Wang, Ming
DeFine: A Decomposed and Fine-Grained Annotated Dataset for Long-form Article Generation
Wang, Ming, Wang, Fang, Hu, Minghao, He, Li, Wang, Haiyang, Zhang, Jun, Yan, Tianwei, Li, Li, Luo, Zhunchen, Luo, Wei, Bai, Xiaoying, Geng, Guotong
Long-form article generation (LFAG) presents challenges such as maintaining logical consistency, comprehensive topic coverage, and narrative coherence across extended articles. Existing datasets often lack both the hierarchical structure and fine-grained annotation needed to effectively decompose tasks, resulting in shallow, disorganized article generation. To address these limitations, we introduce DeFine, a Decomposed and Fine-grained annotated dataset for long-form article generation. DeFine is characterized by its hierarchical decomposition strategy and the integration of domain-specific knowledge with multi-level annotations, ensuring granular control and enhanced depth in article generation. To construct the dataset, a multi-agent collaborative pipeline is proposed, which systematically segments the generation process into four parts: Data Miner, Cite Retreiver, Q&A Annotator and Data Cleaner. To validate the effectiveness of DeFine, we designed and tested three LFAG baselines: the web retrieval, the local retrieval, and the grounded reference. We fine-tuned the Qwen2-7b-Instruct model using the DeFine training dataset. The experimental results showed significant improvements in text quality, specifically in topic coverage, depth of information, and content fidelity. Our dataset publicly available to facilitate future research.
Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis
Zhao, Jiaqi, Wang, Ming, Zhang, Miao, Shang, Yuzhang, Liu, Xuebo, Wang, Yaowei, Zhang, Min, Nie, Liqiang
Post-training Quantization (PTQ) technique has been extensively adopted for large language models (LLMs) compression owing to its efficiency and low resource requirement. However, current research lacks a in-depth analysis of the superior and applicable scenarios of each PTQ strategy. In addition, existing algorithms focus primarily on performance, overlooking the trade-off among model size, performance, and quantization bitwidth. To mitigate these confusions, we provide a novel benchmark for LLMs PTQ in this paper. Firstly, in order to support our benchmark, we propose a comprehensive taxonomy for existing mainstream methods by scrutinizing their computational strategies (e.g., optimization-based, compensation-based, etc.). Then, we conduct extensive experiments with the baseline within each class, covering models with various sizes (7B-70B), bitwidths, training levels (LLaMA1/2/3/3.1), architectures (Mixtral, DeepSeekMoE and Mamba) and modality (LLaVA1.5 and VILA1.5) on a wide range of evaluation metrics.Through comparative analysis on the results, we summarize the superior of each PTQ strategy and modelsize-bitwidth trade-off considering the performance. For example, our benchmark reveals that compensation-based technique demonstrates outstanding cross-architecture robustness and extremely low-bit PTQ for ultra large models should be reexamined. Finally, we further accordingly claim that a practical combination of compensation and other PTQ strategy can achieve SOTA various robustness. We believe that our benchmark will provide valuable recommendations for the deployment of LLMs and future research on PTQ approaches.
PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models
Zhao, Jiaqi, Zhang, Miao, Wang, Ming, Shang, Yuzhang, Zhang, Kaihao, Guan, Weili, Wang, Yaowei, Zhang, Min
Large Language Models (LLMs) suffer severe performance degradation when facing extremely low-bit (sub 2-bit) quantization. Several existing sub 2-bit post-training quantization (PTQ) methods utilize a mix-precision scheme by leveraging an unstructured fine-grained mask to explicitly distinguish salient weights, while which introduces an extra 1-bit or more per weight. To explore the real limit of PTQ, we propose an extremely low-bit PTQ method called PTQ1.61, which enables weight quantization to 1.61-bit for the first time. Specifically, we first introduce a one-dimensional structured mask with negligibly additional 0.0002-bit per weight based on input activations from the perspective of reducing the upper bound of quantization error to allocate corresponding salient weight channels to 4-bit. For non-salient channels binarization, an efficient block-wise scaling factors optimization framework is then presented to take implicit row-wise correlations and angular biases into account. Different from prior works that concentrate on adjusting quantization methodologies, we further propose a novel paradigm called quantization preprocessing, where we argue that transforming the weight distribution of the pretrained model before quantization can alleviate the difficulty in per-channel extremely low-bit PTQ. Extensive experiments indicate our PTQ1.61 achieves state-of-the-art performance in extremely low-bit quantization. Codes are available at https://github.com/zjq0455/PTQ1.61.
