Yumo Xu

Rujun Han, Yuhao Zhang, Peng Qi et al. · stanford

Question answering based on retrieval augmented generation (RAG-QA) is an important research topic in NLP and has a wide range of real-world applications. However, most existing datasets for this task are either constructed using a single source corpus or consist of short extractive answers, which fall short of evaluating large language model (LLM) based RAG-QA systems on cross-domain generalization. To address these limitations, we create Long-form RobustQA (LFRQA), a new dataset comprising human-written long-form answers that integrate short extractive answers from multiple documents into a single, coherent narrative, covering 26K queries and large corpora across seven different domains. We further propose RAG-QA Arena by directly comparing model-generated answers against LFRQA's answers using LLMs as evaluators. We show via extensive experiments that RAG-QA Arena and human judgments on answer quality are highly correlated. Moreover, only 41.3% of the most competitive LLM's answers are preferred to LFRQA's answers, demonstrating RAG-QA Arena as a challenging evaluation platform for future research.

Yumo Xu, Mirella Lapata · amazon-science

Extractive summarization produces summaries by identifying and concatenating the most important sentences in a document. Since most summarization datasets do not come with gold labels indicating whether document sentences are summary-worthy, different labeling algorithms have been proposed to extrapolate oracle extracts for model training. In this work, we identify two flaws with the widely used greedy labeling approach: it delivers suboptimal and deterministic oracles. To alleviate both issues, we propose a simple yet effective labeling algorithm that creates soft, expectation-based sentence labels. We define a new learning objective for extractive summarization which incorporates learning signals from multiple oracle summaries and prove it is equivalent to estimating the oracle expectation for each document sentence. Without any architectural modifications, the proposed labeling scheme achieves superior performance on a variety of summarization benchmarks across domains and languages, in both supervised and zero-shot settings.

Weijia Zhang, Jia-Hong Huang, Svitlana Vakulenko et al. · amazon-science

Query-focused summarization (QFS) is a fundamental task in natural language processing with broad applications, including search engines and report generation. However, traditional approaches assume the availability of relevant documents, which may not always hold in practical scenarios, especially in highly specialized topics. To address this limitation, we propose a novel knowledge-intensive approach that reframes QFS as a knowledge-intensive task setup. This approach comprises two main components: a retrieval module and a summarization controller. The retrieval module efficiently retrieves potentially relevant documents from a large-scale knowledge corpus based on the given textual query, eliminating the dependence on pre-existing document sets. The summarization controller seamlessly integrates a powerful large language model (LLM)-based summarizer with a carefully tailored prompt, ensuring the generated summary is comprehensive and relevant to the query. To assess the effectiveness of our approach, we create a new dataset, along with human-annotated relevance labels, to facilitate comprehensive evaluation covering both retrieval and summarization performance. Extensive experiments demonstrate the superior performance of our approach, particularly its ability to generate accurate summaries without relying on the availability of relevant documents initially. This underscores our method's versatility and practical applicability across diverse query scenarios.

Zhengxuan Wu, Yuhao Zhang, Peng Qi et al. · stanford

Modern language models (LMs) need to follow human instructions while being faithful; yet, they often fail to achieve both. Here, we provide concrete evidence of a trade-off between instruction following (i.e., follow open-ended instructions) and faithfulness (i.e., ground responses in given context) when training LMs with these objectives. For instance, fine-tuning LLaMA-7B on instruction following datasets renders it less faithful. Conversely, instruction-tuned Vicuna-7B shows degraded performance at following instructions when further optimized on tasks that require contextual grounding. One common remedy is multi-task learning (MTL) with data mixing, yet it remains far from achieving a synergic outcome. We propose a simple yet effective method that relies on Rejection Sampling for Continued Self-instruction Tuning (ReSet), which significantly outperforms vanilla MTL. Surprisingly, we find that less is more, as training ReSet with high-quality, yet substantially smaller data (three-fold less) yields superior results. Our findings offer a better understanding of objective discrepancies in alignment training of LMs.

