Zhaokun Jiang, Qianxi Lv, Ziyin Zhang, Lei Lei
The growing popularity of neural machine translation (NMT) and LLMs represented by ChatGPT underscores the need for a deeper understanding of their distinct characteristics and relationships. Such understanding is crucial for language professionals and researchers to make informed decisions and tactful use of these cutting-edge translation technology, but remains underexplored. This study aims to fill this gap by investigating three key questions: (1) the distinguishability of ChatGPT-generated translations from NMT and human translation (HT), (2) the linguistic characteristics of each translation type, and (3) the degree of resemblance between ChatGPT-produced translations and HT or NMT. To achieve these objectives, we employ statistical testing, machine learning algorithms, and multidimensional analysis (MDA) to analyze Spokesperson's Remarks and their translations. After extracting a wide range of linguistic features, supervised classifiers demonstrate high accuracy in distinguishing the three translation types, whereas unsupervised clustering techniques do not yield satisfactory results. Another major finding is that ChatGPT-produced translations exhibit greater similarity with NMT than HT in most MDA dimensions, which is further corroborated by distance computing and visualization. These novel insights shed light on the interrelationships among the three translation types and have implications for the future advancements of NMT and generative AI.
Zeli Su, Ziyin Zhang, Guixian Xu, Jianing Liu, XU Han, Ting Zhang, Yushuang Dong
While multilingual language models like XLM-R have advanced multilingualism in NLP, they still perform poorly in extremely low-resource languages. This situation is exacerbated by the fact that modern LLMs such as LLaMA and Qwen support far fewer languages than XLM-R, making text generation models non-existent for many languages in the world. To tackle this challenge, we propose a novel framework for adapting multilingual encoders to text generation in extremely low-resource languages. By reusing the weights between the encoder and the decoder, our framework allows the model to leverage the learned semantic space of the encoder, enabling efficient learning and effective generalization in low-resource languages. Applying this framework to four Chinese minority languages, we present XLM-SWCM, and demonstrate its superior performance on various downstream tasks even when compared with much larger models.
Zhaokun Jiang, Ziyin Zhang
Hedges are widely studied across registers and disciplines, yet research on the translation of hedges in political texts is extremely limited. This contrastive study is dedicated to investigating whether there is a diachronic change in the frequencies of hedging devices in the target texts, to what extent the changing frequencies of translated hedges through years are attributed to the source texts, and what translation strategies are adopted to deal with them. For the purposes of this research, two types of official political texts and their translations from China and the United Nations were collected to form three sub-corpora. Results show that hedges tend to appear more frequently in English political texts, be it original English or translated English. In addition, directionality seems to play an important role in influencing both the frequencies and translation strategies regarding the use of hedges. A noticeable diachronic increase of hedging devices is also observed in our corpus.
Ziyin Zhang, Chaoyu Chen, Bingchang Liu, Cong Liao, Zi Gong, Hang Yu, Jianguo Li, Rui Wang
In this work we systematically review the recent advancements in software engineering with language models, covering 70+ models, 40+ evaluation tasks, 180+ datasets, and 900 related works. Unlike previous works, we integrate software engineering (SE) with natural language processing (NLP) by discussing the perspectives of both sides: SE applies language models for development automation, while NLP adopts SE tasks for language model evaluation. We break down code processing models into general language models represented by the GPT family and specialized models that are specifically pretrained on code, often with tailored objectives. We discuss the relations and differences between these models, and highlight the historical transition of code modeling from statistical models and RNNs to pretrained Transformers and LLMs, which is exactly the same course that had been taken by NLP. We also go beyond programming and review LLMs' application in other software engineering activities including requirement engineering, testing, deployment, and operations in an endeavor to provide a global view of NLP in SE, and identify key challenges and potential future directions in this domain. We keep the survey open and updated on GitHub at https://github.com/codefuse-ai/Awesome-Code-LLM.
