Computation and Language (cs.CL)

Abstract: Few-shot event detection (ED) has been widely studied, while this brings noticeable discrepancies, e.g., various motivations, tasks, and experimental settings, that hinder the understanding of models for future progress. This paper presents a thorough empirical study, a unified view of ED models, and a better unified baseline. For fair evaluation, we choose two practical settings: low-resource setting to assess generalization ability and class-transfer setting for transferability. We compare ten representative methods on three datasets, which are roughly grouped into prompt-based and prototype-based models for detailed analysis. To investigate the superior performance of prototype-based methods, we break down the design and build a unified framework. Based on that, we not only propose a simple yet effective method (e.g., 2.7% F1 gains under low-resource setting) but also offer many valuable research insights for future research.

Abstract: Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models. Without proper security measures, however, these contents are susceptible to illegal piracy and potential misuse. This calls for a secure watermarking system to guarantee copyright protection through leakage tracing or ownership identification. To effectively combat piracy and protect copyrights, a watermarking framework should be able not only to embed adequate bits of information but also extract the watermarks in a robust manner despite possible corruption. In this work, we explore ways to advance both payload and robustness by following a well-known proposition from image watermarking and identify features in natural language that are invariant to minor corruption. Through a systematic analysis of the possible sources of errors, we further propose a corruption-resistant infill model. Our full method improves upon the previous work on robustness by +16.8% point on average on four datasets, three corruption types, and two corruption ratios. Code available at https://github.com/bangawayoo/nlp-watermarking.

Abstract: Few-shot named entity recognition (NER) systems aims at recognizing new classes of entities based on a few labeled samples. A significant challenge in the few-shot regime is prone to overfitting than the tasks with abundant samples. The heavy overfitting in few-shot learning is mainly led by spurious correlation caused by the few samples selection bias. To alleviate the problem of the spurious correlation in the few-shot NER, in this paper, we propose a causal intervention-based few-shot NER method. Based on the prototypical network, the method intervenes in the context and prototype via backdoor adjustment during training. In particular, intervening in the context of the one-shot scenario is very difficult, so we intervene in the prototype via incremental learning, which can also avoid catastrophic forgetting. Our experiments on different benchmarks show that our approach achieves new state-of-the-art results (achieving up to 29% absolute improvement and 12% on average for all tasks).

Abstract: Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the quality of positive and negative sample pairs generated through data augmentation methods. Although supervised contrastive learning can produce more accurate sample pairs with human feedback labels, it still lacks fine-grained training signals. In this paper, we propose to improve \textbf{C}ontrastive \textbf{L}earning of sentence embeddings from \textbf{AI} \textbf{F}eedback \textbf{(CLAIF)}. Our method utilizes AI feedback from large pre-trained language models (LLMs) to construct sample pairs with fine-grained sample similarity scores to improve contrastive learning. Besides, we combine human feedback and AI feedback to provide better supervision signals for supervised contrastive learning of sentence embeddings. Experimental results show that our method achieves state-of-the-art performance on several semantic textual similarity (STS) and transfer learning tasks compared to other unsupervised and supervised contrastive learning methods.

Abstract: The zero-shot relation triplet extraction (ZeroRTE) task aims to extract relation triplets from a piece of text with unseen relation types. The seminal work adopts the pre-trained generative model to generate synthetic samples for new relations. However, current generative models lack the optimization process of model generalization on different tasks during training, and thus have limited generalization capability. For this reason, we propose a novel generative meta-learning framework which exploits the `learning-to-learn' ability of meta-learning to boost the generalization capability of generative models. Specifically, we first design a task-aware generative model which can learn the general knowledge by forcing the optimization process to be conducted across multiple tasks. Based on it, we then present three generative meta-learning approaches designated for three typical meta-learning categories. Extensive experimental results demonstrate that our framework achieves a new state-of-the-art performance for the ZeroRTE task.

