LLMs have achieved remarkable fluency and coherence in text generation, yet their widespread adoption has raised concerns about content reliability and accountability. In high-stakes domains, it is crucial to understand where and how the content is created. To address this, we introduce the Text pROVEnance (TROVE) challenge, designed to trace each sentence of a target text back to specific source sentences within potentially lengthy or multi-document inputs. Beyond identifying sources, TROVE annotates the fine-grained relationships (quotation, compression, inference, and others), providing a deep understanding of how each target sentence is formed.To benchmark TROVE, we construct our dataset by leveraging three public datasets covering 11 diverse scenarios (e.g., QA and summarization) in English and Chinese, spanning source texts of varying lengths (0–5k, 5–10k, 10k+), emphasizing the multi-document and long-document settings essential for provenance. To ensure high-quality data, we employ a three-stage annotation process: sentence retrieval, GPT-4o provenance, and human provenance. We evaluate 11 LLMs under direct prompting and retrieval-augmented paradigms, revealing that retrieval is essential for robust performance, larger models perform better in complex relationship classification, and closed-source models often lead, yet open-source models show significant promise, particularly with retrieval augmentation. We make our dataset available here: https://github.com/ZNLP/ZNLP-Dataset.

Current VLM-based VQA methods often process entire images, leading to excessive visual tokens that include redundant information irrelevant to the posed question.This abundance of unnecessary image details creates numerous visual tokens, drastically increasing memory and computational requirements in VLMs.To address this, we propose Contextual Region-Oriented Visual Token Pruning (CROP 1 ), a novel framework to compress visual tokens through a two-step process: Localization and Pruning.Specifically, CROP first employs an efficient model to identify the contextual region relevant to the input query.Subsequently, two distinct strategies are introduced for pruning: (1) Pre-LLM Compression (PLC), which adaptively compresses different image regions with varying ratios, and (2) Inner-LLM Pruning (ILP), a training-free method that prunes tokens within early LLM layers guided by the identified contextual region.Extensive experiments on a wide range of VQA tasks demonstrate that CROP significantly outperforms existing visual token pruning methods and achieves state-ofthe-art performance.

Min Xiao, Junnan Zhu, Feifei Zhai, Chengqing Zong, Yu Zhou. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Donglei Yu, Xiaomian Kang, Yuchen Liu, Feifei Zhai, Nanchang Cheng, Yu Zhou, Chengqing Zong. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Existing multimodal summarization approaches focus on fusing image features in the encoding process, ignoring the individualized needs for images when generating different summaries. However, whether intuitively or empirically, not all images can improve summary quality. Therefore, we propose a novel Dynamic Image Utilization framework for multimodal Summarization (DIUSum) to select and utilize valuable images for summarization. First, to predict whether an image helps produce a high-quality summary, we propose an image selector to score the usefulness of each image. Second, to dynamically utilize the multimodal information, we incorporate the hard and soft guidance from the image selector. Under the guidance, the image information is plugged into the decoder to generate a summary. Experimental results have shown that DIUSum outperforms multiple strong baselines and achieves SOTA on two public multimodal summarization datasets. Further analysis demonstrates that the image selector can reflect the improved level of summary quality brought by the images.

Existing Chinese spelling check (CSC) methods have limitations in correcting variable-length error characters, requiring the input and output to be the same length. They mainly focus on modelling Chinese characters’ phonetic information and generating candidates for each position. In contrast, few approaches delve into the intricacies of splitting Chinese characters to address glyph errors and splitting variable-length corrections. We define the Chinese Splitting Error Correction (CSEC) task and develop CSEC datasets in news and social media domains to address this issue. We then propose Soft-Masked Multi-feature Error Correction (SoMu) model, which first generates semantic, phonetic, graphic, and unique Chinese Wubi embeddings, then integrates those features through selective gating fusion, followed by a soft-mask strategy to filter incorrect tokens and finally use transformer layers to predict the correct ones. This model effectively addresses both spelling and splitting errors. Extensive analysis shows that our model significantly improves character-splitting information modelling for CSEC. Our dataset is available at https://github.com/Skywalker-Harrison/SoMu.

