Search

With the rise of globalisation, code-switching (CSW) has become a ubiquitous part of multilingual conversation, posing new challenges for natural language processing (NLP), especially in Grammatical Error Correction (GEC). This work explores the complexities of applying GEC systems to CSW texts. Our objectives include evaluating the performance of state-of-the-art GEC systems on an authentic CSW dataset from English as a Second Language (ESL) learners, exploring synthetic data generation as a solution to data scarcity, and developing a model capable of correcting grammatical errors in monolingual and CSW texts. We generated synthetic CSW GEC data, resulting in one of the first substantial datasets for this task, and showed that a model trained on this data is capable of significant improvements over existing systems. This work targets ESL learners, aiming to provide educational technologies that aid in the development of their English grammatical correctness without constraining their natural multilingualism.

In this article, we introduce some generalized Hardy spaces on fibrations of planar domains and fibrations of products of planar domains. We consider the kernel functions on these spaces, and we prove some weighted versions of Saitoh's conjecture in fibration cases., Comment: 48 pages. All comments are welcome!

To tackle the difficulties in fitting paired real-world data for single image deraining (SID), recent unsupervised methods have achieved notable success. However, these methods often struggle to generate high-quality, rain-free images due to a lack of attention to semantic representation and image content, resulting in ineffective separation of content from the rain layer. In this paper, we propose a novel cycle contrastive generative adversarial network for unsupervised SID, called CCLGAN. This framework combines cycle contrastive learning (CCL) and location contrastive learning (LCL). CCL improves image reconstruction and rain-layer removal by bringing similar features closer and pushing dissimilar features apart in both semantic and discriminative spaces. At the same time, LCL preserves content information by constraining mutual information at the same location across different exemplars. CCLGAN shows superior performance, as extensive experiments demonstrate the benefits of CCLGAN and the effectiveness of its components.

Currently many benchmarks have been proposed to evaluate the perception ability of the Large Vision-Language Models (LVLMs). However, most benchmarks conduct questions by selecting images from existing datasets, resulting in the potential data leakage. Besides, these benchmarks merely focus on evaluating LVLMs on the realistic style images and clean scenarios, leaving the multi-stylized images and noisy scenarios unexplored. In response to these challenges, we propose a dynamic and scalable benchmark named Dysca for evaluating LVLMs by leveraging synthesis images. Specifically, we leverage Stable Diffusion and design a rule-based method to dynamically generate novel images, questions and the corresponding answers. We consider 51 kinds of image styles and evaluate the perception capability in 20 subtasks. Moreover, we conduct evaluations under 4 scenarios (i.e., Clean, Corruption, Print Attacking and Adversarial Attacking) and 3 question types (i.e., Multi-choices, True-or-false and Free-form). Thanks to the generative paradigm, Dysca serves as a scalable benchmark for easily adding new subtasks and scenarios. A total of 8 advanced open-source LVLMs with 10 checkpoints are evaluated on Dysca, revealing the drawbacks of current LVLMs. The benchmark is released in \url{https://github.com/Benchmark-Dysca/Dysca}.

Despite the rapid progress and outstanding performance of Large Vision-Language Models (LVLMs) in recent years, LVLMs have been plagued by the issue of hallucination, i.e., LVLMs tend to generate responses that are inconsistent with the corresponding visual inputs. To evaluate the degree of hallucination in LVLMs, previous works have proposed a series of benchmarks featuring different types of tasks and evaluation metrics. However, we find that the quality of the existing hallucination benchmarks varies, with some suffering from problems, e.g., inconsistent evaluation results under repeated tests, and misalignment with human evaluation. To this end, we propose a Hallucination benchmark Quality Measurement framework (HQM), which leverages various indicators to assess the reliability and validity of existing hallucination benchmarks separately. Specifically, for reliability we explore test-retest reliability and parallel-forms reliability, while for validity we examine criterion validity and coverage of hallucination types. Furthermore, based on the results of our quality measurement, we construct a High-Quality Hallucination Benchmark (HQH) for LVLMs, which demonstrates superior reliability and validity under our HQM framework. We conduct an extensive evaluation of over 10 representative LVLMs, including GPT-4o and Gemini-1.5-Pro, to provide an in-depth analysis of the hallucination issues in existing models. Our benchmark is publicly available at https://github.com/HQHBench/HQHBench.

