings demonstrate that contemporary LLMs are not robust to adversarial prompts. Furthermore, we present a comprehensive analysis to understand the mystery behind prompt robustness and its transferability. We then offer insightful robustness analysis and pragmatic recommendations for prompt composition, beneficial to both researchers and everyday users.
The machine reading comprehension (MRC) of user manuals has huge potential in customer service. However, current methods have trouble answering complex questions. Therefore, we introduce the Knowing-how & Knowing-that task that requires the model to answer factoid-style, procedure-style, and inconsistent questions about user manuals. We resolve this task by jointly representing the steps and facts in a graph TARA, which supports a unified inference of various questions. Towards a systematical benchmarking study, we design a heuristic method to automatically parse user manuals into TARAs and build an annotated dataset to test the model's ability in answering real-world questions. Empirical results demonstrate that representing user manuals as TARAs is a desired solution for the MRC of user manuals. An in-depth investigation of TARA further sheds light on the issues and broader impacts of future representations of user manuals. We hope our work can move the MRC of user manuals to a more complex and realistic stage.
The multi-answer phenomenon, where a question may have multiple answers scattered in the document, can be well handled by humans but is challenging enough for machine reading comprehension (MRC) systems. Despite recent progress in multi-answer MRC, there lacks a systematic analysis of how this phenomenon arises and how to better address it. In this work, we design a taxonomy to categorize commonly-seen multi-answer MRC instances, with which we inspect three multi-answer datasets and analyze where the multi-answer challenge comes from. We further analyze how well different paradigms of current multi-answer MRC models deal with different types of multi-answer instances. We find that some paradigms capture well the key information in the questions while others better model the relationship between questions and contexts. We thus explore strategies to make the best of the strengths of different paradigms. Experiments show that generation models can be a promising platform to incorporate different paradigms. Our annotations and code are released for further research.
Large Language Models have shown tremendous performance on a large variety of natural language processing tasks, ranging from text comprehension to common sense reasoning. However, the mechanisms responsible for this success remain opaque, and it is unclear whether LLMs can achieve human-like cognitive capabilities or whether these models are still fundamentally circumscribed. Abstract reasoning is a fundamental task for cognition, consisting of finding and applying a general pattern from few data. Evaluating deep neural architectures on this task could give insight into their potential limitations regarding reasoning and their broad generalisation abilities, yet this is currently an under-explored area. In this paper, we introduce a new benchmark for evaluating language models beyond memorization on abstract reasoning tasks. We perform extensive evaluations of state-of-the-art LLMs, showing that they currently achieve very limited performance in contrast with other natural language tasks, even when applying techniques that have been shown to improve performance on other NLP tasks. We argue that guiding LLM generation to follow causal paths could help improve the generalisation and reasoning abilities of LLMs.
Generating questions along with associated answers from a text has applications in several domains, such as creating reading comprehension tests for students, or improving document search by providing auxiliary questions and answers based on the query. Training models for question and answer generation (QAG) is not straightforward due to the expected structured output (i.e. a list of question and answer pairs), as it requires more than generating a single sentence. This results in a small number of publicly accessible QAG models. In this paper, we introduce AutoQG, an online service for multilingual QAG, along with lmqg, an all-in-one Python package for model fine-tuning, generation, and evaluation. We also release QAG models in eight languages fine-tuned on a few variants of pre-trained encoder-decoder language models, which can be used online via AutoQG or locally via lmqg. With these resources, practitioners of any level can benefit from a toolkit that includes a web interface for end users, and easy-to-use code for developers who require custom models or fine-grained controls for generation.
Contrast consistency, the ability of a model to make consistently correct predictions in the presence of perturbations, is an essential aspect in NLP. While studied in tasks such as sentiment analysis and reading comprehension, it remains unexplored in open-domain question answering (OpenQA) due to the difficulty of collecting perturbed questions that satisfy factuality requirements. In this work, we collect minimally edited questions as challenging contrast sets to evaluate OpenQA models. Our collection approach combines both human annotation and large language model generation. We find that the widely used dense passage retriever (DPR) performs poorly on our contrast sets, despite fitting the training set well and performing competitively on standard test sets. To address this issue, we introduce a simple and effective query-side contrastive loss with the aid of data augmentation to improve DPR training. Our experiments on the contrast sets demonstrate that DPR's contrast consistency is improved without sacrificing its accuracy on the standard test sets.