A multi-turn dialogue often contains multiple discussion topics. In several scenarios (e.g., customer service dispute, public opinion monitoring), people are only interested in the gist of a specific topic in the dialogue. Therefore, we propose a novel summarization task, i.e., Topic-Oriented Dialogue Summarization (TODS). Given a dialogue with a topic label, TODS aims to produce a summary covering the main content of the given topic in the dialogue. To model the relationship between dialogues and topics, three key abilities are needed for TODS: (1) Learning the semantic information of different topics. (2) Locating the topic-related content in the dialogue. (3) Distinguishing summaries for different topics in the same dialogue. Thus, we propose three topic-related auxiliary tasks to make the summarization model learn the three abilities above. First, the topic identification task aims at generating all the topics in the dialogue. Second, the topic attention restriction task tries to constrain the attention distribution on topic-related utterances. Third, the topic summary distinguishing task focuses on increasing the difference of summaries for different topics in the same dialogue. Experimental results on two public TODS datasets show that all auxiliary tasks are critical for TODS and help generate high-quality summaries. We also point out the expansions and challenges in TODS for future research.

While neural machine translation has achieved state-of-the-art translation performance, it is unable to capture the alignment between the input and output during the translation process. The lack of alignment in neural machine translation models leads to three problems: it is hard to (1) interpret the translation process, (2) impose lexical constraints, and (3) impose structural constraints. These problems not only increase the difficulty of designing new architectures for neural machine translation, but also limit its applications in practice. To alleviate these problems, we propose to introduce explicit phrase alignment into the translation process of arbitrary neural machine translation models. The key idea is to build a search space similar to that of phrase-based statistical machine translation for neural machine translation where phrase alignment is readily available. We design a new decoding algorithm that can easily impose lexical and structural constraints. Experiments show that our approach makes the translation process of neural machine translation more interpretable without sacrificing translation quality. In addition, our approach achieves significant improvements in lexically and structurally constrained translation tasks.

Multilingual neural machine translation (Multi-NMT) with one encoder-decoder model has made remarkable progress due to its simple deployment.However, this multilingual translation paradigm does not make full use of language commonality and parameter sharing between encoder and decoder.Furthermore, this kind of paradigm cannot outperform the individual models trained on bilingual corpus in most cases.In this paper, we propose a compact and language-sensitive method for multilingual translation.To maximize parameter sharing, we first present a universal representor to replace both encoder and decoder models.To make the representor sensitive for specific languages, we further introduce language-sensitive embedding, attention, and discriminator with the ability to enhance model performance.We verify our methods on various translation scenarios, including one-to-many, many-to-many and zero-shot.Extensive experiments demonstrate that our proposed methods remarkably outperform strong standard multilingual translation systems on WMT and IWSLT datasets.Moreover, we find that our model is especially helpful in low-resource and zero-shot translation scenarios.

Due to the benefits of model compactness, multilingual translation (including many-toone, many-to-many and one-to-many) based on a universal encoder-decoder architecture attracts more and more attention.However, previous studies show that one-to-many translation based on this framework cannot perform on par with the individually trained models.In this work, we introduce three strategies to improve one-to-many multilingual translation by balancing the shared and unique features.Within the architecture of one decoder for all target languages, we first exploit the use of unique initial states for different target languages.Then, we employ language-dependent positional embeddings.Finally and especially, we propose to divide the hidden cells of the decoder into shared and language-dependent ones.The extensive experiments demonstrate that our proposed methods can obtain remarkable improvements over the strong baselines.Moreover, our strategies can achieve comparable or even better performance than the individually trained translation models.