The emergence of Large Vision-Language Models (LVLMs) marks significant strides towards achieving general artificial intelligence. However, these advancements are tempered by the outputs that often reflect biases, a concern not yet extensively investigated. Existing benchmarks are not sufficiently comprehensive in evaluating biases due to their limited data scale, single questioning format and narrow sources of bias. To address this problem, we introduce VLBiasBench, a benchmark aimed at evaluating biases in LVLMs comprehensively. In VLBiasBench, we construct a dataset encompassing nine distinct categories of social biases, including age, disability status, gender, nationality, physical appearance, race, religion, profession, social economic status and two intersectional bias categories (race x gender, and race x social economic status). To create a large-scale dataset, we use Stable Diffusion XL model to generate 46,848 high-quality images, which are combined with different questions to form 128,342 samples. These questions are categorized into open and close ended types, fully considering the sources of bias and comprehensively evaluating the biases of LVLM from multiple perspectives. We subsequently conduct extensive evaluations on 15 open-source models as well as one advanced closed-source model, providing some new insights into the biases revealing from these models. Our benchmark is available at https://github.com/Xiangkui-Cao/VLBiasBench.

Generating accurate SQL from natural language questions (text-to-SQL) is a long-standing challenge due to the complexities in user question understanding, database schema comprehension, and SQL generation. Conventional text-to-SQL systems, comprising human engineering and deep neural networks, have made substantial progress. Subsequently, pre-trained language models (PLMs) have been developed and utilized for text-to-SQL tasks, achieving promising performance. As modern databases become more complex, the corresponding user questions also grow more challenging, causing PLMs with parameter constraints to produce incorrect SQL. This necessitates more sophisticated and tailored optimization methods, which, in turn, restricts the applications of PLM-based systems. Recently, large language models (LLMs) have demonstrated significant capabilities in natural language understanding as the model scale increases. Therefore, integrating LLM-based implementation can bring unique opportunities, improvements, and solutions to text-to-SQL research. In this survey, we present a comprehensive review of LLM-based text-to-SQL. Specifically, we propose a brief overview of the technical challenges and the evolutionary process of text-to-SQL. Then, we provide a detailed introduction to the datasets and metrics designed to evaluate text-to-SQL systems. After that, we present a systematic analysis of recent advances in LLM-based text-to-SQL. Finally, we discuss the remaining challenges in this field and propose expectations for future research directions.

Code-switching (CSW) is a common phenomenon among multilingual speakers where multiple languages are used in a single discourse or utterance. Mixed language utterances may still contain grammatical errors however, yet most existing Grammar Error Correction (GEC) systems have been trained on monolingual data and not developed with CSW in mind. In this work, we conduct the first exploration into the use of GEC systems on CSW text. Through this exploration, we propose a novel method of generating synthetic CSW GEC datasets by translating different spans of text within existing GEC corpora. We then investigate different methods of selecting these spans based on CSW ratio, switch-point factor and linguistic constraints, and identify how they affect the performance of GEC systems on CSW text. Our best model achieves an average increase of 1.57 $F_{0.5}$ across 3 CSW test sets (English-Chinese, English-Korean and English-Japanese) without affecting the model's performance on a monolingual dataset. We furthermore discovered that models trained on one CSW language generalise relatively well to other typologically similar CSW languages.

Hallucination in Natural Language Generation (NLG) is like the elephant in the room, obvious but often overlooked until recent achievements significantly improved the fluency and grammaticality of generated text. As the capabilities of text generation models have improved, researchers have begun to pay more attention to the phenomenon of hallucination. Despite significant progress in this field in recent years, the evaluation system for hallucination is complex and diverse, lacking clear organization. We are the first to comprehensively survey how various evaluation methods have evolved with the development of text generation models from three dimensions, including hallucinated fact granularity, evaluator design principles, and assessment facets. This survey aims to help researchers identify current limitations in hallucination evaluation and highlight future research directions., Comment: 16 pages, 2 figures