Entity bias widely affects pretrained (large) language models, causing them to rely on (biased) parametric knowledge to make unfaithful predictions. Although causality-inspired methods have shown great potential to mitigate entity bias, it is hard to precisely estimate the parameters of underlying causal models in practice. The rise of black-box LLMs also makes the situation even worse, because of their inaccessible parameters and uncalibrated logits. To address these problems, we propose a specific structured causal model (SCM) whose parameters are comparatively easier to estimate. Building upon this SCM, we propose causal intervention techniques to mitigate entity bias for both white-box and black-box settings. The proposed causal intervention perturbs the original entity with neighboring entities. This intervention reduces specific biasing information pertaining to the original entity while still preserving sufficient semantic information from similar entities. Under the white-box setting, our training-time intervention improves OOD performance of PLMs on relation extraction (RE) and machine reading comprehension (MRC) by 5.7 points and by 9.1 points, respectively. Under the black-box setting, our in-context intervention effectively reduces the entity-based knowledge conflicts of GPT-3.5, achieving up to 20.5 points of improvement of exact match accuracy on MRC and up to 17.6 points of reduction in memorization ratio on RE. Our code is available at https://github.com/luka-group/Causal-View-of-Entity-Bias.
We present multilingual Pre-trained Machine Reader (mPMR), a novel method for multilingual machine reading comprehension (MRC)-style pre-training. mPMR aims to guide multilingual pre-trained language models (mPLMs) to perform natural language understanding (NLU) including both sequence classification and span extraction in multiple languages. To achieve cross-lingual generalization when only source-language fine-tuning data is available, existing mPLMs solely transfer NLU capability from a source language to target languages. In contrast, mPMR allows the direct inheritance of multilingual NLU capability from the MRC-style pre-training to downstream tasks. Therefore, mPMR acquires better NLU capability for target languages. mPMR also provides a unified solver for tackling cross-lingual span extraction and sequence classification, thereby enabling the extraction of rationales to explain the sentence-pair classification process.
To fully evaluate the overall performance of different NLP models in a given domain, many evaluation benchmarks are proposed, such as GLUE, SuperGLUE and CLUE. The fi eld of natural language understanding has traditionally focused on benchmarks for various tasks in languages such as Chinese, English, and multilingua, however, there has been a lack of attention given to the area of classical Chinese, also known as "wen yan wen", which has a rich history spanning thousands of years and holds signifi cant cultural and academic value. For the prosperity of the NLP community, in this paper, we introduce the WYWEB evaluation benchmark, which consists of nine NLP tasks in classical Chinese, implementing sentence classifi cation, sequence labeling, reading comprehension, and machine translation. We evaluate the existing pre-trained language models, which are all struggling with this benchmark. We also introduce a number of supplementary datasets and additional tools to help facilitate further progress on classical Chinese NLU. The github repository is https://github.com/baudzhou/WYWEB.
We propose a new large-scale (nearly a million questions) ultra-long-context (more than 50,000 words average document length) reading comprehension dataset. Using GPT 3.5, we summarized each scene in 1,500 hand-curated fiction books from Project Gutenberg, which resulted in approximately 150 scene-level summaries per book. After that, we created a number of reading comprehension questions based on these summaries, including three types of multiple-choice scene recognition questions, as well as free-form narrative reconstruction questions. With 990,595 total questions, our dataset is an order of magnitude larger than the closest alternatives. Crucially, most questions have a known ``retention demand'', indicating how long-term of a memory is needed to answer them, which should aid long-term memory performance evaluation. We validate our data in four small-scale experiments: one with human labelers, and three with existing language models. We show that our questions 1) adequately represent the source material 2) can be used to diagnose a model's memory capacity 3) are not trivial for modern language models even when the memory demand does not exceed those models' context lengths. Lastly, we provide our code which can be used to further expand the dataset with minimal human labor.
