Liner Yang

Cunliang Kong, Xuezhi Fang, Liner Yang et al.

Dictionaries can help language learners to learn vocabulary by providing definitions of words. Since traditional dictionaries present word senses as discrete items in predefined inventories, they fall short of flexibility, which is required in providing specific meanings of words in particular contexts. In this paper, we introduce the LitMind Dictionary (https://dictionary.litmind.ink), an open-source online generative dictionary that takes a word and context containing the word as input and automatically generates a definition as output. Incorporating state-of-the-art definition generation models, it supports not only Chinese and English, but also Chinese-English cross-lingual queries. Moreover, it has a user-friendly front-end design that can help users understand the query words quickly and easily. All the code and data are available at https://github.com/blcuicall/litmind-dictionary.

Cunliang Kong, Yun Chen, Hengyuan Zhang et al.

The definition generation task can help language learners by providing explanations for unfamiliar words. This task has attracted much attention in recent years. We propose a novel task of Simple Definition Generation (SDG) to help language learners and low literacy readers. A significant challenge of this task is the lack of learner's dictionaries in many languages, and therefore the lack of data for supervised training. We explore this task and propose a multitasking framework SimpDefiner that only requires a standard dictionary with complex definitions and a corpus containing arbitrary simple texts. We disentangle the complexity factors from the text by carefully designing a parameter sharing scheme between two decoders. By jointly training these components, the framework can generate both complex and simple definitions simultaneously. We demonstrate that the framework can generate relevant, simple definitions for the target words through automatic and manual evaluations on English and Chinese datasets. Our method outperforms the baseline model by a 1.77 SARI score on the English dataset, and raises the proportion of the low level (HSK level 1-3) words in Chinese definitions by 3.87%.

Cunliang Kong, Yujie Wang, Ruining Chong et al.

This paper describes the BLCU-ICALL system used in the SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings, the Definition Modeling subtrack, achieving 1st on Italian, 2nd on Spanish and Russian, and 3rd on English and French. We propose a transformer-based multitasking framework to explore the task. The framework integrates multiple embedding architectures through the cross-attention mechanism, and captures the structure of glosses through a masking language model objective. Additionally, we also investigate a simple but effective model ensembling strategy to further improve the robustness. The evaluation results show the effectiveness of our solution. We release our code at: https://github.com/blcuicall/SemEval2022-Task1-DM.

Ruining Chong, Luming Lu, Liner Yang et al.

Text simplification aims to make the text easier to understand by applying rewriting transformations. There has been very little research on Chinese text simplification for a long time. The lack of generic evaluation data is an essential reason for this phenomenon. In this paper, we introduce MCTS, a multi-reference Chinese text simplification dataset. We describe the annotation process of the dataset and provide a detailed analysis. Furthermore, we evaluate the performance of several unsupervised methods and advanced large language models. We additionally provide Chinese text simplification parallel data that can be used for training, acquired by utilizing machine translation and English text simplification. We hope to build a basic understanding of Chinese text simplification through the foundational work and provide references for future research. All of the code and data are released at https://github.com/blcuicall/mcts/.

Jiyuan An, Liner Yang, Mengyan Wang et al.

As spatial intelligence becomes an increasingly important capability for foundation models, it remains unclear whether large language models' (LLMs) performance on spatial reasoning benchmarks reflects structured internal spatial representations or reliance on linguistic heuristics. We address this question from a mechanistic perspective by examining how spatial information is internally represented and used. Drawing on computational theories of human spatial cognition, we decompose spatial reasoning into three primitives, relational composition, representational transformation, and stateful spatial updating, and design controlled task families for each. We evaluate multilingual LLMs in English, Chinese, and Arabic under single pass inference, and analyze internal representations using linear probing, sparse autoencoder based feature analysis, and causal interventions. We find that task relevant spatial information is encoded in intermediate layers and can causally influence behavior, but these representations are transient, fragmented across task families, and weakly integrated into final predictions. Cross linguistic analysis further reveals mechanistic degeneracy, where similar behavioral performance arises from distinct internal pathways. Overall, our results suggest that current LLMs exhibit limited and context dependent spatial representations rather than robust, general purpose spatial reasoning, highlighting the need for mechanistic evaluation beyond benchmark accuracy.

Jiaxin Yuan, Cunliang Kong, Chenhui Xie et al.