This study explores F0 entrainment in second language (L2) English speech imitation during an Alternating Reading Task (ART). Participants with Italian, French, and Slovak native languages imitated English utterances, and their F0 entrainment was quantified using the Dynamic Time Warping (DTW) distance between the parameterized F0 contours of the imitated utterances and those of the model utterances. Results indicate a nuanced relationship between L2 English proficiency and entrainment: speakers with higher proficiency generally exhibit less entrainment in pitch variation and declination. However, within dyads, the more proficient speakers demonstrate a greater ability to mimic pitch range, leading to increased entrainment. This suggests that proficiency influences entrainment differently at individual and dyadic levels, highlighting the complex interplay between language skill and prosodic adaptation., Comment: Accepted at Speech Prosody 2024

Traffic flow modeling relies heavily on fundamental diagrams. However, deterministic fundamental diagrams, such as single or multi-regime models, cannot capture the uncertainty pattern that underlies traffic flow. To address this limitation, a sparse non-parametric regression model is proposed in this paper to formulate the stochastic fundamental diagram. Unlike parametric stochastic fundamental diagram models, a non-parametric model is insensitive to parameters, flexible, and applicable. The computation complexity and the huge memory required for training in the Gaussian process regression have been reduced by introducing the sparse Gaussian process regression. The paper also discusses how empirical knowledge influences the modeling process. The paper analyzes the influence of modeling empirical knowledge in the prior of the stochastic fundamental diagram model and whether empirical knowledge can improve the robustness and accuracy of the proposed model. By introducing several well-known single-regime fundamental diagram models as the prior and testing the model's robustness and accuracy with different sampling methods given real-world data, the authors find that empirical knowledge can only benefit the model under small inducing samples given a relatively clean and large dataset. A pure data-driven approach is sufficient to estimate and describe the pattern of the density-speed relationship.

We introduce the Alternating Reading Task (ART) Corpus, a collection of dyadic sentence reading for studying the entrainment and imitation behaviour in speech communication. The ART corpus features three experimental conditions - solo reading, alternating reading, and deliberate imitation - as well as three sub-corpora encompassing French-, Italian-, and Slovak-accented English. This design allows systematic investigation of speech entrainment in a controlled and less-spontaneous setting. Alongside detailed transcriptions, it includes English proficiency scores, demographics, and in-experiment questionnaires for probing linguistic, personal and interpersonal influences on entrainment. Our presentation covers its design, collection, annotation processes, initial analysis, and future research prospects., Comment: 15 pages, 2 figures, 7 tables, accepted at LREC-COLING 2024 conference

In this study, we evaluated the performance of the state-of-the-art sequence tagging grammar error detection and correction model (SeqTagger) using Japanese university students' writing samples. With an automatic annotation toolkit, ERRANT, we first evaluated SeqTagger's performance on error correction with human expert correction as the benchmark. Then a human-annotated approach was adopted to evaluate Seqtagger's performance in error detection using a subset of the writing dataset. Results indicated a precision of 63.66% and a recall of 20.19% for error correction in the full dataset. For the subset, after manual exclusion of irrelevant errors such as semantic and mechanical ones, the model shows an adjusted precision of 97.98% and an adjusted recall of 42.98% for error detection, indicating the model's high accuracy but also its conservativeness. Thematic analysis on errors undetected by the model revealed that determiners and articles, especially the latter, were predominant. Specifically, in terms of context-independent errors, the model occasionally overlooked basic ones and faced challenges with overly erroneous or complex structures. Meanwhile, context-dependent errors, notably those related to tense and noun number, as well as those possibly influenced by the students' first language (L1), remained particularly challenging., Comment: 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Lexical Simplification (LS) aims to simplify text at the lexical level. Existing methods rely heavily on annotated data, making it challenging to apply in low-resource scenarios. In this paper, we propose a novel LS method without parallel corpora. This method employs an Adversarial Editing System with guidance from a confusion loss and an invariance loss to predict lexical edits in the original sentences. Meanwhile, we introduce an innovative LLM-enhanced loss to enable the distillation of knowledge from Large Language Models (LLMs) into a small-size LS system. From that, complex words within sentences are masked and a Difficulty-aware Filling module is crafted to replace masked positions with simpler words. At last, extensive experimental results and analyses on three benchmark LS datasets demonstrate the effectiveness of our proposed method., Comment: Accepted by COLING 2024 main conference

