Publications

2025

2024

2023

1. ACL

   BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics

   Liang Ma, Shuyang Cao, Robert L Logan IV, Di Lu, Shihao Ran, Ke Zhang, Joel Tetreault, and Alejandro Jaimes

   In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Jul 2023

   Abs

   The proliferation of automatic faithfulness metrics for summarization has produced a need for benchmarks to evaluate them. While existing benchmarks measure the correlation with human judgements of faithfulness on model-generated summaries, they are insufficient for diagnosing whether metrics are: 1) consistent, i.e., indicate lower faithfulness as errors are introduced into a summary, 2) effective on human-written texts, and 3) sensitive to different error types (as summaries can contain multiple errors). To address these needs, we present a benchmark of unfaithful minimal pairs (BUMP), a dataset of 889 human-written, minimally different summary pairs, where a single error is introduced to a summary from the CNN/DailyMail dataset to produce an unfaithful summary. We find BUMP complements existing benchmarks in a number of ways: 1) the summaries in BUMP are harder to discriminate and less probable under SOTA summarization models, 2) unlike non-pair-based datasets, BUMP can be used to measure the consistency of metrics, and reveals that the most discriminative metrics tend not to be the most consistent, and 3) unlike datasets containing generated summaries with multiple errors, BUMP enables the measurement of metrics’ performance on individual error types.

2. Findings

   Multi-View Source Ablation for Faithful Summarization

   Shuyang Cao, Liang Ma, Di Lu, Robert L Logan IV, Joel Tetreault, and Alejandro Jaimes

   In Findings of the Association for Computational Linguistics: EACL 2023 May 2023

   Abs

   In this paper, we present MuFaSSa (Multi-view Faithfulness Scoring via Source Ablation), a metric for evaluating faithfulness of abstractive summaries, and for guiding training of more faithful summarizers. For evaluation, MuFaSSa employs different strategies (e.g., masking entity mentions) to first remove information from the source document to form multiple ablated views. Then, the faithfulness level of each token in a generated summary is measured by the difference between the token generation probabilities when given the original document and the ablated document as inputs to trained summarizers. For training, MuFaSSa uses a novel word truncation objective that drops unfaithful tokens located by MuFaSSa in both the decoder input and output. Alignments with human-annotated faithfulness labels on AggreFact show that MuFaSSa is comparable to or better than existing metrics built on classifiers or QA models pre-trained on other tasks. In experiments on summarization with XSum and CNN/DailyMail, models trained with word truncation using MuFaSSa outperform competitive methods according to both automatic faithfulness metrics and human assessments.

2022

1. Findings

   Time-aware Prompting for Text Generation

   Shuyang Cao, and Lu Wang

   In Findings of the Association for Computational Linguistics: EMNLP 2022 Dec 2022

   Abs Website

   In this paper, we study the effects of incorporating timestamps, such as document creation dates, into generation systems. Two types of time-aware prompts are investigated: (1) textual prompts that encode document timestamps in natural language sentences; and (2) linear prompts that convert timestamps into continuous vectors. To explore extrapolation to future data points, we further introduce a new data-to-text generation dataset, TempWikiBio, containing more than 4 millions of chronologically ordered revisions of biographical articles from English Wikipedia, each paired with structured personal profiles.Through data-to-text generation on TempWikiBio, text-to-text generation on the content transfer dataset, and summarization on XSum,we show that linear prompts on encoder and textual prompts improve the generation quality on all datasets.Despite having less performance drop when testing on data drawn from a later time, linear prompts focus more on non-temporal information and are less sensitive to the given timestamps, according to human evaluations and sensitivity analyses.Meanwhile, textual prompts establish the association between the given timestamps and the output dates, yielding more factual temporal information in the output.

2. ACL

   HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document Summarization

   Shuyang Cao, and Lu Wang

   In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) May 2022

   Abs Website

   Document structure is critical for efficient information consumption. However, it is challenging to encode it efficiently into the modern Transformer architecture. In this work, we present HIBRIDS, which injects Hierarchical Biases foR Incorporating Document Structure into attention score calculation. We further present a new task, hierarchical question-summary generation, for summarizing salient content in the source document into a hierarchy of questions and summaries, where each follow-up question inquires about the content of its parent question-summary pair. We also annotate a new dataset with 6,153 question-summary hierarchies labeled on government reports. Experiment results show that our model produces better question-summary hierarchies than comparisons on both hierarchy quality and content coverage, a finding also echoed by human judges. Additionally, our model improves the generation of long-form summaries from long government reports and Wikipedia articles, as measured by ROUGE scores.