Abstract: Human evaluation is indispensable and inevitable for assessing the quality of texts generated by machine learning models or written by humans. However, human evaluation is very difficult to reproduce and its quality is notoriously unstable, hindering fair comparisons among different natural language processing (NLP) models and algorithms. Recently, large language models (LLMs) have demonstrated exceptional performance on unseen tasks when only the task instructions are provided. In this paper, we explore if such an ability of the LLMs can be used as an alternative to human evaluation. We present the LLMs with the exact same instructions, samples to be evaluated, and questions used to conduct human evaluation, and then ask the LLMs to generate responses to those questions; we dub this LLM evaluation. We use human evaluation and LLM evaluation to evaluate the texts in two NLP tasks: open-ended story generation and adversarial attacks. We show that the result of LLM evaluation is consistent with the results obtained by expert human evaluation: the texts rated higher by human experts are also rated higher by the LLMs. We also find that the results of LLM evaluation are stable over different formatting of the task instructions and the sampling algorithm used to generate the answer. We are the first to show the potential of using LLMs to assess the quality of texts and discuss the limitations and ethical considerations of LLM evaluation.

Abstract: Discrete reasoning over table-text documents (e.g., financial reports) gains increasing attention in recent two years. Existing works mostly simplify this challenge by manually selecting and transforming document pages to structured tables and paragraphs, hindering their practical application. In this work, we explore a more realistic problem setting in the form of TAT-DQA, i.e. to answer the question over a visually-rich table-text document. Specifically, we propose a novel Doc2SoarGraph framework with enhanced discrete reasoning capability by harnessing the differences and correlations among different elements (e.g., quantities, dates) of the given question and document with Semantic-oriented hierarchical Graph structures. We conduct extensive experiments on TAT-DQA dataset, and the results show that our proposed framework outperforms the best baseline model by 17.73% and 16.91% in terms of Exact Match (EM) and F1 score respectively on the test set, achieving the new state-of-the-art.

Abstract: Recent pre-trained language models (PLMs) achieve promising results in existing abstractive summarization datasets. However, existing summarization benchmarks overlap in time with the standard pre-training corpora and finetuning datasets. Hence, the strong performance of PLMs may rely on the parametric knowledge that is memorized during pre-training and fine-tuning. Moreover, the knowledge memorized by PLMs may quickly become outdated, which affects the generalization performance of PLMs on future data. In this work, we propose TempoSum, a novel benchmark that contains data samples from 2010 to 2022, to understand the temporal generalization ability of abstractive summarization models. Through extensive human evaluation, we show that parametric knowledge stored in summarization models significantly affects the faithfulness of the generated summaries on future data. Moreover, existing faithfulness enhancement methods cannot reliably improve the faithfulness of summarization models on future data. Finally, we discuss several recommendations to the research community on how to evaluate and improve the temporal generalization capability of text summarization models.

Abstract: Data augmentation is a prevalent technique for improving performance in various machine learning applications. We propose SeqAug, a modality-agnostic augmentation method that is tailored towards sequences of extracted features. The core idea of SeqAug is to augment the sequence by resampling from the underlying feature distribution. Resampling is performed by randomly selecting feature dimensions and permuting them along the temporal axis. Experiments on CMU-MOSEI verify that SeqAug is modality agnostic; it can be successfully applied to a single modality or multiple modalities. We further verify its compatibility with both recurrent and transformer architectures, and also demonstrate comparable to state-of-the-art results.

Abstract: In this paper we present NorQuAD: the first Norwegian question answering dataset for machine reading comprehension. The dataset consists of 4,752 manually created question-answer pairs. We here detail the data collection procedure and present statistics of the dataset. We also benchmark several multilingual and Norwegian monolingual language models on the dataset and compare them against human performance. The dataset will be made freely available.

Abstract: Modelling of early language acquisition aims to understand how infants bootstrap their language skills. The modelling encompasses properties of the input data used for training the models, the cognitive hypotheses and their algorithmic implementations being tested, and the evaluation methodologies to compare models to human data. Recent developments have enabled the use of more naturalistic training data for computational models. This also motivates development of more naturalistic tests of model behaviour. A crucial step towards such an aim is to develop representative speech datasets consisting of speech heard by infants in their natural environments. However, a major drawback of such recordings is that they are typically noisy, and it is currently unclear how the sound quality could affect analyses and modelling experiments conducted on such data. In this paper, we explore this aspect for the case of infant-directed speech (IDS) and adult-directed speech (ADS) analysis. First, we manually and automatically annotated audio quality of utterances extracted from two corpora of child-centred long-form recordings (in English and French). We then compared acoustic features of IDS and ADS in an in-lab dataset and across different audio quality subsets of naturalistic data. Finally, we assessed how the audio quality and recording environment may change the conclusions of a modelling analysis using a recent self-supervised learning model. Our results show that the use of modest and high audio quality naturalistic speech data result in largely similar conclusions on IDS and ADS in terms of acoustic analyses and modelling experiments. We also found that an automatic sound quality assessment tool can be used to screen out useful parts of long-form recordings for a closer analysis with comparable results to that of manual quality annotation.