Jin Qin, Zihan Liao, Ziyin Zhang, Hang Yu, Peng Di, Rui Wang
We present C2LLM - Contrastive Code Large Language Models, a family of code embedding models in both 0.5B and 7B sizes. Building upon Qwen-2.5-Coder backbones, C2LLM adopts a Pooling by Multihead Attention (PMA) module for generating sequence embedding from token embeddings, effectively 1) utilizing the LLM's causal representations acquired during pretraining, while also 2) being able to aggregate information from all tokens in the sequence, breaking the information bottleneck in EOS-based sequence embeddings, and 3) supporting flexible adaptation of embedding dimension, serving as an alternative to MRL. Trained on three million publicly available data, C2LLM models set new records on MTEB-Code among models of similar sizes, with C2LLM-7B ranking 1st on the overall leaderboard.
Ziyin Zhang, Yikang Liu, Weifang Huang, Junyu Mao, Rui Wang, Hai Hu
In this work, we present the largest benchmark to date on linguistic acceptability: Multilingual Evaluation of Linguistic Acceptability -- MELA, with 46K samples covering 10 languages from a diverse set of language families. We establish LLM baselines on this benchmark, and investigate cross-lingual transfer in acceptability judgements with XLM-R. In pursuit of multilingual interpretability, we conduct probing experiments with fine-tuned XLM-R to explore the process of syntax capability acquisition. Our results show that GPT-4o exhibits a strong multilingual ability, outperforming fine-tuned XLM-R, while open-source multilingual models lag behind by a noticeable gap. Cross-lingual transfer experiments show that transfer in acceptability judgment is non-trivial: 500 Icelandic fine-tuning examples lead to 23 MCC performance in a completely unrelated language -- Chinese. Results of our probing experiments indicate that training on MELA improves the performance of XLM-R on syntax-related tasks. Our data is available at https://github.com/sjtu-compling/MELA.
Zhaokun Jiang, Ziyin Zhang
Recent advancements in machine learning have spurred growing interests in automated interpreting quality assessment. Nevertheless, existing research suffers from insufficient examination of language use quality, unsatisfactory modeling effectiveness due to data scarcity and imbalance, and a lack of efforts to explain model predictions. To address these gaps, we propose a multi-dimensional modeling framework that integrates feature engineering, data augmentation, and explainable machine learning. This approach prioritizes explainability over ``black box'' predictions by utilizing only construct-relevant, transparent features and conducting Shapley Value (SHAP) analysis. Our results demonstrate strong predictive performance on a novel English-Chinese consecutive interpreting dataset, identifying BLEURT and CometKiwi scores to be the strongest predictive features for fidelity, pause-related features for fluency, and Chinese-specific phraseological diversity metrics for language use. Overall, by placing particular emphasis on explainability, we present a scalable, reliable, and transparent alternative to traditional human evaluation, facilitating the provision of detailed diagnostic feedback for learners and supporting self-regulated learning advantages not afforded by automated scores in isolation.
Ziyin Zhang, Zihan Liao, Hang Yu, Peng Di, Rui Wang
We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available high-quality data samples, F2LLM-v2 supports more than 200 languages, with a particular emphasis on previously underserved mid- and low-resource languages. By integrating a two-stage LLM-based embedding training pipeline with matryoshka learning, model pruning, and knowledge distillation techniques, we present models that are far more efficient than previous LLM-based embedding models while retaining competitive performances. Extensive evaluations confirm that F2LLM-v2-14B ranks first on 11 MTEB benchmarks, while the smaller models in the family also set a new state of the art for resource-constrained applications. To facilitate open-source embedding model research, we release all models, data, code, and intermediate checkpoints.