Language Models as Continuous Self-Evolving Data Engineers
Wang, Peidong, Wang, Ming, Ma, Zhiming, Yang, Xiaocui, Feng, Shi, Wang, Daling, Zhang, Yifei
Large Language Models (LLMs) have demonstrated remarkable capabilities on various tasks, while the further evolvement is limited to the lack of high-quality training data. In addition, traditional training approaches rely too much on expert-labeled data, setting an upper limit on the performance of LLMs. To address this issue, we propose a novel paradigm that enables LLMs to train itself by autonomously generating, cleaning, reviewing, and annotating data with preference information, named LANCE. Our approach demonstrates that LLMs can serve as continuous self-evolving data engineers, significantly reducing the time and cost of the post-training data construction process. Through iterative fine-tuning on different variants of the Qwen2, we validate the effectiveness of LANCE across various tasks, showing that it can continuously improve model performance and maintain high-quality data generation. Across eight benchmark dimensions, LANCE resulted in an average score enhancement of 3.36 for Qwen2-7B and 2.70 for Qwen2-7B-Instruct. This training paradigm with autonomous data construction not only reduces the reliance on human experts or external models but also ensures that the data aligns with human values and preferences, paving the way for the development of future superintelligent systems that can exceed human capabilities.
Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts
Wang, Ming, Liu, Yuanzhong, Liang, Xiaoyu, Huang, Yijie, Wang, Daling, Yang, Xiaocui, Shen, Sijia, Feng, Shi, Zhang, Xiaoming, Guan, Chaofeng, Zhang, Yifei
LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to assist them in their work poses a challenge for non-AI experts. Existing research in prompt engineering suggests somewhat scattered optimization principles and designs empirically dependent prompt optimizers. Unfortunately, these endeavors lack a structural design, incurring high learning costs and it is not conducive to the iterative updating of prompts, especially for non-AI experts. Inspired by structured reusable programming languages, we propose LangGPT, a structural prompt design framework. Furthermore, we introduce Minstrel, a multi-generative agent system with reflection to automate the generation of structural prompts. Experiments and the case study illustrate that structural prompts generated by Minstrel or written manually significantly enhance the performance of LLMs. Furthermore, we analyze the ease of use of structural prompts through a user survey in our online community.
FEEL: A Framework for Evaluating Emotional Support Capability with Large Language Models
Zhang, Huaiwen, Chen, Yu, Wang, Ming, Feng, Shi
Emotional Support Conversation (ESC) is a typical dialogue that can effectively assist the user in mitigating emotional pressures. However, owing to the inherent subjectivity involved in analyzing emotions, current non-artificial methodologies face challenges in effectively appraising the emotional support capability. These metrics exhibit a low correlation with human judgments. Concurrently, manual evaluation methods extremely will cause high costs. To solve these problems, we propose a novel model FEEL (Framework for Evaluating Emotional Support Capability with Large Lan-guage Models), employing Large Language Models (LLMs) as evaluators to assess emotional support capabilities. The model meticulously considers various evaluative aspects of ESC to apply a more comprehensive and accurate evaluation method for ESC. Additionally, it employs a probability distribution approach for a more stable result and integrates an ensemble learning strategy, leveraging multiple LLMs with assigned weights to enhance evaluation accuracy. To appraise the performance of FEEL, we conduct extensive experiments on existing ESC model dialogues. Experimental results demonstrate our model exhibits a substantial enhancement in alignment with human evaluations compared to the baselines. Our source code is available at https://github.com/Ansisy/FEEL.
Is Mamba Effective for Time Series Forecasting?
Wang, Zihan, Kong, Fanheng, Feng, Shi, Wang, Ming, Yang, Xiaocui, Zhao, Han, Wang, Daling, Zhang, Yifei
In the realm of time series forecasting (TSF), it is imperative for models to adeptly discern and distill hidden patterns within historical time series data to forecast future states. Transformer-based models exhibit formidable efficacy in TSF, primarily attributed to their advantage in apprehending these patterns. However, the quadratic complexity of the Transformer leads to low computational efficiency and high costs, which somewhat hinders the deployment of the TSF model in real-world scenarios. Recently, Mamba, a selective state space model, has gained traction due to its ability to process dependencies in sequences while maintaining near-linear complexity. For TSF tasks, these characteristics enable Mamba to comprehend hidden patterns as the Transformer and reduce computational overhead compared to the Transformer. Therefore, we propose a Mamba-based model named Simple-Mamba (S-Mamba) for TSF. Specifically, we tokenize the time points of each variate autonomously via a linear layer. A bidirectional Mamba layer is utilized to extract inter-variate correlations and a Feed-Forward Network is set to learn temporal dependencies. Finally, the generation of forecast outcomes through a linear mapping layer. Experiments on thirteen public datasets prove that S-Mamba maintains low computational overhead and achieves leading performance. Furthermore, we conduct extensive experiments to explore Mamba's potential in TSF tasks. Our code is available at https://github.com/wzhwzhwzh0921/S-D-Mamba.
MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks
Yang, Xiaocui, Wu, Wenfang, Feng, Shi, Wang, Ming, Wang, Daling, Li, Yang, Sun, Qi, Zhang, Yifei, Fu, Xiaoming, Poria, Soujanya
The popularity of multimodal large language models (MLLMs) has triggered a recent surge in research efforts dedicated to evaluating these models. Nevertheless, existing evaluation studies of MLLMs primarily focus on the comprehension and reasoning of unimodal (vision) content, neglecting performance evaluations in the domain of multimodal (vision-language) content understanding. Beyond multimodal reasoning, tasks related to multimodal content comprehension necessitate a profound understanding of multimodal contexts, achieved through the multimodal interaction to obtain a final answer. In this paper, we introduce a comprehensive assessment framework called MM-BigBench, which incorporates a diverse range of metrics to offer an extensive evaluation of the performance of various models and instructions across a wide spectrum of diverse multimodal content comprehension tasks. Consequently, our work complements research on the performance of MLLMs in multimodal comprehension tasks, achieving a more comprehensive and holistic evaluation of MLLMs. To begin, we employ the Best Performance metric to ascertain each model's performance upper bound on different datasets. Subsequently, the Mean Relative Gain metric offers an assessment of the overall performance of various models and instructions, while the Stability metric measures their sensitivity. Furthermore, previous research centers on evaluating models independently or solely assessing instructions, neglecting the adaptability between models and instructions. We propose the Adaptability metric to quantify the adaptability between models and instructions. Our paper evaluates a total of 20 language models (14 MLLMs) on 14 multimodal datasets spanning 6 tasks, with 10 instructions for each task, and derives novel insights. Our code will be released at https://github.com/declare-lab/MM-BigBench.
T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems
Wang, Ming, Wang, Daling, Wu, Wenfang, Feng, Shi, Zhang, Yifei
Machine learning (ML) based systems have been suffering a lack of interpretability. To address this problem, counterfactual explanations (CEs) have been proposed. CEs are unique as they provide workable suggestions to users, in addition to explaining why a certain outcome was predicted. However, the application of CEs has been hindered by two main challenges, namely general user preferences and variable ML systems. User preferences, in particular, tend to be general rather than specific feature values. Additionally, CEs need to be customized to suit the variability of ML models, while also maintaining robustness even when these validation models change. To overcome these challenges, we propose several possible general user preferences that have been validated by user research and map them to the properties of CEs. We also introduce a new method called \uline{T}ree-based \uline{C}onditions \uline{O}ptional \uline{L}inks (T-COL), which has two optional structures and several groups of conditions for generating CEs that can be adapted to general user preferences. Meanwhile, a group of conditions lead T-COL to generate more robust CEs that have higher validity when the ML model is replaced. We compared the properties of CEs generated by T-COL experimentally under different user preferences and demonstrated that T-COL is better suited for accommodating user preferences and variable ML systems compared to baseline methods including Large Language Models.
RoCar: A Relationship Network-based Evaluation Method to Large Language Models
Wang, Ming, Wu, Wenfang, Gao, Chongyun, Wang, Daling, Feng, Shi, Zhang, Yifei
Pre-trained Models have become the dominant approach in the field of deep learning since Transformer [1]. Buy now, the Large Language Models (LLMs) represented by ChatGPT [2] have received the widest attention from researchers in the field of Artificial Intelligence (AI), especially Natural Language Processing (NLP). Like LLaMA [3], many open-source LLMs [4, 5, 6, 3, 7, 8] have been published. Due to the strong reasoning, generative and memory abilities acquired by LLMs during training, they are able to operate a variety of traditional tasks based on specific prompts and achieve great performance. As a result, LLMs have gained widespread interest and applications, such as in the financial [9], emotional [10, 11], legal [12], medical [13, 14, 15] and educational [16] fields. To evaluate the capability of LLMs and to guide the selection of more appropriate LLMs in applications, many evaluation approaches [17] for LLMs have been proposed by researchers. C-Eval [18] constructed a reasoning test set of 13,948 questions in 52 subjects ranging from junior school to postgraduate university and vocational exams to evaluate LLM's problem-solving skills. Gaokao-Bench [19] collected questions from the 2010-2022 Chinese national college entrance examination papers, including 1,781 objective questions and 1,030 subjective questions, and constructed a framework for assessing the language comprehension and logical reasoning ability of LLMs. Microsoft has released a new benchmark test, AGIEval [20], by selecting 20 official, public, high-standard exams, including general university entrance exams (Chinese national college entrance examination and the U.S. SAT), law school entrance exams, maths competitions, bar exams, national civil service exams, and more.