Abstract: Automatic analysis of customer data for businesses is an area that is of interest to companies. Business to business data is studied rarely in academia due to the sensitive nature of such information. Applying natural language processing can speed up the analysis of prohibitively large sets of data. This paper addresses this subject and applies sentiment analysis, topic modelling and keyword extraction to a B2B data set. We show that accurate sentiment can be extracted from the notes automatically and the notes can be sorted by relevance into different topics. We see that without clear separation topics can lack relevance to a business context.

Abstract: Modern Natural Language Generation (NLG) models come with massive computational and storage requirements. In this work, we study the potential of compressing them, which is crucial for real-world applications serving millions of users. We focus on Knowledge Distillation (KD) techniques, in which a small student model learns to imitate a large teacher model, allowing to transfer knowledge from the teacher to the student. In contrast to much of the previous work, our goal is to optimize the model for a specific NLG task and a specific dataset. Typically, in real-world applications, in addition to labeled data there is abundant unlabeled task-specific data, which is crucial for attaining high compression rates via KD. In this work, we conduct a systematic study of task-specific KD techniques for various NLG tasks under realistic assumptions. We discuss the special characteristics of NLG distillation and particularly the exposure bias problem. Following, we derive a family of Pseudo-Target (PT) augmentation methods, substantially extending prior work on sequence-level KD. We propose the Joint-Teaching method for NLG distillation, which applies word-level KD to multiple PTs generated by both the teacher and the student. Our study provides practical model design observations and demonstrates the effectiveness of PT training for task-specific KD in NLG.

Abstract: Previous approaches to turn-taking and response generation in conversational systems have treated it as a two-stage process: First, the end of a turn is detected (based on conversation history), then the system generates an appropriate response. Humans, however, do not take the turn just because it is likely, but also consider whether what they want to say fits the position. In this paper, we present a model (an extension of TurnGPT) that conditions the end-of-turn prediction on both conversation history and what the next speaker wants to say. We found that our model consistently outperforms the baseline model in a variety of metrics. The improvement is most prominent in two scenarios where turn predictions can be ambiguous solely from the conversation history: 1) when the current utterance contains a statement followed by a question; 2) when the end of the current utterance semantically matches the response. Treating the turn-prediction and response-ranking as a one-stage process, our findings suggest that our model can be used as an incremental response ranker, which can be applied in various settings.

Abstract: Filled pauses (or fillers), such as "uh" and "um", are frequent in spontaneous speech and can serve as a turn-holding cue for the listener, indicating that the current speaker is not done yet. In this paper, we use the recently proposed Voice Activity Projection (VAP) model, which is a deep learning model trained to predict the dynamics of conversation, to analyse the effects of filled pauses on the expected turn-hold probability. The results show that, while filled pauses do indeed have a turn-holding effect, it is perhaps not as strong as could be expected, probably due to the redundancy of other cues. We also find that the prosodic properties and position of the filler has a significant effect on the turn-hold probability. However, contrary to what has been suggested in previous work, there is no difference between "uh" and "um" in this regard.

Abstract: Communication of scientific findings to the public is important for keeping non-experts informed of developments such as life-saving medical treatments. However, generating readable lay summaries from scientific documents is challenging, and currently, these summaries suffer from critical factual errors. One popular intervention for improving factuality is using additional external knowledge to provide factual grounding. However, it is unclear how these grounding sources should be retrieved, selected, or integrated, and how supplementary grounding documents might affect the readability or relevance of the generated summaries. We develop a simple method for selecting grounding sources and integrating them with source documents. We then use the BioLaySum summarization dataset to evaluate the effects of different grounding sources on summary quality. We found that grounding source documents improves the relevance and readability of lay summaries but does not improve factuality of lay summaries. This continues to be true in zero-shot summarization settings where we hypothesized that grounding might be even more important for factual lay summaries.

