Yiqing Xie, Wenxuan Zhou, Pradyot Prakash, Di Jin, Yuning Mao, Quintin Fettes, Arya Talebzadeh, Sinong Wang, Han Fang, Carolyn Rose, Daniel Fried, Hejia Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

From ice cream flavors to climate change, people exhibit a wide array of opinions on various topics, and understanding the rationale for these opinions can promote healthy discussion and consensus among them. As such, it can be valuable for a large language model (LLM), particularly as an AI assistant, to be able to empathize with or even explain these various standpoints. In this work, we hypothesize that different topic stances often manifest correlations that can be used to extrapolate to topics with unknown opinions. We explore various prompting and fine-tuning methods to improve an LLM’s ability to (a) extrapolate from opinions on known topics to unknown ones and (b) support their extrapolation with reasoning. Our findings suggest that LLMs possess inherent knowledge from training data about these opinion correlations, and with minimal data, the similarities between human opinions and model-extrapolated opinions can be improved by more than 50%. Furthermore, LLM can generate the reasoning process behind their extrapolation of opinions.

Taowen Wang, Yiyang Liu, James Chenhao Liang, Junhan Zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Masked Language Modeling (MLM) has been one of the most prominent approaches for pretraining bidirectional text encoders due to its simplicity and effectiveness. One notable concern about MLM is that the special $\texttt{[MASK]}$ symbol causes a discrepancy between pretraining data and downstream data as it is present only in pretraining but not in fine-tuning. In this work, we offer a new perspective on the consequence of such a discrepancy: We demonstrate empirically and theoretically that MLM pretraining allocates some model dimensions exclusively for representing $\texttt{[MASK]}$ tokens, resulting in a representation deficiency for real tokens and limiting the pretrained model's expressiveness when it is adapted to downstream data without $\texttt{[MASK]}$ tokens. Motivated by the identified issue, we propose MAE-LM, which pretrains the Masked Autoencoder architecture with MLM where $\texttt{[MASK]}$ tokens are excluded from the encoder. Empirically, we show that MAE-LM improves the utilization of model dimensions for real token representations, and MAE-LM consistently outperforms MLM-pretrained models on the GLUE and SQuAD benchmarks.

Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, Yuning Mao. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to adversarial attacks is of paramount importance. Existing methods for identifying adversarial prompts tend to focus on specific domains, lack diversity, or require extensive human annotations. To address these limitations, we present Rainbow Teaming, a novel black-box approach for producing a diverse collection of adversarial prompts. Rainbow Teaming casts adversarial prompt generation as a quality-diversity problem and uses open-ended search to generate prompts that are both effective and diverse. Focusing on the safety domain, we use Rainbow Teaming to target various state-of-the-art LLMs, including the Llama 2 and Llama 3 models. Our approach reveals hundreds of effective adversarial prompts, with an attack success rate exceeding 90% across all tested models. Furthermore, we demonstrate that prompts generated by Rainbow Teaming are highly transferable and that fine-tuning models with synthetic data generated by our method significantly enhances their safety without sacrificing general performance or helpfulness. We additionally explore the versatility of Rainbow Teaming by applying it to question answering and cybersecurity, showcasing its potential to drive robust open-ended self-improvement in a wide range of applications.

Tiezheng Yu, Hanchao Yu, Davis Liang, Yuning Mao, Shaoliang Nie, Po-Yao Huang, Madian Khabsa, Pascale Fung, Yi-Chia Wang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Large multilingual language models typically rely on a single vocabulary shared across 100+ languages.As these models have increased in parameter count and depth, vocabulary size has remained largely unchanged.This vocabulary bottleneck limits the representational capabilities of multilingual models like XLM-R.In this paper, we introduce a new approach for scaling to very large multilingual vocabularies by de-emphasizing token sharing between languages with little lexical overlap and assigning vocabulary capacity to achieve sufficient coverage for each individual language.Tokenizations using our vocabulary are typically more semantically meaningful and shorter compared to XLM-R.Leveraging this improved vocabulary, we train XLM-V, a multilingual language model with a one million token vocabulary.XLM-V outperforms XLM-R on every task we tested on ranging from natural language inference (XNLI), question answering (MLQA, XQuAD, TyDiQA), to named entity recognition (WikiAnn).XLM-V is particularly effective on low-resource language tasks and outperforms XLM-R by 11.2% and 5.8% absolute on MasakhaNER and Americas NLI, respectively.