The definition generation task aims to generate a word's definition within a specific context automatically. However, owing to the lack of datasets for different complexities, the definitions produced by models tend to keep the same complexity level. This paper proposes a novel task of generating definitions for a word with controllable complexity levels. Correspondingly, we introduce COMPILING, a dataset given detailed information about Chinese definitions, and each definition is labeled with its complexity levels. The COMPILING dataset includes 74,303 words and 106,882 definitions. To the best of our knowledge, it is the largest dataset of the Chinese definition generation task. We select various representative generation methods as baselines for this task and conduct evaluations, which illustrates that our dataset plays an outstanding role in assisting models in generating different complexity-level definitions. We believe that the COMPILING dataset will benefit further research in complexity controllable definition generation.

Jinran Nie, Liner Yang, Yun Chen et al.

Text generation rarely considers the control of lexical complexity, which limits its more comprehensive practical application. We introduce a novel task of lexical complexity controlled sentence generation, which aims at keywords to sentence generation with desired complexity levels. It has enormous potential in domains such as grade reading, language teaching and acquisition. The challenge of this task is to generate fluent sentences only using the words of given complexity levels. We propose a simple but effective approach for this task based on complexity embedding. Compared with potential solutions, our approach fuses the representations of the word complexity levels into the model to get better control of lexical complexity. And we demonstrate the feasibility of the approach for both training models from scratch and fine-tuning the pre-trained models. To facilitate the research, we develop two datasets in English and Chinese respectively, on which extensive experiments are conducted. Results show that our approach better controls lexical complexity and generates higher quality sentences than baseline methods.

Jiyuan An, Jiachen Zhao, Fan Chen et al.

The construction of CAD models has traditionally relied on labor-intensive manual operations and specialized expertise. Recent advances in large language models (LLMs) have inspired research into text-to-CAD generation. However, existing approaches typically treat generation and editing as disjoint tasks, limiting their practicality. We propose PR-CAD, a progressive refinement framework that unifies generation and editing for controllable and faithful text-to-CAD modeling. To support this, we curate a high-fidelity interaction dataset spanning the full CAD lifecycle, encompassing multiple CAD representations as well as both qualitative and quantitative descriptions. The dataset systematically defines the types of edit operations and generates highly human-like interaction data. Building on a CAD representation tailored for LLMs, we propose a reinforcement learning-enhanced reasoning framework that integrates intent understanding, parameter estimation, and precise edit localization into a single agent. This enables an "all-in-one" solution for both design creation and refinement. Extensive experiments demonstrate strong mutual reinforcement between generation and editing tasks, and across qualitative and quantitative modalities. On public benchmarks, PR-CAD achieves state-of-the-art controllability and faithfulness in both generation and refinement scenarios, while also proving user-friendly and significantly improving CAD modeling efficiency.

Yang Liu, Meng Xu, Shuo Wang et al.

Modern large language models (LLMs) should generally benefit individuals from various cultural backgrounds around the world. However, most recent advanced generative evaluation benchmarks tailed for LLMs mainly focus on English. To this end, we introduce OMGEval, the first Open-source Multilingual Generative test set that can assess the capability of LLMs in different languages. For each language, OMGEval provides 804 open-ended questions, covering a wide range of important capabilities of LLMs, such as general knowledge, logical reasoning, and so on. Each question is rigorously verified by human annotators. Notably, to sufficiently reflect the compatibility of LLMs in different cultural backgrounds, we perform localization for each non-English language. Specifically, the current version of OMGEval includes 5 languages (i.e., Zh, Ru, Fr, Es, Ar). Following AlpacaEval, we employ GPT-4 as the adjudicator to automatically score different model outputs, which is shown closely related to human evaluation. We evaluate several representative multilingual LLMs on the proposed OMGEval, which we believe will provide a valuable reference for the community to further understand and improve the multilingual capability of LLMs. OMGEval is available at https://github.com/blcuicall/OMGEval.

Haoyu Wang, Shuo Wang, Yukun Yan et al. · tsinghua

Open-source large language models (LLMs) have gained significant strength across diverse fields. Nevertheless, the majority of studies primarily concentrate on English, with only limited exploration into the realm of multilingual abilities. In this work, we therefore construct an open-source multilingual supervised fine-tuning dataset. Different from previous works that simply translate English instructions, we consider both the language-specific and language-agnostic abilities of LLMs. Firstly, we introduce a knowledge-grounded data augmentation approach to elicit more language-specific knowledge of LLMs, improving their ability to serve users from different countries. Moreover, we find modern LLMs possess strong cross-lingual transfer capabilities, thus repeatedly learning identical content in various languages is not necessary. Consequently, we can substantially prune the language-agnostic supervised fine-tuning (SFT) data without any performance degradation, making multilingual SFT more efficient. The resulting UltraLink dataset comprises approximately 1 million samples across five languages (i.e., En, Zh, Ru, Fr, Es), and the proposed data construction method can be easily extended to other languages. UltraLink-LM, which is trained on UltraLink, outperforms several representative baselines across many tasks.

