Qwen2 Technical Report

This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruction-tuned language models, encompassing a parameter range from 0.5 to 72 billion, featuring dense models and a Mixture-of-Experts model. Qwen2 surpasses most prior open-weight models, including its predecessor Qwen1.5, and exhibits competitive performance relative to proprietary models across diverse benchmarks on language understanding, generation, multilingual proficiency, coding, mathematics, and reasoning. The flagship model, Qwen2-72B, showcases remarkable performance: 84.2 on MMLU, 37.9 on GPQA, 64.6 on HumanEval, 89.5 on GSM8K, and 82.4 on BBH as a base language model. The instruction-tuned variant, Qwen2-72B-Instruct, attains 9.1 on MT-Bench, 48.1 on Arena-Hard, and 35.7 on LiveCodeBench. Moreover, Qwen2 demonstrates robust multilingual capabilities, proficient in approximately 30 languages, spanning English, Chinese, Spanish, French, German, Arabic, Russian, Korean, Japanese, Thai, Vietnamese, and more, underscoring its versatility and global reach. To foster community innovation and accessibility, we have made the Qwen2 model weights openly available on Hugging Face and ModelScope, and the supplementary materials including example code on GitHub. These platforms also include resources for quantization, fine-tuning, and deployment, facilitating a wide range of applications and research endeavors.

Qwen2-Audio Technical Report

We introduce the latest progress of Qwen-Audio, a large-scale audio-language model called Qwen2-Audio, which is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions. In contrast to complex hierarchical tags, we have simplified the pre-training process by utilizing natural language prompts for different data and tasks, and have further expanded the data volume. We have boosted the instruction-following capability of Qwen2-Audio and implemented two distinct audio interaction modes for voice chat and audio analysis. In the voice chat mode, users can freely engage in voice interactions with Qwen2-Audio without text input. In the audio analysis mode, users could provide audio and text instructions for analysis during the interaction. Note that we do not use any system prompts to switch between voice chat and audio analysis modes. Qwen2-Audio is capable of intelligently comprehending the content within audio and following voice commands to respond appropriately. For instance, in an audio segment that simultaneously contains sounds, multi-speaker conversations, and a voice command, Qwen2-Audio can directly understand the command and provide an interpretation and response to the audio. Additionally, DPO has optimized the model's performance in terms of factuality and adherence to desired behavior. According to the evaluation results from AIR-Bench, Qwen2-Audio outperformed previous SOTAs, such as Gemini-1.5-pro, in tests focused on audio-centric instruction-following capabilities. Qwen2-Audio is open-sourced with the aim of fostering the advancement of the multi-modal language community.

VideoCoT: A Video Chain-of-Thought Dataset with Active Annotation Tool

Multimodal large language models (MLLMs) are flourishing, but mainly focus on images with less attention than videos, especially in sub-fields such as prompt engineering, video chain-of-thought (CoT), and instruction tuning on videos. Therefore, we try to explore the collection of CoT datasets in videos to lead to video OpenQA and improve the reasoning ability of MLLMs. Unfortunately, making such video CoT datasets is not an easy task. Given that human annotation is too cumbersome and expensive, while machine-generated is not reliable due to the hallucination issue, we develop an automatic annotation tool that combines machine and human experts, under the active learning paradigm. Active learning is an interactive strategy between the model and human experts, in this way, the workload of human labeling can be reduced and the quality of the dataset can be guaranteed. With the help of the automatic annotation tool, we strive to contribute three datasets, namely VideoCoT, TopicQA, TopicCoT. Furthermore, we propose a simple but effective benchmark based on the collected datasets, which exploits CoT to maximize the complex reasoning capabilities of MLLMs. Extensive experiments demonstrate the effectiveness our solution.

cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers

An emerging area of research in situated and multimodal interactive conversations (SIMMC) includes interactions in scientific papers. Since scientific papers are primarily composed of text, equations, figures, and tables, SIMMC methods must be developed specifically for each component to support the depth of inquiry and interactions required by research scientists. This work introduces Conversational Papers (cPAPERS), a dataset of conversational question-answer pairs from reviews of academic papers grounded in these paper components and their associated references from scientific documents available on arXiv. We present a data collection strategy to collect these question-answer pairs from OpenReview and associate them with contextual information from LaTeX source files. Additionally, we present a series of baseline approaches utilizing Large Language Models (LLMs) in both zero-shot and fine-tuned configurations to address the cPAPERS dataset.

Secrecy Performance Analysis of Multi-Functional RIS-Assisted NOMA Networks

Although reconfigurable intelligent surface (RIS) can improve the secrecy communication performance of wireless users, it still faces challenges such as limited coverage and double-fading effect. To address these issues, in this paper, we utilize a novel multi-functional RIS (MF-RIS) to enhance the secrecy performance of wireless users, and investigate the physical layer secrecy problem in non-orthogonal multiple access (NOMA) networks. Specifically, we derive closed-form expressions for the secrecy outage probability (SOP) and secrecy throughput of users in the MF-RIS-assisted NOMA networks with external and internal eavesdroppers. The asymptotic expressions for SOP and secrecy diversity order are also analyzed under high signal-to-noise ratio (SNR) conditions. Additionally, we examine the impact of receiver hardware limitations and error transmission-induced imperfect successive interference cancellation (SIC) on the secrecy performance. Numerical results indicate that: i) under the same power budget, the secrecy performance achieved by MF-RIS significantly outperforms active RIS and simultaneously transmitting and reflecting RIS; ii) with increasing power budget, residual interference caused by imperfect SIC surpasses thermal noise as the primary factor affecting secrecy capacity; and iii) deploying additional elements at the MF-RIS brings significant secrecy enhancements for the external eavesdropping scenario, in contrast to the internal eavesdropping case.