Qifan Wang, Yuning Mao, Jingang Wang, Hanchao Yu, Shaoliang Nie, Sinong Wang, Fuli Feng, Lifu Huang, Xiaojun Quan, Zenglin Xu, Dongfang Liu. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement learning, to better align to end tasks and user preferences. We measure the relative importance of these two stages by training LIMA, a 65B parameter LLaMa language model fine-tuned with the standard supervised loss on only 1,000 carefully curated prompts and responses, without any reinforcement learning or human preference modeling. LIMA demonstrates remarkably strong performance, learning to follow specific response formats from only a handful of examples in the training data, including complex queries that range from planning trip itineraries to speculating about alternate history. Moreover, the model tends to generalize well to unseen tasks that did not appear in the training data. In a controlled human study, responses from LIMA are either equivalent or strictly preferred to GPT-4 in 43\% of cases; this statistic is as high as 58\% when compared to Bard and 65\% versus DaVinci003, which was trained with human feedback. Taken together, these results strongly suggest that almost all knowledge in large language models is learned during pretraining, and only limited instruction tuning data is necessary to teach models to produce high quality output.

Yuning Mao, Lambert Mathias, Rui Hou, Amjad Almahairi, Hao Ma, Jiawei Han, Scott Yih, Madian Khabsa. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Scientific extreme summarization (TLDR) aims to form ultra-short summaries of scientific papers.Previous efforts on curating scientific TLDR datasets failed to scale up due to the heavy human annotation and domain expertise required.In this paper, we propose a simple yet effective approach to automatically extracting TLDR summaries for scientific papers from their citation texts.Based on the proposed approach, we create a new benchmark CiteSum without human annotation, which is around 30 times larger than the previous human-curated dataset SciTLDR.We conduct a comprehensive analysis of CiteSum, examining its data characteristics and establishing strong baselines.We further demonstrate the usefulness of CiteSum by adapting models pre-trained on CiteSum (named CITES) to new tasks and domains with limited supervision.For scientific extreme summarization, CITES outperforms most fully-supervised methods on SciTLDR without any fine-tuning and obtains state-of-theart results with only 128 examples.For news extreme summarization, CITES achieves significant gains on XSum over its base model (not pre-trained on CiteSum), e.g., +7.2 ROUGE-1 zero-shot performance and state-of-the-art few-shot performance.For news headline generation, CITES performs the best among unsupervised and zero-shot methods on Gigaword. 1

Multi-dimensional evaluation is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimensions, such as coherence and fluency.However, automatic evaluation in NLG is still dominated by similarity-based metrics, and we lack a reliable framework for a more comprehensive evaluation of advanced models.In this paper, we propose a unified multi-dimensional evaluator UNIEVAL for NLG.We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions.Furthermore, thanks to the unified Boolean QA format, we are able to introduce an intermediate learning phase that enables UNIEVAL to incorporate external knowledge from multiple related tasks and gain further improvement.Experiments on three typical NLG tasks show that UNIEVAL correlates substantially better with human judgments than existing metrics.Specifically, compared to the top-performing unified evaluators, UNIEVAL achieves a 23% higher correlation on text summarization, and over 43% on dialogue response generation.Also, UNIEVAL demonstrates a strong zero-shot learning ability for unseen evaluation dimensions and tasks.Source code, data and all pre-trained evaluators are available on our GitHub repository 1 . Generated Summary:Harry Kane is nominated for both the PFA player and young player of the season.The Spurs striker has been released from the awards ceremony on Sunday.The Tottenham striker features in a new animation.Reference Summary: Harry Kane has been in superb form for Tottenham this season.The 21-year-old has scored 30 goals in all competitions for Spurs.Kane also made his England debut and scored within two minutes.Document: Harry Kane's celebrations this season have always shown him to be an animated young man . . .Similarity-based Evaluators ROUGE-1: 0.44 ROUGE-2: 0.25 ROUGE-L: 0.42 BERTScore: 0.24 Single-dimensional Evaluators (predicted by two different evaluators (Deng et al., 2021)) Consistency: 0.87 Relevance: 0.74 Unified Evaluator (predicted by BARTScore, and the scoring range is negative infinity to 0) Precision: -5.45 Recall: -4.93 F1: -5.19