2021

1. EMNLP

   CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization

   Shuyang Cao, and Lu Wang

   In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing Nov 2021

   Abs Website

   We study generating abstractive summaries that are faithful and factually consistent with the given articles. A novel contrastive learning formulation is presented, which leverages both reference summaries, as positive training data, and automatically generated erroneous summaries, as negative training data, to train summarization systems that are better at distinguishing between them. We further design four types of strategies for creating negative samples, to resemble errors made commonly by two state-of-the-art models, BART and PEGASUS, found in our new human annotations of summary errors. Experiments on XSum and CNN/Daily Mail show that our contrastive learning framework is robust across datasets and models. It consistently produces more factual summaries than strong comparisons with post error correction, entailment-based reranking, and unlikelihood training, according to QA-based factuality evaluation. Human judges echo the observation and find that our model summaries correct more errors.

2. ACL

   Controllable Open-ended Question Generation with A New Question Type Ontology

   Shuyang Cao, and Lu Wang

   In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) Aug 2021

   Abs Website

   We investigate the less-explored task of generating open-ended questions that are typically answered by multiple sentences. We first define a new question type ontology which differentiates the nuanced nature of questions better than widely used question words. A new dataset with 4,959 questions is labeled based on the new ontology. We then propose a novel question type-aware question generation framework, augmented by a semantic graph representation, to jointly predict question focuses and produce the question. Based on this framework, we further use both exemplars and automatically generated templates to improve controllability and diversity. Experiments on two newly collected large-scale datasets show that our model improves question quality over competitive comparisons based on automatic metrics. Human judges also rate our model outputs highly in answerability, coverage of scope, and overall quality. Finally, our model variants with templates can produce questions with enhanced controllability and diversity.

3. NAACL

   Inference Time Style Control for Summarization

   Shuyang Cao, and Lu Wang

   In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Jun 2021

   Abs Website

   How to generate summaries of different styles without requiring corpora in the target styles, or training separate models? We present two novel methods that can be deployed during summary decoding on any pre-trained Transformer-based summarization model. (1) Decoder state adjustment instantly modifies decoder final states with externally trained style scorers, to iteratively refine the output against a target style. (2) Word unit prediction constrains the word usage to impose strong lexical control during generation. In experiments of summarizing with simplicity control, automatic evaluation and human judges both find our models producing outputs in simpler languages while still informative. We also generate news headlines with various ideological leanings, which can be distinguished by humans with a reasonable probability.

4. NAACL

   Attention Head Masking for Inference Time Content Selection in Abstractive Summarization

   Shuyang Cao, and Lu Wang

   In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Jun 2021

   Abs Website

   How can we effectively inform content selection in Transformer-based abstractive summarization models? In this work, we present a simple-yet-effective attention head masking technique, which is applied on encoder-decoder attentions to pinpoint salient content at inference time. Using attention head masking, we are able to reveal the relation between encoder-decoder attentions and content selection behaviors of summarization models. We then demonstrate its effectiveness on three document summarization datasets based on both in-domain and cross-domain settings. Importantly, our models outperform prior state-of-the-art models on CNN/Daily Mail and New York Times datasets. Moreover, our inference-time masking technique is also data-efficient, requiring only 20% of the training samples to outperform BART fine-tuned on the full CNN/DailyMail dataset.

5. NAACL

   Efficient Attentions for Long Document Summarization

   Luyang Huang, Shuyang Cao, Nikolaus Parulian, Heng Ji, and Lu Wang

   In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Jun 2021

   Abs

   The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose Hepos, a novel efficient encoder-decoder attention with head-wise positional strides to effectively pinpoint salient information from the source. We further conduct a systematic study of existing efficient self-attentions. Combined with Hepos, we are able to process ten times more tokens than existing models that use full attentions. For evaluation, we present a new dataset, GovReport, with significantly longer documents and summaries. Results show that our models produce significantly higher ROUGE scores than competitive comparisons, including new state-of-the-art results on PubMed. Human evaluation also shows that our models generate more informative summaries with fewer unfaithful errors.