Huajian Zhang, Yumo Xu, Laura Perez-Beltrachini

We study existing approaches to leverage off-the-shelf Natural Language Inference (NLI) models for the evaluation of summary faithfulness and argue that these are sub-optimal due to the granularity level considered for premises and hypotheses. That is, the smaller content unit considered as hypothesis is a sentence and premises are made up of a fixed number of document sentences. We propose a novel approach, namely InFusE, that uses a variable premise size and simplifies summary sentences into shorter hypotheses. Departing from previous studies which focus on single short document summarisation, we analyse NLI based faithfulness evaluation for diverse summarisation tasks. We introduce DiverSumm, a new benchmark comprising long form summarisation (long documents and summaries) and diverse summarisation tasks (e.g., meeting and multi-document summarisation). In experiments, InFusE obtains superior performance across the different summarisation tasks. Our code and data are available at https://github.com/HJZnlp/infuse.

Yilun Zhao, Zhenting Qi, Linyong Nan et al.

People primarily consult tables to conduct data analysis or answer specific questions. Text generation systems that can provide accurate table summaries tailored to users' information needs can facilitate more efficient access to relevant data insights. Motivated by this, we define a new query-focused table summarization task, where text generation models have to perform human-like reasoning and analysis over the given table to generate a tailored summary. We introduce a new benchmark named QTSumm for this task, which contains 7,111 human-annotated query-summary pairs over 2,934 tables covering diverse topics. We investigate a set of strong baselines on QTSumm, including text generation, table-to-text generation, and large language models. Experimental results and manual analysis reveal that the new task presents significant challenges in table-to-text generation for future research. Moreover, we propose a new approach named ReFactor, to retrieve and reason over query-relevant information from tabular data to generate several natural language facts. Experimental results demonstrate that ReFactor can bring improvements to baselines by concatenating the generated facts to the model input. Our data and code are publicly available at https://github.com/yale-nlp/QTSumm.

Yumo Xu, Peng Qi, Jifan Chen et al. · amazon-science

Citation quality is crucial in information-seeking systems, directly influencing trust and the effectiveness of information access. Current evaluation frameworks, both human and automatic, mainly rely on Natural Language Inference (NLI) to assess binary or ternary supportiveness from cited sources, which we argue is a suboptimal proxy for citation evaluation. In this work we introduce CiteEval, a citation evaluation framework driven by principles focusing on fine-grained citation assessment within a broad context, encompassing not only the cited sources but the full retrieval context, user query, and generated text. Guided by the proposed framework, we construct CiteBench, a multi-domain benchmark with high-quality human annotations on citation quality. To enable efficient evaluation, we further develop CiteEval-Auto, a suite of model-based metrics that exhibit strong correlation with human judgments. Experiments across diverse systems demonstrate CiteEval-Auto's superior ability to capture the multifaceted nature of citations compared to existing metrics, offering a principled and scalable approach to evaluate and improve model-generated citations.

Weijia Zhang, Svitlana Vakulenko, Thilina Rajapakse et al.

Query-focused summarization (QFS) requires generating a summary given a query using a set of relevant documents. However, such relevant documents should be annotated manually and thus are not readily available in realistic scenarios. To address this limitation, we tackle the QFS task as a knowledge-intensive (KI) task without access to any relevant documents. Instead, we assume that these documents are present in a large-scale knowledge corpus and should be retrieved first. To explore this new setting, we build a new dataset (KI-QFS) by adapting existing QFS datasets. In this dataset, answering the query requires document retrieval from a knowledge corpus. We construct three different knowledge corpora, and we further provide relevance annotations to enable retrieval evaluation. Finally, we benchmark the dataset with state-of-the-art QFS models and retrieval-enhanced models. The experimental results demonstrate that QFS models perform significantly worse on KI-QFS compared to the original QFS task, indicating that the knowledge-intensive setting is much more challenging and offers substantial room for improvement. We believe that our investigation will inspire further research into addressing QFS in more realistic scenarios.