Yuxin Xiao, Zecheng Zhang, Yuning Mao, Carl Yang, Jiawei Han. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Automatically constructing taxonomy finds many applications in e-commerce and web search. One critical challenge is as data and business scope grow in real applications, new concepts are emerging and needed to be added to the existing taxonomy. Previous approaches focus on the taxonomy expansion, i.e. finding an appropriate hypernym concept from the taxonomy for a new query concept. In this paper, we formulate a new task, “taxonomy completion”, by discovering both the hypernym and hyponym concepts for a query. We propose Triplet Matching Network (TMN), to find the appropriate pairs for a given query concept. TMN consists of one primal scorer and multiple auxiliary scorers. These auxiliary scorers capture various fine-grained signals (e.g., query to hypernym or query to hyponym semantics), and the primal scorer makes a holistic prediction on triplet based on the internal feature representations of all auxiliary scorers. Also, an innovative channel-wise gating mechanism that retains task-specific information in concept representations is introduced to further boost model performance. Experiments on four real-world large-scale datasets show that TMN achieves the best performance on both taxonomy completion task and the previous taxonomy expansion task, outperforming existing methods.

Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, Weizhu Chen. 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). 2021.

Prior studies on text-to-text generation typically assume that the model could figure out what to attend to in the input and what to include in the output via seq2seq learning, with only the parallel training data and no additional guidance.However, it remains unclear whether current models can preserve important concepts in the source input, as seq2seq learning does not have explicit focus on the concepts and commonly used evaluation metrics also treat concepts equally important as other tokens.In this paper, we present a systematic analysis that studies whether current seq2seq models, especially pre-trained language models, are good enough for preserving important input concepts and to what extent explicitly guiding generation with the concepts as lexical constraints is beneficial.We answer the above questions by conducting extensive analytical experiments on four representative text-to-text generation tasks.Based on the observations, we then propose a simple yet effective framework to automatically extract, denoise, and enforce important input concepts as lexical constraints.This new method performs comparably or better than its unconstrained counterpart on automatic metrics, demonstrates higher coverage for concept preservation, and receives better ratings in the human evaluation. 1

Multi-document summarization, which summarizes a set of documents with a small number of phrases or sentences, provides a concise and critical essence of the documents. Existing multi-document summarization methods ignore the fact that there often exist many relevant documents that provide surrounding background knowledge, which can help generate a salient and discriminative summary for a given set of documents. In this paper, we propose a novel method, SUMDocS (Surrounding-aware Unsupervised Multi-Document Summarization), which incorporates rich surrounding (topically related) documents to help improve the quality of extractive summarization without human supervision. Specifically, we propose a joint optimization algorithm to unify global novelty (i.e., category-level frequent and discriminative), local consistency (i.e., locally frequent, co-occurring), and local saliency (i.e., salient from its surroundings) such that the obtained summary captures the characteristics of the target documents. Extensive experiments on news and scientific domains demonstrate the superior performance of our method when the unlabeled surrounding corpus is utilized.

Commonly adopted metrics for extractive summarization focus on lexical overlap at the token level.In this paper, we present a facetaware evaluation setup for better assessment of the information coverage in extracted summaries.Specifically, we treat each sentence in the reference summary as a facet, identify the sentences in the document that express the semantics of each facet as support sentences of the facet, and automatically evaluate extractive summarization methods by comparing the indices of extracted sentences and support sentences of all the facets in the reference summary.To facilitate this new evaluation setup, we construct an extractive version of the CNN/Daily Mail dataset and perform a thorough quantitative investigation, through which we demonstrate that facet-aware evaluation manifests better correlation with human judgment than ROUGE, enables fine-grained evaluation as well as comparative analysis, and reveals valuable insights of state-of-the-art summarization methods. 1 1 Data can be found at https://github.com/ morningmoni/FAR.Reference: Three people in Kansas have died from a listeria outbreak.Lexical Overlap: But they did not appear identical to listeria samples taken from patients infected in the Kansas outbreak.(ROUGE-1 F1=37.0,multiple token matches but totally different semantics) Manual Extract: Five people were infected and three died in the past year in Kansas from listeria that might be linked to blue bell creameries products, according to the CDC.(ROUGE-1 F1=36.9, semantics covered but lower ROUGE due to the presence of other details)

Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions.However, the sparse reward signals offered by the KG during traversal are often insufficient to guide a sophisticated walk-based reinforcement learning (RL) model.An alternate approach is to use traditional symbolic methods (e.g., rule induction), which achieve good performance but can be hard to generalize due to the limitation of symbolic representation.In this paper, we propose RuleGuider, which leverages high-quality rules generated by symbolicbased methods to provide reward supervision for walk-based agents.Experiments on benchmark datasets show that RuleGuider improves the performance of walk-based models without losing interpretability. 1

While neural sequence learning methods have made significant progress in single-document summarization (SDS), they produce unsatisfactory results on multi-document summarization (MDS).We observe two major challenges when adapting SDS advances to MDS: (1) MDS involves larger search space and yet more limited training data, setting obstacles for neural methods to learn adequate representations; (2) MDS needs to resolve higher information redundancy among the source documents, which SDS methods are less effective to handle.To close the gap, we present RL-MMR, Maximal Margin Relevance-guided Reinforcement Learning for MDS, which unifies advanced neural SDS methods and statistical measures used in classical MDS.RL-MMR casts MMR guidance on fewer promising candidates, which restrains the search space and thus leads to better representation learning.Additionally, the explicit redundancy measure in MMR helps the neural representation of the summary to better capture redundancy.Extensive experiments demonstrate that RL-MMR achieves state-of-the-art performance on benchmark MDS datasets.In particular, we show the benefits of incorporating MMR into end-to-end learning when adapting SDS to MDS in terms of both learning effectiveness and efficiency. 1

Can one build a knowledge graph (KG) for all products in the world? Knowledge graphs have firmly established themselves as valuable sources of information for search and question answering, and it is natural to wonder if a KG can contain information about products offered at online retail sites. There have been several successful examples of generic KGs, but organizing information about products poses many additional challenges, including sparsity and noise of structured data for products, complexity of the domain with millions of product types and thousands of attributes, heterogeneity across large number of categories, as well as large and constantly growing number of products.

Taxonomies have found wide applications in various domains, especially online for item categorization, browsing, and search. Despite the prevalent use of online catalog taxonomies, most of them in practice are maintained by humans, which is labor-intensive and difficult to scale. While taxonomy construction from scratch is considerably studied in the literature, how to effectively enrich existing incomplete taxonomies remains an open yet important research question. Taxonomy enrichment not only requires the robustness to deal with emerging terms but also the consistency between existing taxonomy structure and new term attachment. In this paper, we present a self-supervised end-to-end framework, Octet, for Online Catalog Taxonomy EnrichmenT. Octet leverages heterogeneous information unique to online catalog taxonomies such as user queries, items, and their relations to the taxonomy nodes while requiring no other supervision than the existing taxonomies. We propose to distantly train a sequence labeling model for term extraction and employ graph neural networks (GNNs) to capture the taxonomy structure as well as the query-item-taxonomy interactions for term attachment. Extensive experiments in different online domains demonstrate the superiority of Octet over state-of-the-art methods via both automatic and human evaluations. Notably, Octet enriches an online catalog taxonomy in production to 2 times larger in the open-world evaluation.

Millions of news articles are published online every day, which can be overwhelming for readers to follow. Grouping articles that are reporting the same event into news stories is a common way of assisting readers in their news consumption. However, it remains a challenging research problem to efficiently and effectively generate a representative headline for each story. Automatic summarization of a document set has been studied for decades, while few studies have focused on generating representative headlines for a set of articles. Unlike summaries, which aim to capture most information with least redundancy, headlines aim to capture information jointly shared by the story articles in short length and exclude information specific to each individual article.

Yuning Mao, Jingjing Tian, Jiawei Han, Xiang Ren. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

We present a novel end-to-end reinforcement learning approach to automatic taxonomy induction from a set of terms.While prior methods treat the problem as a two-phase task (i.e., detecting hypernymy pairs followed by organizing these pairs into a tree-structured hierarchy), we argue that such two-phase methods may suffer from error propagation, and cannot effectively optimize metrics that capture the holistic structure of a taxonomy.In our approach, the representations of term pairs are learned using multiple sources of information and used to determine which term to select and where to place it on the taxonomy via a policy network.All components are trained in an end-to-end manner with cumulative rewards, measured by a holistic tree metric over the training taxonomies.Experiments on two public datasets of different domains show that our approach outperforms prior state-ofthe-art taxonomy induction methods up to 19.6% on ancestor F1. 1