Simple Multigraph Convolution Networks

Existing multigraph convolution methods either ignore the cross-view interaction among multiple graphs, or induce extremely high computational cost due to standard cross-view polynomial operators. To alleviate this problem, this paper proposes a Simple MultiGraph Convolution Networks (SMGCN) which first extracts consistent cross-view topology from multigraphs including edge-level and subgraph-level topology, then performs polynomial expansion based on raw multigraphs and consistent topologies. In theory, SMGCN utilizes the consistent topologies in polynomial expansion rather than standard cross-view polynomial expansion, which performs credible cross-view spatial message-passing, follows the spectral convolution paradigm, and effectively reduces the complexity of standard polynomial expansion. In the simulations, experimental results demonstrate that SMGCN achieves state-of-the-art performance on ACM and DBLP multigraph benchmark datasets. Our codes are available at https://github.com/frinkleko/SMGCN.

FinReport: Explainable Stock Earnings Forecasting via News Factor Analyzing Model

The task of stock earnings forecasting has received considerable attention due to the demand investors in real-world scenarios. However, compared with financial institutions, it is not easy for ordinary investors to mine factors and analyze news. On the other hand, although large language models in the financial field can serve users in the form of dialogue robots, it still requires users to have financial knowledge to ask reasonable questions. To serve the user experience, we aim to build an automatic system, FinReport, for ordinary investors to collect information, analyze it, and generate reports after summarizing. Specifically, our FinReport is based on financial news announcements and a multi-factor model to ensure the professionalism of the report. The FinReport consists of three modules: news factorization module, return forecasting module, risk assessment module. The news factorization module involves understanding news information and combining it with stock factors, the return forecasting module aim to analysis the impact of news on market sentiment, and the risk assessment module is adopted to control investment risk. Extensive experiments on real-world datasets have well verified the effectiveness and explainability of our proposed FinReport. Our codes and datasets are available at https://github.com/frinkleko/FinReport.

Identifying Factual Inconsistency in Summaries: Towards Effective Utilization of Large Language Model

Factual inconsistency poses a significant hurdle for the commercial deployment of abstractive summarizers. Under this Large Language Model (LLM) era, this work focuses around two important questions: what is the best way to leverage LLM for factual inconsistency detection, and how could we distill a smaller LLM with both high efficiency and efficacy? Three zero-shot paradigms are firstly proposed and evaluated across five diverse datasets: direct inference on the entire summary or each summary window; entity verification through question generation and answering. Experiments suggest that LLM itself is capable to resolve this task train-free under the proper paradigm design, surpassing strong trained baselines by 2.8% on average. To further promote practical utility, we then propose training strategies aimed at distilling smaller open-source LLM that learns to score the entire summary at once with high accuracy, which outperforms the zero-shot approaches by much larger LLM, serving as an effective and efficient ready-to-use scorer.

AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension

Recently, instruction-following audio-language models have received broad attention for human-audio interaction. However, the absence of benchmarks capable of evaluating audio-centric interaction capabilities has impeded advancements in this field. Previous models primarily focus on assessing different fundamental tasks, such as Automatic Speech Recognition (ASR), and lack an assessment of the open-ended generative capabilities centered around audio. Thus, it is challenging to track the progression in the Large Audio-Language Models (LALMs) domain and to provide guidance for future improvement. In this paper, we introduce AIR-Bench (\textbf{A}udio \textbf{I}nst\textbf{R}uction \textbf{Bench}mark), the first benchmark designed to evaluate the ability of LALMs to understand various types of audio signals (including human speech, natural sounds, and music), and furthermore, to interact with humans in the textual format. AIR-Bench encompasses two dimensions: \textit{foundation} and \textit{chat} benchmarks. The former consists of 19 tasks with approximately 19k single-choice questions, intending to inspect the basic single-task ability of LALMs. The latter one contains 2k instances of open-ended question-and-answer data, directly assessing the comprehension of the model on complex audio and its capacity to follow instructions. Both benchmarks require the model to generate hypotheses directly. We design a unified framework that leverages advanced language models, such as GPT-4, to evaluate the scores of generated hypotheses given the meta-information of the audio. Experimental results demonstrate a high level of consistency between GPT-4-based evaluation and human evaluation. By revealing the limitations of existing LALMs through evaluation results, AIR-Bench can provide insights into the direction of future research.

SIG: Speaker Identification in Literature via Prompt-Based Generation

Identifying speakers of quotations in narratives is an important task in literary analysis, with challenging scenarios including the out-of-domain inference for unseen speakers, and non-explicit cases where there are no speaker mentions in surrounding context. In this work, we propose a simple and effective approach SIG, a generation-based method that verbalizes the task and quotation input based on designed prompt templates, which also enables easy integration of other auxiliary tasks that further bolster the speaker identification performance. The prediction can either come from direct generation by the model, or be determined by the highest generation probability of each speaker candidate. Based on our approach design, SIG supports out-of-domain evaluation, and achieves open-world classification paradigm that is able to accept any forms of candidate input. We perform both cross-domain evaluation and in-domain evaluation on PDNC, the largest dataset of this task, where empirical results suggest that SIG outperforms previous baselines of complicated designs, as well as the zero-shot ChatGPT, especially excelling at those hard non-explicit scenarios by up to 17% improvement. Additional experiments on another dataset WP further corroborate the efficacy of SIG.