Generating accurate SQL queries for user questions (text-to-SQL) has been a long-standing challenge since it requires a deep understanding of both the user's question and the corresponding database schema in order to retrieve the desired content accurately. Existing methods rely on the comprehensive capability of large language models (LLMs) to generate the SQL. However, some necessary knowledge is not explicitly included in the database schema and user question or has been learned by LLMs. Thus, the generated SQL of the knowledge-insufficient questions may be inaccurate, negatively influencing the text-to-SQL models' performance and robustness. To address this challenge, we propose the Knowledge-to-SQL framework, which employs tailored Data Expert LLM (DELLM) to provide helpful knowledge for all text-to-SQL models. Specifically, we introduce the detailed implementation of DELLM regarding table reading and the basic fine-tuning process. We further propose a Preference Learning via Database Feedback (PLDBF) strategy, refining the DELLM to generate more helpful knowledge for LLMs. Extensive experiments verify that DELLM can enhance the state-of-the-art approaches for text-to-SQL tasks. The corresponding code of DELLM is released for further research., Comment: Accepted to ACL2024 Findings

Representing information of multiple behaviors in the single graph collaborative filtering (CF) vector has been a long-standing challenge. This is because different behaviors naturally form separate behavior graphs and learn separate CF embeddings. Existing models merge the separate embeddings by appointing the CF embeddings for some behaviors as the primary embedding and utilizing other auxiliaries to enhance the primary embedding. However, this approach often results in the joint embedding performing well on the main tasks but poorly on the auxiliary ones. To address the problem arising from the separate behavior graphs, we propose the concept of Partial Order Recommendation Graphs (POG). POG defines the partial order relation of multiple behaviors and models behavior combinations as weighted edges to merge separate behavior graphs into a joint POG. Theoretical proof verifies that POG can be generalized to any given set of multiple behaviors. Based on POG, we propose the tailored Partial Order Graph Convolutional Networks (POGCN) that convolute neighbors' information while considering the behavior relations between users and items. POGCN also introduces a partial-order BPR sampling strategy for efficient and effective multiple-behavior CF training. POGCN has been successfully deployed on the homepage of Alibaba for two months, providing recommendation services for over one billion users. Extensive offline experiments conducted on three public benchmark datasets demonstrate that POGCN outperforms state-of-the-art multi-behavior baselines across all types of behaviors. Furthermore, online A/B tests confirm the superiority of POGCN in billion-scale recommender systems., Comment: Accepted by KDD2024

Large-scale pre-trained vision-language models like CLIP have demonstrated impressive performance across various tasks, and exhibit remarkable zero-shot generalization capability, while they are also vulnerable to imperceptible adversarial examples. Existing works typically employ adversarial training (fine-tuning) as a defense method against adversarial examples. However, direct application to the CLIP model may result in overfitting, compromising the model's capacity for generalization. In this paper, we propose Pre-trained Model Guided Adversarial Fine-Tuning (PMG-AFT) method, which leverages supervision from the original pre-trained model by carefully designing an auxiliary branch, to enhance the model's zero-shot adversarial robustness. Specifically, PMG-AFT minimizes the distance between the features of adversarial examples in the target model and those in the pre-trained model, aiming to preserve the generalization features already captured by the pre-trained model. Extensive Experiments on 15 zero-shot datasets demonstrate that PMG-AFT significantly outperforms the state-of-the-art method, improving the top-1 robust accuracy by an average of 4.99%. Furthermore, our approach consistently improves clean accuracy by an average of 8.72%. Our code is available at https://github.com/serendipity1122/Pre-trained-Model-Guided-Fine-Tuning-for-Zero-Shot-Adversarial-Robustness., Comment: Accepted by CVPR 2024