Buqiang Xu, Xin Dai, Zhenghao Liu et al.

Legal Judgment Prediction (LJP) is a fundamental task of legal artificial intelligence, aiming to automatically predict the judgment outcomes of legal cases. Existing LJP models primarily focus on identifying legal triggers within criminal fact descriptions by contrastively training language models. However, these LJP models overlook the importance of learning to effectively distinguish subtle differences among judgments, which is crucial for producing more accurate predictions. In this paper, we propose LegalDuet, which continuously pretrains language models to learn a more tailored embedding space for representing legal cases. Specifically, LegalDuet designs a dual-view mechanism to continuously pretrain language models: 1) Law Case Clustering retrieves similar cases as hard negatives and employs contrastive training to differentiate among confusing cases; 2) Legal Decision Matching aims to identify legal clues within criminal fact descriptions to align them with the chain of reasoning that contains the correct legal decision. Our experiments on the CAIL2018 dataset demonstrate the effectiveness of LegalDuet. Further analysis reveals that LegalDuet improves the ability of pretrained language models to distinguish confusing criminal charges by reducing prediction uncertainty and enhancing the separability of criminal charges. The experiments demonstrate that LegalDuet produces a more concentrated and distinguishable embedding space, effectively aligning criminal facts with corresponding legal decisions. The code is available at https://github.com/NEUIR/LegalDuet.

Zhenghao Liu, Xiaoyuan Yi, Maosong Sun et al.

Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. However, existing GEC models tend to produce spurious corrections or fail to detect lots of errors. The quality estimation model is necessary to ensure learners get accurate GEC results and avoid misleading from poorly corrected sentences. Well-trained GEC models can generate several high-quality hypotheses through decoding, such as beam search, which provide valuable GEC evidence and can be used to evaluate GEC quality. However, existing models neglect the possible GEC evidence from different hypotheses. This paper presents the Neural Verification Network (VERNet) for GEC quality estimation with multiple hypotheses. VERNet establishes interactions among hypotheses with a reasoning graph and conducts two kinds of attention mechanisms to propagate GEC evidence to verify the quality of generated hypotheses. Our experiments on four GEC datasets show that VERNet achieves state-of-the-art grammatical error detection performance, achieves the best quality estimation results, and significantly improves GEC performance by reranking hypotheses. All data and source codes are available at https://github.com/thunlp/VERNet.

Yuqing Lan, Zhenghao Liu, Yu Gu et al.

Fact verification tasks aim to identify the integrity of textual contents according to the truthful corpus. Existing fact verification models usually build a fully connected reasoning graph, which regards claim-evidence pairs as nodes and connects them with edges. They employ the graph to propagate the semantics of the nodes. Nevertheless, the noisy nodes usually propagate their semantics via the edges of the reasoning graph, which misleads the semantic representations of other nodes and amplifies the noise signals. To mitigate the propagation of noisy semantic information, we introduce a Confidential Graph Attention Network (CO-GAT), which proposes a node masking mechanism for modeling the nodes. Specifically, CO-GAT calculates the node confidence score by estimating the relevance between the claim and evidence pieces. Then, the node masking mechanism uses the node confidence scores to control the noise information flow from the vanilla node to the other graph nodes. CO-GAT achieves a 73.59% FEVER score on the FEVER dataset and shows the generalization ability by broadening the effectiveness to the science-specific domain.

Luming Lu, Jiyuan An, Yujie Wang et al.