Abstract: In spite of the potential for ground-breaking achievements offered by large language models (LLMs) (e.g., GPT-3), they still lag significantly behind fully-supervised baselines (e.g., fine-tuned BERT) in relation extraction (RE). This is due to the two major shortcomings of LLMs in RE: (1) low relevance regarding entity and relation in retrieved demonstrations for in-context learning; and (2) the strong inclination to wrongly classify NULL examples into other pre-defined labels. In this paper, we propose GPT-RE to bridge the gap between LLMs and fully-supervised baselines. GPT-RE successfully addresses the aforementioned issues by (1) incorporating task-specific entity representations in demonstration retrieval; and (2) enriching the demonstrations with gold label-induced reasoning logic. We evaluate GPT-RE on four widely-used RE datasets, and observe that GPT-RE achieves improvements over not only existing GPT-3 baselines, but also fully-supervised baselines. Specifically, GPT-RE achieves SOTA performances on the Semeval and SciERC datasets, and competitive performances on the TACRED and ACE05 datasets.

Abstract: Knowledge base question answering (KBQA) is a challenging task that aims to retrieve correct answers from large-scale knowledge bases. Existing attempts primarily focus on entity representation and final answer reasoning, which results in limited supervision for this task. Moreover, the relations, which empirically determine the reasoning path selection, are not fully considered in recent advancements. In this study, we propose a novel framework, RE-KBQA, that utilizes relations in the knowledge base to enhance entity representation and introduce additional supervision. We explore guidance from relations in three aspects, including (1) distinguishing similar entities by employing a variational graph auto-encoder to learn relation importance; (2) exploring extra supervision by predicting relation distributions as soft labels with a multi-task scheme; (3) designing a relation-guided re-ranking algorithm for post-processing. Experimental results on two benchmark datasets demonstrate the effectiveness and superiority of our framework, improving the F1 score by 5.7% from 40.5 to 46.3 on CWQ and 5.8% from 62.8 to 68.5 on WebQSP, better or on par with state-of-the-art methods.

Abstract: Prior research has investigated the impact of various linguistic features on cross-lingual transfer performance. In this study, we investigate the manner in which this effect can be mapped onto the representation space. While past studies have focused on the impact on cross-lingual alignment in multilingual language models during fine-tuning, this study examines the absolute evolution of the respective language representation spaces produced by MLLMs. We place a specific emphasis on the role of linguistic characteristics and investigate their inter-correlation with the impact on representation spaces and cross-lingual transfer performance. Additionally, this paper provides preliminary evidence of how these findings can be leveraged to enhance transfer to linguistically distant languages.

Abstract: The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have further undermined the trustworthiness of NLP systems, leading to unreliable model explanations that are merely correlated with the output predictions. To encourage fairness and transparency, there exists an urgent demand for reliable explanations that allow users to consistently understand the model's behavior. In this work, we propose a complete framework for extending concept-based interpretability methods to NLP. Specifically, we propose a post-hoc interpretability method for extracting predictive high-level features (concepts) from the pretrained model's hidden layer activations. We optimize for features whose existence causes the output predictions to change substantially, \ie generates a high impact. Moreover, we devise several evaluation metrics that can be universally applied. Extensive experiments on real and synthetic tasks demonstrate that our method achieves superior results on {predictive impact}, usability, and faithfulness compared to the baselines.

Abstract: We present a pipeline for a statistical textual exploration, offering a stylometry-based explanation and statistical validation of a hypothesized partition of a text. Given a parameterization of the text, our pipeline: (1) detects literary features yielding the optimal overlap between the hypothesized and unsupervised partitions, (2) performs a hypothesis-testing analysis to quantify the statistical significance of the optimal overlap, while conserving implicit correlations between units of text that are more likely to be grouped, and (3) extracts and quantifies the importance of features most responsible for the classification, estimates their statistical stability and cluster-wise abundance. We apply our pipeline to the first two books in the Bible, where one stylistic component stands out in the eyes of biblical scholars, namely, the Priestly component. We identify and explore statistically significant stylistic differences between the Priestly and non-Priestly components.