Yumo Xu, Mirella Lapata

The availability of large-scale datasets has driven the development of neural models that create summaries from single documents, for generic purposes. When using a summarization system, users often have specific intents with various language realizations, which, depending on the information need, can range from a single keyword to a long narrative composed of multiple questions. Existing summarization systems, however, often either fail to support or act robustly on this query focused summarization task. We introduce LaQSum, the first unified text summarization system that learns Latent Queries from documents for abstractive summarization with any existing query forms. Under a deep generative framework, our system jointly optimizes a latent query model and a conditional language model, allowing users to plug-and-play queries of any type at test time. Despite learning from only generic summarization data and requiring no further optimization for downstream summarization tasks, our system robustly outperforms strong comparison systems across summarization benchmarks with different query types, document settings, and target domains.

Yumo Xu, Mirella Lapata

The availability of large-scale datasets has driven the development of neural models that create generic summaries from single or multiple documents. In this work we consider query focused summarization (QFS), a task for which training data in the form of queries, documents, and summaries is not readily available. We propose to decompose QFS into (1) query modeling (i.e., finding supportive evidence within a set of documents for a query) and (2) conditional language modeling (i.e., summary generation). We introduce MaRGE, a Masked ROUGE Regression framework for evidence estimation and ranking which relies on a unified representation for summaries and queries, so that summaries in generic data can be converted into proxy queries for learning a query model. Experiments across QFS benchmarks and query types show that our model achieves state-of-the-art performance despite learning from weak supervision.

Yumo Xu, Chenguang Zhu, Baolin Peng et al.

Dialog policy determines the next-step actions for agents and hence is central to a dialogue system. However, when migrated to novel domains with little data, a policy model can fail to adapt due to insufficient interactions with the new environment. We propose Deep Transferable Q-Network (DTQN) to utilize shareable low-level signals between domains, such as dialogue acts and slots. We decompose the state and action representation space into feature subspaces corresponding to these low-level components to facilitate cross-domain knowledge transfer. Furthermore, we embed DTQN in a meta-learning framework and introduce Meta-DTQN with a dual-replay mechanism to enable effective off-policy training and adaptation. In experiments, our model outperforms baseline models in terms of both success rate and dialogue efficiency on the multi-domain dialogue dataset MultiWOZ 2.0.

Yumo Xu, Mirella Lapata

We consider the problem of better modeling query-cluster interactions to facilitate query focused multi-document summarization (QFS). Due to the lack of training data, existing work relies heavily on retrieval-style methods for estimating the relevance between queries and text segments. In this work, we leverage distant supervision from question answering where various resources are available to more explicitly capture the relationship between queries and documents. We propose a coarse-to-fine modeling framework which introduces separate modules for estimating whether segments are relevant to the query, likely to contain an answer, and central. Under this framework, a trained evidence estimator further discerns which retrieved segments might answer the query for final selection in the summary. We demonstrate that our framework outperforms strong comparison systems on standard QFS benchmarks.

Tom Sherborne, Yumo Xu, Mirella Lapata

Recent progress in semantic parsing scarcely considers languages other than English but professional translation can be prohibitively expensive. We adapt a semantic parser trained on a single language, such as English, to new languages and multiple domains with minimal annotation. We query if machine translation is an adequate substitute for training data, and extend this to investigate bootstrapping using joint training with English, paraphrasing, and multilingual pre-trained models. We develop a Transformer-based parser combining paraphrases by ensembling attention over multiple encoders and present new versions of ATIS and Overnight in German and Chinese for evaluation. Experimental results indicate that MT can approximate training data in a new language for accurate parsing when augmented with paraphrasing through multiple MT engines. Considering when MT is inadequate, we also find that using our approach achieves parsing accuracy within 2% of complete translation using only 50% of training data.

Yumo Xu, Mirella Lapata

In this paper we introduce domain detection as a new natural language processing task. We argue that the ability to detect textual segments which are domain-heavy, i.e., sentences or phrases which are representative of and provide evidence for a given domain could enhance the robustness and portability of various text classification applications. We propose an encoder-detector framework for domain detection and bootstrap classifiers with multiple instance learning (MIL). The model is hierarchically organized and suited to multilabel classification. We demonstrate that despite learning with minimal supervision, our model can be applied to text spans of different granularities, languages, and genres. We also showcase the potential of domain detection for text summarization.