Jun Wang, Ziyin Zhang, Rui Wang, Hang Yu, Peng Di, Rui Wang
Real-time detection and mitigation of technical anomalies are critical for large-scale cloud-native services, where even minutes of downtime can result in massive financial losses and diminished user trust. While customer incidents serve as a vital signal for discovering risks missed by monitoring, extracting actionable intelligence from this data remains challenging due to extreme noise, high throughput, and semantic complexity of diverse business lines. In this paper, we present TingIS, an end-to-end system designed for enterprise-grade incident discovery. At the core of TingIS is a multi-stage event linking engine that synergizes efficient indexing techniques with Large Language Models (LLMs) to make informed decisions on event merging, enabling the stable extraction of actionable incidents from just a handful of diverse user descriptions. This engine is complemented by a cascaded routing mechanism for precise business attribution and a multi-dimensional noise reduction pipeline that integrates domain knowledge, statistical patterns, and behavioral filtering. Deployed in a production environment handling a peak throughput of over 2,000 messages per minute and 300,000 messages per day, TingIS achieves a P90 alert latency of 3.5 minutes and a 95\% discovery rate for high-priority incidents. Benchmarks constructed from real-world data demonstrate that TingIS significantly outperforms baseline methods in routing accuracy, clustering quality, and Signal-to-Noise Ratio.
Ziyin Zhang, Hang Yu, Shijie Li, Peng Di, Jianguo Li, Rui Wang
Programming languages possess rich semantic information - such as data flow - that is represented by graphs and not available from the surface form of source code. Recent code language models have scaled to billions of parameters, but model source code solely as text tokens while ignoring any other structural information. Conversely, models that do encode structural information of code make modifications to the Transformer architecture, limiting their scale and compatibility with pretrained LLMs. In this work, we take the best of both worlds with GALLa - Graph Aligned Large Language Models. GALLa utilizes graph neural networks and cross-modal alignment technologies to inject the structural information of code into LLMs as an auxiliary task during finetuning. This framework is both model-agnostic and task-agnostic, as it can be applied to any code LLM for any code downstream task, and requires the structural graph data only at training time from a corpus unrelated to the finetuning data, while incurring no cost at inference time over the baseline LLM. Experiments on five code tasks with seven different baseline LLMs ranging in size from 350M to 14B validate the effectiveness of GALLa, demonstrating consistent improvement over the baseline, even for powerful models such as LLaMA3 and Qwen2.5-Coder.
Hai Hu, Ziyin Zhang, Weifang Huang, Jackie Yan-Ki Lai, Aini Li, Yina Patterson, Jiahui Huang, Peng Zhang, Chien-Jer Charles Lin, Rui Wang
In this work, we revisit linguistic acceptability in the context of large language models. We introduce CoLAC - Corpus of Linguistic Acceptability in Chinese, the first large-scale acceptability dataset for a non-Indo-European language. It is verified by native speakers and is the first acceptability dataset that comes with two sets of labels: a linguist label and a crowd label. Our experiments show that even the largest InstructGPT model performs only at chance level on CoLAC, while ChatGPT's performance (48.30 MCC) is also much below supervised models (59.03 MCC) and human (65.11 MCC). Through cross-lingual transfer experiments and fine-grained linguistic analysis, we provide detailed analysis of the model predictions and demonstrate for the first time that knowledge of linguistic acceptability can be transferred across typologically distinct languages, as well as be traced back to pre-training. Our dataset is publicly available at \url{https://github.com/huhailinguist/CoLAC}.
Ziyin Zhang, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Rui Wang, Zhaopeng Tu
Conventional speculative decoding (SD) methods utilize a predefined length policy for proposing drafts, which implies the premise that the target model smoothly accepts the proposed draft tokens. However, reality deviates from this assumption: the oracle draft length varies significantly, and the fixed-length policy hardly satisfies such a requirement. Moreover, such discrepancy is further exacerbated in scenarios involving complex reasoning and long-form generation, particularly under test-time scaling for reasoning-specialized models. Through both theoretical and empirical estimation, we establish that the discrepancy between the draft and target models can be approximated by the draft model's prediction entropy: a high entropy indicates a low acceptance rate of draft tokens, and vice versa. Based on this insight, we propose SVIP: Self-Verification Length Policy for Long-Context Speculative Decoding, which is a training-free dynamic length policy for speculative decoding systems that adaptively determines the lengths of draft sequences by referring to the draft entropy. Experimental results on mainstream SD benchmarks as well as reasoning-heavy benchmarks demonstrate the superior performance of SVIP, achieving up to 17% speedup on MT-Bench at 8K context compared with fixed draft lengths, and 22% speedup for QwQ in long-form reasoning.