The VNHSGE (VietNamese High School Graduation Examination) dataset, developed exclusively for evaluating large language models (LLMs), is introduced in this article. The dataset, which covers nine subjects, was generated from the Vietnamese National High School Graduation Examination and comparable tests. 300 literary essays have been included, and there are over 19,000 multiple-choice questions on a range of topics. The dataset assesses LLMs in multitasking situations such as question answering, text generation, reading comprehension, visual question answering, and more by including both textual data and accompanying images. Using ChatGPT and BingChat, we evaluated LLMs on the VNHSGE dataset and contrasted their performance with that of Vietnamese students to see how well they performed. The results show that ChatGPT and BingChat both perform at a human level in a number of areas, including literature, English, history, geography, and civics education. They still have space to grow, though, especially in the areas of mathematics, physics, chemistry, and biology. The VNHSGE dataset seeks to provide an adequate benchmark for assessing the abilities of LLMs with its wide-ranging coverage and variety of activities. We intend to promote future developments in the creation of LLMs by making this dataset available to the scientific community, especially in resolving LLMs' limits in disciplines involving mathematics and the natural sciences.
In behavioural testing, system functionalities underrepresented in the standard evaluation setting (with a held-out test set) are validated through controlled input-output pairs. Optimising performance on the behavioural tests during training (behavioural learning) would improve coverage of phenomena not sufficiently represented in the i.i.d. data and could lead to seemingly more robust models. However, there is the risk that the model narrowly captures spurious correlations from the behavioural test suite, leading to overestimation and misrepresentation of model performance -- one of the original pitfalls of traditional evaluation. In this work, we introduce BeLUGA, an analysis method for evaluating behavioural learning considering generalisation across dimensions of different granularity levels. We optimise behaviour-specific loss functions and evaluate models on several partitions of the behavioural test suite controlled to leave out specific phenomena. An aggregate score measures generalisation to unseen functionalities (or overfitting). We use BeLUGA to examine three representative NLP tasks (sentiment analysis, paraphrase identification and reading comprehension) and compare the impact of a diverse set of regularisation and domain generalisation methods on generalisation performance.
Combining large language models with logical reasoning enhances their capacity to address problems in a robust and reliable manner. Nevertheless, the intricate nature of logical reasoning poses challenges when gathering reliable data from the web to build comprehensive training datasets, subsequently affecting performance on downstream tasks. To address this, we introduce a novel logic-driven data augmentation approach, AMR-LDA. AMR-LDA converts the original text into an Abstract Meaning Representation (AMR) graph, a structured semantic representation that encapsulates the logical structure of the sentence, upon which operations are performed to generate logically modified AMR graphs. The modified AMR graphs are subsequently converted back into text to create augmented data. Notably, our methodology is architecture-agnostic and enhances both generative large language models, such as GPT-3.5 and GPT-4, through prompt augmentation, and discriminative large language models through contrastive learning with logic-driven data augmentation. Empirical evidence underscores the efficacy of our proposed method with improvement in performance across seven downstream tasks, such as reading comprehension requiring logical reasoning, textual entailment, and natural language inference. Furthermore, our method leads on the ReClor leaderboard at https://eval.ai/web/challenges/challenge-page/503/leaderboard/1347. The source code and data are publicly available at https://github.com/Strong-AI-Lab/Logical-Equivalence-driven-AMR-Data-Augmentation-for-Representation-Learning.
Answering multi-hop questions over hybrid factual knowledge from the given text and table (TextTableQA) is a challenging task. Existing models mainly adopt a retriever-reader framework, which have several deficiencies, such as noisy labeling in training retriever, insufficient utilization of heterogeneous information over text and table, and deficient ability for different reasoning operations. In this paper, we propose a three-stage TextTableQA framework S3HQA, which comprises of retriever, selector, and reasoner. We use a retriever with refinement training to solve the noisy labeling problem. Then, a hybrid selector considers the linked relationships between heterogeneous data to select the most relevant factual knowledge. For the final stage, instead of adapting a reading comprehension module like in previous methods, we employ a generation-based reasoner to obtain answers. This includes two approaches: a row-wise generator and an LLM prompting generator~(first time used in this task). The experimental results demonstrate that our method achieves competitive results in the few-shot setting. When trained on the full dataset, our approach outperforms all baseline methods, ranking first on the HybridQA leaderboard.