In recent years, the Vision Transformer (ViT) model has gradually become mainstream in various computer vision tasks, and the robustness of the model has received increasing attention. However, existing large models tend to prioritize performance during training, potentially neglecting the robustness, which may lead to serious security concerns. In this paper, we establish a new challenge: exploring how to use a small number of additional parameters for adversarial finetuning to quickly and effectively enhance the adversarial robustness of a standardly trained model. To address this challenge, we develop the novel LNLoRA module, incorporating a learnable layer normalization before the conventional LoRA module, which helps mitigate magnitude differences in parameters between the adversarial and standard training paradigms. Furthermore, we propose the FullLoRA-AT framework by integrating the learnable LNLoRA modules into all key components of ViT-based models while keeping the pretrained model frozen, which can significantly improve the model robustness via adversarial finetuning in a parameter-efficient manner. Extensive experiments on CIFAR-10, CIFAR-100, and Imagenette demonstrate the superiority of our proposed FullLoRA-AT framework. It achieves comparable robustness with full finetuning while only requiring about 5% of the learnable parameters. This also effectively addresses concerns regarding extra model storage space and enormous training time caused by adversarial finetuning., Comment: 10 pages, 2 figures, 6 tables

We propose a novel approach to enable the agile manipulation of light- and dark-seeking particles. Our approach involves introducing a two-curvilinear perfect optical vortex beam (TC-POVB) generated by superimposing a pair of curved beams. The TC-POVB exhibits the property of a perfect optical vortex, which means that its size remains constant regardless of its topological charge. Additionally, each curve of the TC-POVB can support a distinct orbital flow density (OFD). This enables the application of torques to produce a dark channel that satisfies the requirements for particle size and drives the revolution or rotation motion of the confined dark-seeking particles. To demonstrate the effectiveness of our approach, we manipulate light- and dark-seeking particles experimentally, making them perform various curvilinear trajectories simultaneously, including moving, revolving, and rotating.

Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias. Inspired by speculative decoding and contrastive decoding, we introduce Speculative Contrastive Decoding~(SCD), a straightforward yet powerful decoding approach that leverages predictions from smaller language models~(LMs) to achieve both decoding acceleration and quality improvement. Extensive evaluations and analyses on four diverse language tasks demonstrate the effectiveness of SCD, showing that decoding efficiency and quality can compatibly benefit from one smaller LM., Comment: Revised version

The complementary potential of Large Language Models (LLM) assumes off-the-shelf LLMs have heterogeneous expertise in a wide range of domains and tasks so that an ensemble of LLMs can achieve consistently better performance. Existing ensemble methods for LLMs mainly focus on reward model ranking of outputs, leading to significant computation overhead. To combat this issue, we revisit the complementary potential of LLMs and further elaborate it by mining latent expertise with off-the-shelf reward models. We propose Zooter, a reward-guided routing method distilling rewards on training queries to train a routing function, which can precisely distribute each query to the LLM with expertise about it. We also integrate a tag-based label enhancement to mitigate noise from uncertainty when using rewards as silver supervision. Zooter shows computation efficiency in inference as it introduces only a minor computation overhead of a routing function compared with reward model ranking methods. We evaluate Zooter on a comprehensive benchmark collection with 26 subsets on different domains and tasks. Zooter outperforms the best single model on average and ranks first on 44% of tasks, even surpassing multiple reward model ranking methods.

In this article, we prove that for any Zhou valuation $\nu$, there exists a graded sequence of ideals $\mathfrak{a}_{\bullet}$ and a nonzero ideal $\mathfrak{q}$ such that $\nu$ $\mathscr{A}-$computes the jumping number $\mathrm{lct}^{\mathfrak{q}}(\mathfrak{a}_{\bullet})$, and that for the subadditive sequence $\mathfrak{b}^{\varphi}_{\bullet}$ related to a plurisubharmonic function $\varphi$, there exists a Zhou valuation which $\mathscr{A}-$computes $\mathrm{lct}^{\mathfrak{q}}(\mathfrak{b}^{\varphi}_{\bullet})$, where the ``$\mathscr{A}-$compute'' coincides with the ``compute'' in Jonsson-Musta\c{t}\u{a}'s Conjecture when the Zhou valuation $\nu$ is quasimonomial. We also give a characterization for a valuation being a Zhou valuation., Comment: 19 pages, all comments are welcome!