Ziyin Zhang, Ning Lu, Minghui Liao, Yongshuai Huang, Cheng Li, Min Wang, Wei Peng
Text recognition methods are gaining rapid development. Some advanced techniques, e.g., powerful modules, language models, and un- and semi-supervised learning schemes, consecutively push the performance on public benchmarks forward. However, the problem of how to better optimize a text recognition model from the perspective of loss functions is largely overlooked. CTC-based methods, widely used in practice due to their good balance between performance and inference speed, still grapple with accuracy degradation. This is because CTC loss emphasizes the optimization of the entire sequence target while neglecting to learn individual characters. We propose a self-distillation scheme for CTC-based model to address this issue. It incorporates a framewise regularization term in CTC loss to emphasize individual supervision, and leverages the maximizing-a-posteriori of latent alignment to solve the inconsistency problem that arises in distillation between CTC-based models. We refer to the regularized CTC loss as Distillation Connectionist Temporal Classification (DCTC) loss. DCTC loss is module-free, requiring no extra parameters, longer inference lag, or additional training data or phases. Extensive experiments on public benchmarks demonstrate that DCTC can boost text recognition model accuracy by up to 2.6%, without any of these drawbacks.
Yikang Liu, Ziyin Zhang, Wanyang Zhang, Shisen Yue, Xiaojing Zhao, Xinyuan Cheng, Yiwen Zhang, Hai Hu
AI generated content (AIGC) presents considerable challenge to educators around the world. Instructors need to be able to detect such text generated by large language models, either with the naked eye or with the help of some tools. There is also growing need to understand the lexical, syntactic and stylistic features of AIGC. To address these challenges in English language teaching, we first present ArguGPT, a balanced corpus of 4,038 argumentative essays generated by 7 GPT models in response to essay prompts from three sources: (1) in-class or homework exercises, (2) TOEFL and (3) GRE writing tasks. Machine-generated texts are paired with roughly equal number of human-written essays with three score levels matched in essay prompts. We then hire English instructors to distinguish machine essays from human ones. Results show that when first exposed to machine-generated essays, the instructors only have an accuracy of 61% in detecting them. But the number rises to 67% after one round of minimal self-training. Next, we perform linguistic analyses of these essays, which show that machines produce sentences with more complex syntactic structures while human essays tend to be lexically more complex. Finally, we test existing AIGC detectors and build our own detectors using SVMs and RoBERTa. Results suggest that a RoBERTa fine-tuned with the training set of ArguGPT achieves above 90% accuracy in both essay- and sentence-level classification. To the best of our knowledge, this is the first comprehensive analysis of argumentative essays produced by generative large language models. Machine-authored essays in ArguGPT and our models will be made publicly available at https://github.com/huhailinguist/ArguGPT
Zhaokun Jiang, Qianxi Lv, Ziyin Zhang, Lei Lei
Large language models have demonstrated parallel and even superior translation performance compared to neural machine translation (NMT) systems. However, existing comparative studies between them mainly rely on automated metrics, raising questions into the feasibility of these metrics and their alignment with human judgment. The present study investigates the convergences and divergences between automated metrics and human evaluation in assessing the quality of machine translation from ChatGPT and three NMT systems. To perform automatic assessment, four automated metrics are employed, while human evaluation incorporates the DQF-MQM error typology and six rubrics. Notably, automatic assessment and human evaluation converge in measuring formal fidelity (e.g., error rates), but diverge when evaluating semantic and pragmatic fidelity, with automated metrics failing to capture the improvement of ChatGPT's translation brought by prompt engineering. These results underscore the indispensable role of human judgment in evaluating the performance of advanced translation tools at the current stage.