Natural Language Processing (NLP) technologies have revolutionized the way we interact with information systems, with a significant focus on converting natural language queries into formal query languages such as SQL. However, less emphasis has been placed on the Corpus Query Language (CQL), a critical tool for linguistic research and detailed analysis within text corpora. The manual construction of CQL queries is a complex and time-intensive task that requires a great deal of expertise, which presents a notable challenge for both researchers and practitioners. This paper presents the first text-to-CQL task that aims to automate the translation of natural language into CQL. We present a comprehensive framework for this task, including a specifically curated large-scale dataset and methodologies leveraging large language models (LLMs) for effective text-to-CQL task. In addition, we established advanced evaluation metrics to assess the syntactic and semantic accuracy of the generated queries. We created innovative LLM-based conversion approaches and detailed experiments. The results demonstrate the efficacy of our methods and provide insights into the complexities of text-to-CQL task.

Brian S. Lin, Jiaxin Yuan, Zihan Zhou et al.

As large language models (LLMs) increasingly exhibit human-like capabilities, a fundamental question emerges: How can we enable LLMs to learn the underlying patterns from limited examples in entirely novel environments and apply them effectively? This question is central to the ability of LLMs in inductive reasoning. Existing research on LLM-based inductive reasoning can be broadly categorized based on whether the underlying rules are expressible via explicit mathematical equations. However, many recent studies in the beyond-equations category have emphasized rule design without grounding them in specific scenarios. Inspired by the parallels between inductive reasoning and human scientific discovery, we propose the task of LLM-Based Scientific Inductive Reasoning Beyond Equations and introduce a new benchmark, SIRBench-V1, to evaluate the inductive reasoning abilities of LLMs in scientific settings. Our experimental results show that current LLMs still struggle with this task, underscoring its difficulty and the need for further advancement in this area.

Jingsi Yu, Cunliang Kong, Liner Yang et al.

Sentence Pattern Structure (SPS) parsing is a syntactic analysis method primarily employed in language teaching.Existing SPS parsers rely heavily on textbook corpora for training, lacking cross-domain capability.To overcome this constraint, this paper proposes an innovative approach leveraging large language models (LLMs) within a self-training framework. Partial syntactic rules from a source domain are combined with target domain sentences to dynamically generate training data, enhancing the adaptability of the parser to diverse domains.Experiments conducted on textbook and news domains demonstrate the effectiveness of the proposed method, outperforming rule-based baselines by 1.68 points on F1 metrics.

Yujie Wang, Chao Huang, Liner Yang et al.

This paper introduces a novel crowdsourcing worker selection algorithm, enhancing annotation quality and reducing costs. Unlike previous studies targeting simpler tasks, this study contends with the complexities of label interdependencies in sequence labeling. The proposed algorithm utilizes a Combinatorial Multi-Armed Bandit (CMAB) approach for worker selection, and a cost-effective human feedback mechanism. The challenge of dealing with imbalanced and small-scale datasets, which hinders offline simulation of worker selection, is tackled using an innovative data augmentation method termed shifting, expanding, and shrinking (SES). Rigorous testing on CoNLL 2003 NER and Chinese OEI datasets showcased the algorithm's efficiency, with an increase in F1 score up to 100.04% of the expert-only baseline, alongside cost savings up to 65.97%. The paper also encompasses a dataset-independent test emulating annotation evaluation through a Bernoulli distribution, which still led to an impressive 97.56% F1 score of the expert baseline and 59.88% cost savings. Furthermore, our approach can be seamlessly integrated into Reinforcement Learning from Human Feedback (RLHF) systems, offering a cost-effective solution for obtaining human feedback.

Yingying Wang, Cunliang Kong, Liner Yang et al.

Learner corpus collects language data produced by L2 learners, that is second or foreign-language learners. This resource is of great relevance for second language acquisition research, foreign-language teaching, and automatic grammatical error correction. However, there is little focus on learner corpus for Chinese as Foreign Language (CFL) learners. Therefore, we propose to construct a large-scale, multidimensional annotated Chinese learner corpus. To construct the corpus, we first obtain a large number of topic-rich texts generated by CFL learners. Then we design an annotation scheme including a sentence acceptability score as well as grammatical error and fluency-based corrections. We build a crowdsourcing platform to perform the annotation effectively (https://yaclc.wenmind.net). We name the corpus YACLC (Yet Another Chinese Learner Corpus) and release it as part of the CUGE benchmark (http://cuge.baai.ac.cn). By analyzing the original sentences and annotations in the corpus, we found that YACLC has a considerable size and very high annotation quality. We hope this corpus can further enhance the studies on Chinese International Education and Chinese automatic grammatical error correction.

Shengsheng Zhang, Yaping Huang, Yun Chen et al.