In the present paper, we give the definition and properties of the multipoled global Zhou weights. Some approximation and convergence results of multipoled global Zhou weights are given. We also establish a semi-continuity result for the Zhou numbers., Comment: 27 pages. All comments are welcome!

In this paper, we present the results of the NeurIPS-2022 Neural MMO Challenge, which attracted 500 participants and received over 1,600 submissions. Like the previous IJCAI-2022 Neural MMO Challenge, it involved agents from 16 populations surviving in procedurally generated worlds by collecting resources and defeating opponents. This year's competition runs on the latest v1.6 Neural MMO, which introduces new equipment, combat, trading, and a better scoring system. These elements combine to pose additional robustness and generalization challenges not present in previous competitions. This paper summarizes the design and results of the challenge, explores the potential of this environment as a benchmark for learning methods, and presents some practical reinforcement learning training approaches for complex tasks with sparse rewards. Additionally, we have open-sourced our baselines, including environment wrappers, benchmarks, and visualization tools for future research.

The emergence of large language models (LLMs) has revolutionized natural language processing tasks. However, existing instruction-tuning datasets suffer from occupational bias: the majority of data relates to only a few occupations, which hampers the instruction-tuned LLMs to generate helpful responses to professional queries from practitioners in specific fields. To mitigate this issue and promote occupation-inclusive LLMs, we create an instruction-tuning dataset named \emph{OccuQuest}, which contains 110,000+ prompt-completion pairs and 30,000+ dialogues covering over 1,000 occupations in 26 occupational categories. We systematically request ChatGPT, organizing queries hierarchically based on Occupation, Responsibility, Topic, and Question, to ensure a comprehensive coverage of occupational specialty inquiries. By comparing with three commonly used datasets (Dolly, ShareGPT, and WizardLM), we observe that OccuQuest exhibits a more balanced distribution across occupations. Furthermore, we assemble three test sets for comprehensive evaluation, an occu-test set covering 25 occupational categories, an estate set focusing on real estate, and an occu-quora set containing real-world questions from Quora. We then fine-tune LLaMA on OccuQuest to obtain OccuLLaMA, which significantly outperforms state-of-the-art LLaMA variants (Vicuna, Tulu, and WizardLM) on professional questions in GPT-4 and human evaluations. Notably, on the occu-quora set, OccuLLaMA reaches a high win rate of 86.4\% against WizardLM.

Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape, and it is becoming clear that the quality of automatic evaluation metrics is not keeping up with the pace of development of generative models. We aim to improve the understanding of current models' performance by providing a preliminary and hybrid evaluation on a range of open and closed-source generative LLMs on three NLP benchmarks: text summarisation, text simplification and grammatical error correction (GEC), using both automatic and human evaluation. We also explore the potential of the recently released GPT-4 to act as an evaluator. We find that ChatGPT consistently outperforms many other popular models according to human reviewers on the majority of metrics, while scoring much more poorly when using classic automatic evaluation metrics. We also find that human reviewers rate the gold reference as much worse than the best models' outputs, indicating the poor quality of many popular benchmarks. Finally, we find that GPT-4 is capable of ranking models' outputs in a way which aligns reasonably closely to human judgement despite task-specific variations, with a lower alignment in the GEC task., Comment: Accepted at EMNLP 2023

In math reasoning with large language models (LLMs), fine-tuning data augmentation by query evolution and diverse reasoning paths is empirically verified effective, profoundly narrowing the gap between open-sourced LLMs and cutting-edge proprietary LLMs. In this paper, we conduct an investigation for such data augmentation in math reasoning and are intended to answer: (1) What strategies of data augmentation are more effective; (2) What is the scaling relationship between the amount of augmented data and model performance; and (3) Can data augmentation incentivize generalization to out-of-domain mathematical reasoning tasks? To this end, we create two new dataset AugGSM8K and AugMATH, by complicating and diversifying the queries and sampling multiple reasoning paths from GSM8K and MATH. We obtained a series of LLMs called MuggleMath by fine-tuning LLaMA models on AugGSM8K and AugMATH. MuggleMath substantially achieves new state-of-the-art on GSM8K and MATH. A log-linear relationship and a segmented log-linear are presented between MuggleMath's performance and the amount of augmented data on GSM8K and MATH, respectively. We also find that it is weak in out-of-domain math reasoning generalization from AugGSM8K to MATH and from AugMATH to GSM8K, which suggests that augmenting queries that cover a broader range of subjects is more beneficial for generalization. We release our codes and augmented data in https://github.com/OFA-Sys/gsm8k-ScRel., Comment: Accepted to ACL 2024 Main Conference

Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning (SFT). While the open-source community has explored ad-hoc SFT for enhancing individual capabilities, proprietary LLMs exhibit versatility across various skills. Therefore, understanding the facilitation of multiple abilities via SFT is paramount. In this study, we specifically focuses on the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during SFT. We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies. Our experiments reveal that distinct capabilities scale differently and larger models generally show superior performance with same amount of data. Mathematical reasoning and code generation consistently improve with increasing data amount, whereas general abilities plateau after roughly a thousand samples. Moreover, we observe data composition appears to enhance various abilities under limited data conditions, yet can lead to performance conflicts when data is plentiful. Our findings also suggest the amount of composition data influences performance more than the composition ratio. In analysis of SFT strategies, we find that sequentially learning multiple skills risks catastrophic forgetting. Our proposed Dual-stage Mixed Fine-tuning (DMT) strategy offers a promising solution to learn multiple abilities with different scaling patterns., Comment: Accepted to ACL 2024 Main Conference

In this article, we obtain a class of tame maximal weights (Zhou weights). Using Tian functions (the function of jumping numbers with respect to the exponents of a holomorphic function or the multiples of a plurisubharmonic function) as a main tool, we establish an expression of relative types (Zhou numbers) to these tame maximal weights in integral form, which shows that the relative types satisfy tropical multiplicativity and tropical additivity. Thus, the relative types to Zhou weights are valuations (Zhou valuations) on the ring of germs of holomorphic functions. We use Tian functions and Zhou numbers to measure the singularities of plurisubharmonic functions, involving jumping numbers and multiplier ideal sheaves. Especially, the relative types to Zhou weights characterize the division relations of the ring of germs of holomorphic functions. Finally, we consider a global version of Zhou weights on domains in $\mathbb{C}^n$, which is a generalization of the pluricomplex Green functions, and we obtain some properties of them, including continuity and some approximation results., Comment: 55 pages, all comments are welcome!

Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a multitude of downstream tasks, and the chat models, particularly those trained using Reinforcement Learning from Human Feedback (RLHF), are highly competitive. The chat models possess advanced tool-use and planning capabilities for creating agent applications, showcasing impressive performance even when compared to bigger models on complex tasks like utilizing a code interpreter. Furthermore, we have developed coding-specialized models, Code-Qwen and Code-Qwen-Chat, as well as mathematics-focused models, Math-Qwen-Chat, which are built upon base language models. These models demonstrate significantly improved performance in comparison with open-source models, and slightly fall behind the proprietary models., Comment: 59 pages, 5 figures

Large foundational models, through upstream pre-training and downstream fine-tuning, have achieved immense success in the broad AI community due to improved model performance and significant reductions in repetitive engineering. By contrast, the transferable one-for-all models in the recommender system field, referred to as TransRec, have made limited progress. The development of TransRec has encountered multiple challenges, among which the lack of large-scale, high-quality transfer learning recommendation dataset and benchmark suites is one of the biggest obstacles. To this end, we introduce NineRec, a TransRec dataset suite that comprises a large-scale source domain recommendation dataset and nine diverse target domain recommendation datasets. Each item in NineRec is accompanied by a descriptive text and a high-resolution cover image. Leveraging NineRec, we enable the implementation of TransRec models by learning from raw multimodal features instead of relying solely on pre-extracted off-the-shelf features. Finally, we present robust TransRec benchmark results with several classical network architectures, providing valuable insights into the field. To facilitate further research, we will release our code, datasets, benchmarks, and leaderboards at https://github.com/westlake-repl/NineRec.