Ziyin Zhang, Zhaokun Jiang, Lizhen Xu, Hongkun Hao, Rui Wang
We present GSM-MC, a multiple-choice (MC) dataset constructed by collecting answers and incorrect predictions on GSM8K from 60 open-source models. Through extensive experiments, we show that LLMs' performance on the MC version of this popular benchmark is strongly correlated with their performance on the original version and is quite robust to distractor choices and option orders, while the evaluation time is reduced by a factor of up to 30. Following similar procedures, we introduce MATH-MC, constructed from MATH, and PythonIO, a new program reasoning MC dataset constructed from HumanEval and MBPP. Experimental results indicate that LLMs' performance on these MC benchmarks leaves much room for improvement. Our data and code are available at https://github.com/Geralt-Targaryen/MC-Evaluation.
Ziyin Zhang, Jiahao Xu, Zhiwei He, Tian Liang, Qiuzhi Liu, Yansi Li, Linfeng Song, Zhenwen Liang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems that poorly align with LLMs' strength derived from informal, natural language knowledge acquired during pre-training. In this work, we propose DeepTheorem, a comprehensive informal theorem-proving framework exploiting natural language to enhance LLM mathematical reasoning. DeepTheorem includes a large-scale benchmark dataset consisting of 121K high-quality IMO-level informal theorems and proofs spanning diverse mathematical domains, rigorously annotated for correctness, difficulty, and topic categories, accompanied by systematically constructed verifiable theorem variants. We devise a novel reinforcement learning strategy (RL-Zero) explicitly tailored to informal theorem proving, leveraging the verified theorem variants to incentivize robust mathematical inference. Additionally, we propose comprehensive outcome and process evaluation metrics examining proof correctness and the quality of reasoning steps. Extensive experimental analyses demonstrate DeepTheorem significantly improves LLM theorem-proving performance compared to existing datasets and supervised fine-tuning protocols, achieving state-of-the-art accuracy and reasoning quality. Our findings highlight DeepTheorem's potential to fundamentally advance automated informal theorem proving and mathematical exploration.
Ziyin Zhang, Zihan Liao, Hang Yu, Peng Di, Rui Wang
We introduce F2LLM - Foundation to Feature Large Language Models, a suite of state-of-the-art embedding models in three sizes: 0.6B, 1.7B, and 4B. Unlike previous top-ranking embedding models that require massive contrastive pretraining, sophisticated training pipelines, and costly synthetic training data, F2LLM is directly finetuned from foundation models on 6 million query-document-negative tuples curated from open-source, non-synthetic datasets, striking a strong balance between training cost, model size, and embedding performance. On the MTEB English leaderboard, F2LLM-4B ranks 2nd among models with approximately 4B parameters and 7th overall, while F2LLM-1.7B ranks 1st among models in the 1B-2B size range. To facilitate future research in the field, we release the models, training dataset, and code, positioning F2LLM as a strong, reproducible, and budget-friendly baseline for future works.
Yiming Ai, Zhiwei He, Ziyin Zhang, Wenhong Zhu, Hongkun Hao, Kai Yu, Lingjun Chen, Rui Wang
In this study, we delve into the validity of conventional personality questionnaires in capturing the human-like personality traits of Large Language Models (LLMs). Our objective is to assess the congruence between the personality traits LLMs claim to possess and their demonstrated tendencies in real-world scenarios. By conducting an extensive examination of LLM outputs against observed human response patterns, we aim to understand the disjunction between self-knowledge and action in LLMs.
Jaap Jumelet, Abdellah Fourtassi, Akari Haga, Bastian Bunzeck, Bhargav Shandilya, Diana Galvan-Sosa, Faiz Ghifari Haznitrama, Francesca Padovani, Francois Meyer, Hai Hu, Julen Etxaniz, Laurent Prévot, Linyang He, María Grandury, Mila Marcheva, Negar Foroutan, Nikitas Theodoropoulos, Pouya Sadeghi, Siyuan Song, Suchir Salhan, Susana Zhou, Yurii Paniv, Ziyin Zhang, Arianna Bisazza, Alex Warstadt, Leshem Choshen
We present BabyBabelLM, a multilingual collection of datasets modeling the language a person observes from birth until they acquire a native language. We curate developmentally plausible pretraining data aiming to cover the equivalent of 100M English words of content in each of 45 languages. We compile evaluation suites and train baseline models in each language. BabyBabelLM aims to facilitate multilingual pretraining and cognitive modeling.