Abstract: Mixture-of-experts (MoE) models that employ sparse activation have demonstrated effectiveness in significantly increasing the number of parameters while maintaining low computational requirements per token. However, recent studies have established that MoE models are inherently parameter-inefficient as the improvement in performance diminishes with an increasing number of experts. We hypothesize this parameter inefficiency is a result of all experts having equal capacity, which may not adequately meet the varying complexity requirements of different tokens or tasks, e.g., in a multilingual setting, languages based on their resource levels might require different capacities. In light of this, we propose Stratified Mixture of Experts(SMoE) models, which feature a stratified structure and can assign dynamic capacity to different tokens. We demonstrate the effectiveness of SMoE on two multilingual machine translation benchmarks, where it outperforms multiple state-of-the-art MoE models. On a diverse 15-language dataset, SMoE improves the translation quality over vanilla MoE by +0.93 BLEU points on average. Additionally, SMoE is parameter-efficient, matching vanilla MoE performance with around 50\% fewer parameters.

Abstract: The overwhelming success of transformers is a real conundrum stimulating a compelling question: are these machines replicating some traditional linguistic models or discovering radically new theories? In this paper, we propose a novel standpoint to investigate this important question. Using typological similarities among languages, we aim to layer-wise compare transformers for different languages to observe whether these similarities emerge for particular layers. For this investigation, we propose to use Centered kernel alignment to measure similarity among weight matrices. We discovered that syntactic typological similarity is consistent with the similarity among weights in the middle layers. This finding confirms results obtained by syntactically probing BERT and, thus, gives an important confirmation that BERT is replicating traditional linguistic models.

Abstract: This paper describes our submission to the MEDIQA-Chat 2023 shared task for automatic clinical note generation from doctor-patient conversations. We report results for two approaches: the first fine-tunes a pre-trained language model (PLM) on the shared task data, and the second uses few-shot in-context learning (ICL) with a large language model (LLM). Both achieve high performance as measured by automatic metrics (e.g. ROUGE, BERTScore) and ranked second and first, respectively, of all submissions to the shared task. Expert human scrutiny indicates that notes generated via the ICL-based approach with GPT-4 are preferred about as often as human-written notes, making it a promising path toward automated note generation from doctor-patient conversations.

Abstract: Annotating long-document question answering (long-document QA) pairs is time-consuming and expensive. To alleviate the problem, it might be possible to generate long-document QA pairs via unsupervised question answering (UQA) methods. However, existing UQA tasks are based on short documents, and can hardly incorporate long-range information. To tackle the problem, we propose a new task, named unsupervised long-document question answering (ULQA), aiming to generate high-quality long-document QA instances in an unsupervised manner. Besides, we propose AttenWalker, a novel unsupervised method to aggregate and generate answers with long-range dependency so as to construct long-document QA pairs. Specifically, AttenWalker is composed of three modules, i.e., span collector, span linker and answer aggregator. Firstly, the span collector takes advantage of constituent parsing and reconstruction loss to select informative candidate spans for constructing answers. Secondly, by going through the attention graph of a pre-trained long-document model, potentially interrelated text spans (that might be far apart) could be linked together via an attention-walking algorithm. Thirdly, in the answer aggregator, linked spans are aggregated into the final answer via the mask-filling ability of a pre-trained model. Extensive experiments show that AttenWalker outperforms previous methods on Qasper and NarrativeQA. In addition, AttenWalker also shows strong performance in the few-shot learning setting.

Abstract: Large language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to further improve zero-shot accuracies with minimal effort. We curate small finetuning datasets intended to describe the labels for a task. Unlike typical finetuning data, which has texts annotated with labels, our data simply describes the labels in language, e.g., using a few related terms, dictionary/encyclopedia entries, and short templates. Across a range of topic and sentiment datasets, our method is more accurate than zero-shot by 15-17% absolute. It is also more robust to choices required for zero-shot classification, such as patterns for prompting the model to classify and mappings from labels to tokens in the model's vocabulary. Furthermore, since our data merely describes the labels but does not use input texts, finetuning on it yields a model that performs strongly on multiple text domains for a given label set, even improving over few-shot out-of-domain classification in multiple settings.

Abstract: Utilizing pivot language effectively can significantly improve low-resource machine translation. Usually, the two translation models, source-pivot and pivot-target, are trained individually and do not utilize the limited (source, target) parallel data. This work proposes an end-to-end training method for the cascaded translation model and configures an improved decoding algorithm. The input of the pivot-target model is modified to weighted pivot embedding based on the probability distribution output by the source-pivot model. This allows the model to be trained end-to-end. In addition, we mitigate the inconsistency between tokens and probability distributions while using beam search in pivot decoding. Experiments demonstrate that our method enhances the quality of translation.