Most existing Grammatical Error Correction (GEC) methods based on sequence-to-sequence mainly focus on how to generate more pseudo data to obtain better performance. Few work addresses few-shot GEC domain adaptation. In this paper, we treat different GEC domains as different GEC tasks and propose to extend meta-learning to few-shot GEC domain adaptation without using any pseudo data. We exploit a set of data-rich source domains to learn the initialization of model parameters that facilitates fast adaptation on new resource-poor target domains. We adapt GEC model to the first language (L1) of the second language learner. To evaluate the proposed method, we use nine L1s as source domains and five L1s as target domains. Experiment results on the L1 GEC domain adaptation dataset demonstrate that the proposed approach outperforms the multi-task transfer learning baseline by 0.50 $F_{0.5}$ score on average and enables us to effectively adapt to a new L1 domain with only 200 parallel sentences.

Cunliang Kong, Liner Yang, Tianzuo Zhang et al.

Generating dictionary definitions automatically can prove useful for language learners. However, it's still a challenging task of cross-lingual definition generation. In this work, we propose to generate definitions in English for words in various languages. To achieve this, we present a simple yet effective approach based on publicly available pretrained language models. In this approach, models can be directly applied to other languages after trained on the English dataset. We demonstrate the effectiveness of this approach on zero-shot definition generation. Experiments and manual analyses on newly constructed datasets show that our models have a strong cross-lingual transfer ability and can generate fluent English definitions for Chinese words. We further measure the lexical complexity of generated and reference definitions. The results show that the generated definitions are much simpler, which is more suitable for language learners.

Liner Yang, Chencheng Wang, Yun Chen et al.

Due to the lack of parallel data in current Grammatical Error Correction (GEC) task, models based on Sequence to Sequence framework cannot be adequately trained to obtain higher performance. We propose two data synthesis methods which can control the error rate and the ratio of error types on synthetic data. The first approach is to corrupt each word in the monolingual corpus with a fixed probability, including replacement, insertion and deletion. Another approach is to train error generation models and further filtering the decoding results of the models. The experiments on different synthetic data show that the error rate is 40% and the ratio of error types is the same can improve the model performance better. Finally, we synthesize about 100 million data and achieve comparable performance as the state of the art, which uses twice as much data as we use.

Yong Hu, Heyan Huang, Tian Lan et al.

Second language acquisition (SLA) modeling is to predict whether second language learners could correctly answer the questions according to what they have learned. It is a fundamental building block of the personalized learning system and has attracted more and more attention recently. However, as far as we know, almost all existing methods cannot work well in low-resource scenarios due to lacking of training data. Fortunately, there are some latent common patterns among different language-learning tasks, which gives us an opportunity to solve the low-resource SLA modeling problem. Inspired by this idea, in this paper, we propose a novel SLA modeling method, which learns the latent common patterns among different language-learning datasets by multi-task learning and are further applied to improving the prediction performance in low-resource scenarios. Extensive experiments show that the proposed method performs much better than the state-of-the-art baselines in the low-resource scenario. Meanwhile, it also obtains improvement slightly in the non-low-resource scenario.

Liner Yang, Cunliang Kong, Yun Chen et al.

Chinese definition modeling is a challenging task that generates a dictionary definition in Chinese for a given Chinese word. To accomplish this task, we construct the Chinese Definition Modeling Corpus (CDM), which contains triples of word, sememes and the corresponding definition. We present two novel models to improve Chinese definition modeling: the Adaptive-Attention model (AAM) and the Self- and Adaptive-Attention Model (SAAM). AAM successfully incorporates sememes for generating the definition with an adaptive attention mechanism. It has the capability to decide which sememes to focus on and when to pay attention to sememes. SAAM further replaces recurrent connections in AAM with self-attention and relies entirely on the attention mechanism, reducing the path length between word, sememes and definition. Experiments on CDM demonstrate that by incorporating sememes, our best proposed model can outperform the state-of-the-art method by +6.0 BLEU.

Liner Yang, Meishan Zhang, Yang Liu et al.

While part-of-speech (POS) tagging and dependency parsing are observed to be closely related, existing work on joint modeling with manually crafted feature templates suffers from the feature sparsity and incompleteness problems. In this paper, we propose an approach to joint POS tagging and dependency parsing using transition-based neural networks. Three neural network based classifiers are designed to resolve shift/reduce, tagging, and labeling conflicts. Experiments show that our approach significantly outperforms previous methods for joint POS tagging and dependency parsing across a variety of natural languages.