Although the Transformer translation model (Vaswani et al., 2017) has achieved state-ofthe-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge.In this work, we extend the Transformer model with a new context encoder to represent document-level context, which is then incorporated into the original encoder and decoder.As large-scale document-level parallel corpora are usually not available, we introduce a two-step training method to take full advantage of abundant sentence-level parallel corpora and limited document-level parallel corpora.Experiments on the NIST Chinese-English datasets and the IWSLT French-English datasets show that our approach improves over Transformer significantly. 1

We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art. Our model has the additional advantage of being very interpretable, since it allows visualization of its predictions broken up by abstract features such as information content, salience and novelty. Another novel contribution of our work is abstractive training of our extractive model that can train on human generated reference summaries alone, eliminating the need for sentence-level extractive labels.

Many natural language understanding (NLU) tasks, such as shallow parsing (i.e., text chunking) and semantic slot filling, require the assignment of representative labels to the meaningful chunks in a sentence. Most of the current deep neural network (DNN) based methods consider these tasks as a sequence labeling problem, in which a word, rather than a chunk, is treated as the basic unit for labeling. These chunks are then inferred by the standard IOB (Inside-Outside- Beginning) labels. In this paper, we propose an alternative approach by investigating the use of DNN for sequence chunking, and propose three neural models so that each chunk can be treated as a complete unit for labeling. Experimental results show that the proposed neural sequence chunking models can achieve start-of-the-art performance on both the text chunking and slot filling tasks.

In recent years, more and more Chinese people desires to be able to access the large amount of foreign language information and understand what is happening all over the world. However, language barrier is always a problem to them. In order to break the language barrier and connect Chinese people to the foreign language information in the world, Sogou has built a cross-lingual information retrieval (CLIR) system named Sogou English (http://english.sogou.com), which enables Chinese people to search and browse foreign language information with Chinese. In Sogou English, when the user inputs a Chinese query, it will first translate the Chinese query into English, and then search over the Internet, and finally translate the search results into Chinese so that users can understand them better. Hence with Sogou English, people can read and browse the information from English world without actually knowing English.

Parameter tuning is a key problem for statistical machine translation (SMT).Most popular parameter tuning algorithms for SMT are agnostic of decoding, resulting in parameters vulnerable to search errors in decoding.The recent research of "search-aware tuning" (Liu and Huang, 2014) addresses this problem by considering the partial derivations in every decoding step so that the promising ones are more likely to survive the inexact decoding beam.We extend this approach from phrase-based translation to syntaxbased translation by generalizing the evaluation metrics for partial translations to handle tree-structured derivations in a way inspired by inside-outside algorithm.Our approach is simple to use and can be applied to most of the conventional parameter tuning methods as a plugin.Extensive experiments on Chinese-to-English translation show significant BLEU improvements on MERT, MIRA and PRO.

In current research, most tree-based translation models are built directly from parse trees. In this study, we go in another direction and build a translation model with an unsupervised tree structure derived from a novel non-parametric Bayesian model. In the model, we utilize synchronous tree substitution grammars (STSG) to capture the bilingual mapping between language pairs. To train the model efficiently, we develop a Gibbs sampler with three novel Gibbs operators. The sampler is capable of exploring the infinite space of tree structures by performing local changes on the tree nodes. Experimental results show that the string-to-tree translation system using our Bayesian tree structures significantly outperforms the strong baseline string-to-tree system using parse trees.

Syntax-based models can significantly improve the translation performance due to their grammatical modeling on one or both language side(s). However, the translation rules such as the non-lexical rule “ VP→(x0x1,VP:x1PP:x0)” in string-to-tree models do not consider any lexicalized information on the source or target side. The rule is so generalized that any subtree rooted at VP can substitute for the nonterminal VP:x1. Because rules containing nonterminals are frequently used when generating the target-side tree structures, there is a risk that rules of this type will potentially be severely misused in decoding due to a lack of lexicalization guidance. In this article, inspired by lexicalized PCFG, which is widely used in monolingual parsing, we propose to upgrade the STSG (synchronous tree substitution grammars)-based syntax translation model with bilingually lexicalized STSG. Using the string-to-tree translation model as a case study, we present generative and discriminative models to integrate lexicalized STSG into the translation model. Both small- and large-scale experiments on Chinese-to-English translation demonstrate that the proposed lexicalized STSG can provide superior rule selection in decoding and substantially improve the translation quality.