Foundation language models obtain the instruction-following ability through supervised fine-tuning (SFT). Diversity and complexity are considered critical factors of a successful SFT dataset, while their definitions remain obscure and lack quantitative analyses. In this work, we propose InsTag, an open-set fine-grained tagger, to tag samples within SFT datasets based on semantics and intentions and define instruction diversity and complexity regarding tags. We obtain 6.6K tags to describe comprehensive user queries. Then we analyze popular open-sourced SFT datasets and find that the model ability grows with more diverse and complex data. Based on this observation, we propose a data selector based on InsTag to select 6K diverse and complex samples from open-source datasets and fine-tune models on InsTag-selected data. The resulting models, TagLM, outperform open-source models based on considerably larger SFT data evaluated by MT-Bench, echoing the importance of query diversity and complexity. We open-source InsTag in https://github.com/OFA-Sys/InsTag.

Mathematical reasoning is a challenging task for large language models (LLMs), while the scaling relationship of it with respect to LLM capacity is under-explored. In this paper, we investigate how the pre-training loss, supervised data amount, and augmented data amount influence the reasoning performances of a supervised LLM. We find that pre-training loss is a better indicator of the model's performance than the model's parameter count. We apply supervised fine-tuning (SFT) with different amounts of supervised data and empirically find a log-linear relation between data amount and model performance, and we find better models improve less with enlarged supervised datasets. To augment more data samples for improving model performances without any human effort, we propose to apply Rejection sampling Fine-Tuning (RFT). RFT uses supervised models to generate and collect correct reasoning paths as augmented fine-tuning datasets. We find with augmented samples containing more distinct reasoning paths, RFT improves mathematical reasoning performance more for LLMs. We also find RFT brings more improvement for less performant LLMs. Furthermore, we combine rejection samples from multiple models which push LLaMA-7B to an accuracy of 49.3\% on GSM8K which outperforms the supervised fine-tuning (SFT) accuracy of 35.9\% significantly., Comment: Working in Progress

In this article, we consider a generalization of the conjugate Hardy $H^2$ spaces, and give some properties of the minimal norm of the generalization and some relations between the norm of the generalization and the minimal $L^2$ integrals. As applications, we give some monotonicity results for the conjugate Hardy $H^2$ kernels and the Bergman kernels on planar regions, and some relations between the conjugate Hardy $H^2$ kernels and the Bergman kernels on planar regions., Comment: 22 pages, all comments are welcome!

The recent release of very large language models such as PaLM and GPT-4 has made an unprecedented impact in the popular media and public consciousness, giving rise to a mixture of excitement and fear as to their capabilities and potential uses, and shining a light on natural language processing research which had not previously received so much attention. The developments offer great promise for education technology, and in this paper we look specifically at the potential for incorporating large language models in AI-driven language teaching and assessment systems. We consider several research areas and also discuss the risks and ethical considerations surrounding generative AI in education technology for language learners. Overall we find that larger language models offer improvements over previous models in text generation, opening up routes toward content generation which had not previously been plausible. For text generation they must be prompted carefully and their outputs may need to be reshaped before they are ready for use. For automated grading and grammatical error correction, tasks whose progress is checked on well-known benchmarks, early investigations indicate that large language models on their own do not improve on state-of-the-art results according to standard evaluation metrics. For grading it appears that linguistic features established in the literature should still be used for best performance, and for error correction it may be that the models can offer alternative feedback styles which are not measured sensitively with existing methods. In all cases, there is work to be done to experiment with the inclusion of large language models in education technology for language learners, in order to properly understand and report on their capacities and limitations, and to ensure that foreseeable risks such as misinformation and harmful bias are mitigated., Comment: Accepted at the AIED2023 workshop: Empowering Education with LLMs - the Next-Gen Interface and Content Generation

In this article, we give some necessary conditions for the concavity property of minimal $L^2$ integrals degenerating to partial linearity, a charaterization for the concavity degenerating to partial linearity for open Riemann surfaces, and some relations between the concavity property for minimal $L^2$ integrals and the log-convexity for Bergman kernels., Comment: Some typos have been corrected. 37 pages, all comments are welcome! arXiv admin note: text overlap with arXiv:2211.00470