Recent years witnessed an increase in the amount of research on the task of Question Difficulty Estimation from Text QDET with Natural Language Processing (NLP) techniques, with the goal of targeting the limitations of traditional approaches to question calibration. However, almost the entirety of previous research focused on single silos, without performing quantitative comparisons between different models or across datasets from different educational domains. In this work, we aim at filling this gap, by quantitatively analyzing several approaches proposed in previous research, and comparing their performance on three publicly available real world datasets containing questions of different types from different educational domains. Specifically, we consider reading comprehension Multiple Choice Questions (MCQs), science MCQs, and math questions. We find that Transformer based models are the best performing across different educational domains, with DistilBERT performing almost as well as BERT, and that they outperform other approaches even on smaller datasets. As for the other models, the hybrid ones often outperform the ones based on a single type of features, the ones based on linguistic features perform well on reading comprehension questions, while frequency based features (TF-IDF) and word embeddings (word2vec) perform better in domain knowledge assessment.
When training and evaluating machine reading comprehension models, it is very important to work with high-quality datasets that are also representative of real-world reading comprehension tasks. This requirement includes, for instance, having questions that are based on texts of different genres and require generating inferences or reflecting on the reading material. In this article we turn our attention to RACE, a dataset of English texts and corresponding multiple-choice questions (MCQs). Each MCQ consists of a question and four alternatives (of which one is the correct answer). RACE was constructed by Chinese teachers of English for human reading comprehension and is widely used as training material for machine reading comprehension models. By construction, RACE should satisfy the aforementioned quality requirements and the purpose of this article is to check whether they are indeed satisfied. We provide a detailed analysis of the test set of RACE for high-school students (1045 texts and 3498 corresponding MCQs) including (1) an evaluation of the difficulty of each MCQ and (2) annotations for the relevant pieces of the texts (called "bases") that are used to justify the plausibility of each alternative. A considerable number of MCQs appear not to fulfill basic requirements for this type of reading comprehension tasks, so we additionally identify the high-quality subset of the evaluated RACE corpus. We also demonstrate that the distribution of the positions of the bases for the alternatives is biased towards certain parts of texts, which is not necessarily desirable when evaluating MCQ answering and generation models.
We tackle Multi-party Dialogue Reading Comprehension (abbr., MDRC). MDRC stands for an extractive reading comprehension task grounded on a batch of dialogues among multiple interlocutors. It is challenging due to the requirement of understanding cross-utterance contexts and relationships in a multi-turn multi-party conversation. Previous studies have made great efforts on the utterance profiling of a single interlocutor and graph-based interaction modeling. The corresponding solutions contribute to the answer-oriented reasoning on a series of well-organized and thread-aware conversational contexts. However, the current MDRC models still suffer from two bottlenecks. On the one hand, a pronoun like "it" most probably produces multi-skip reasoning throughout the utterances of different interlocutors. On the other hand, an MDRC encoder is potentially puzzled by fuzzy features, i.e., the mixture of inner linguistic features in utterances and external interactive features among utterances. To overcome the bottlenecks, we propose a coreference-aware attention modeling method to strengthen the reasoning ability. In addition, we construct a two-channel encoding network. It separately encodes utterance profiles and interactive relationships, so as to relieve the confusion among heterogeneous features. We experiment on the benchmark corpora Molweni and FriendsQA. Experimental results demonstrate that our approach yields substantial improvements on both corpora, compared to the fine-tuned BERT and ELECTRA baselines. The maximum performance gain is about 2.5\% F1-score. Besides, our MDRC models outperform the state-of-the-art in most cases.
Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (extractive question answering). Current debiasing methods often come at the cost of significant in-distribution performance to achieve favorable out-of-distribution generalizability, while non-debiasing methods sacrifice a considerable amount of out-of-distribution performance in order to obtain high in-distribution performance. Therefore, it is challenging for them to deal with the complicated changing real-world situations. In this paper, we propose a simple yet effective novel loss function with adaptive loose optimization, which seeks to make the best of both worlds for question answering. Our main technical contribution is to reduce the loss adaptively according to the ratio between the previous and current optimization state on mini-batch training data. This loose optimization can be used to prevent non-debiasing methods from overlearning data bias while enabling debiasing methods to maintain slight bias learning. Experiments on the visual question answering datasets, including VQA v2, VQA-CP v1, VQA-CP v2, GQA-OOD, and the extractive question answering dataset SQuAD demonstrate that our approach enables QA methods to obtain state-of-the-art in- and out-of-distribution performance in most cases. The source code has been released publicly in \url{https://github.com/reml-group/ALO}.