Abstract: Pretrained Vision-Language Models (VLMs) have achieved remarkable performance in image retrieval from text. However, their performance drops drastically when confronted with linguistically complex texts that they struggle to comprehend. Inspired by the Divide-and-Conquer algorithm and dual-process theory, in this paper, we regard linguistically complex texts as compound proposition texts composed of multiple simple proposition sentences and propose an end-to-end Neural Divide-and-Conquer Reasoning framework, dubbed NDCR. It contains three main components: 1)Divide: a proposition generator divides the compound proposition text into simple proposition sentences and produces their corresponding representations, 2)Conquer: a pretrained VLMs-based visual-linguistic interactor achieves the interaction between decomposed proposition sentences and images, 3)Combine: a neural-symbolic reasoner combines the above reasoning states to obtain the final solution via a neural logic reasoning approach. According to the dual-process theory, the visual-linguistic interactor and neural-symbolic reasoner could be regarded as analogical reasoning System 1 and logical reasoning System 2. We conduct extensive experiments on a challenging image retrieval from contextual descriptions data set. Experimental results and analyses indicate NDCR significantly improves performance in the complex image-text reasoning problem. Code link: https://github.com/YunxinLi/NDCR.

Abstract: Length-controllable machine translation is a type of constrained translation. It aims to contain the original meaning as much as possible while controlling the length of the translation. We can use automatic summarization or machine translation evaluation metrics for length-controllable machine translation, but this is not necessarily suitable and accurate. This work is the first attempt to evaluate the automatic metrics for length-controllable machine translation tasks systematically. We conduct a rigorous human evaluation on two translation directions and evaluate 18 summarization or translation evaluation metrics. We find that BLEURT and COMET have the highest correlation with human evaluation and are most suitable as evaluation metrics for length-controllable machine translation.

Abstract: Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller task-specific models by either finetuning with human labels or distilling using LLM-generated labels. However, finetuning and distillation require large amounts of training data to achieve comparable performance to LLMs. We introduce Distilling step-by-step, a new mechanism that (a) trains smaller models that outperform LLMs, and (b) achieves so by leveraging less training data needed by finetuning or distillation. Our method extracts LLM rationales as additional supervision for small models within a multi-task training framework. We present three findings across 4 NLP benchmarks: First, compared to both finetuning and distillation, our mechanism achieves better performance with much fewer labeled/unlabeled training examples. Second, compared to LLMs, we achieve better performance using substantially smaller model sizes. Third, we reduce both the model size and the amount of data required to outperform LLMs; our 770M T5 model outperforms the 540B PaLM model using only 80% of available data on a benchmark task.

Abstract: Recent advances in large language models elicit reasoning in a chain of thought that allows models to decompose problems in a human-like fashion. Though this paradigm improves multi-step reasoning ability in language models, it is limited by being unimodal and applied mainly to question-answering tasks. We claim that incorporating visual augmentation into reasoning is essential, especially for complex, imaginative tasks. Consequently, we introduce VCoT, a novel method that leverages chain of thought prompting with vision-language grounding to recursively bridge the logical gaps within sequential data. Our method uses visual guidance to generate synthetic multimodal infillings that add consistent and novel information to reduce the logical gaps for downstream tasks that can benefit from temporal reasoning, as well as provide interpretability into models' multi-step reasoning. We apply VCoT to the Visual Storytelling and WikiHow summarization datasets and demonstrate through human evaluation that VCoT offers novel and consistent synthetic data augmentation beating chain of thought baselines, which can be used to enhance downstream performance.

Abstract: Growing literature has shown that powerful NLP systems may encode social biases; however, the political bias of summarization models remains relatively unknown. In this work, we use an entity replacement method to investigate the portrayal of politicians in automatically generated summaries of news articles. We develop a computational framework based on political entities and lexical resources, and use it to assess biases about Donald Trump and Joe Biden in both extractive and abstractive summarization models. We find consistent differences, such as stronger associations of a collective US government (i.e., administration) with Biden than with Trump. These summary dissimilarities are most prominent when the entity is heavily featured in the source article. Our systematic characterization provides a framework for future studies of bias in summarization.