We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL introduces the Naive Dynamic Resolution mechanism, which enables the model to dynamically process images of varying resolutions into different numbers of visual tokens. This approach allows the model to generate more efficient and accurate visual representations, closely aligning with human perceptual processes. The model also integrates Multimodal Rotary Position Embedding (M-RoPE), facilitating the effective fusion of positional information across text, images, and videos. We employ a unified paradigm for processing both images and videos, enhancing the model's visual perception capabilities. To explore the potential of large multimodal models, Qwen2-VL investigates the scaling laws for large vision-language models (LVLMs). By scaling both the model size-with versions at 2B, 8B, and 72B parameters-and the amount of training data, the Qwen2-VL Series achieves highly competitive performance. Notably, the Qwen2-VL-72B model achieves results comparable to leading models such as GPT-4o and Claude3.5-Sonnet across various multimodal benchmarks, outperforming other generalist models. Code is available at \url{https://github.com/QwenLM/Qwen2-VL}.

Mixture-of-Experts (MoE) models scale more effectively than dense models due to sparse computation through expert routing, selectively activating only a small subset of expert modules. However, sparse computation challenges traditional training practices, as discrete expert routing hinders standard backpropagation and thus gradient-based optimization, which are the cornerstone of deep learning. To better pursue the scaling power of MoE, we introduce GRIN (GRadient-INformed MoE training), which incorporates sparse gradient estimation for expert routing and configures model parallelism to avoid token dropping. Applying GRIN to autoregressive language modeling, we develop a top-2 16$\times$3.8B MoE model. Our model, with only 6.6B activated parameters, outperforms a 7B dense model and matches the performance of a 14B dense model trained on the same data. Extensive evaluations across diverse tasks demonstrate the potential of GRIN to significantly enhance MoE efficacy, achieving 79.4 on MMLU, 83.7 on HellaSwag, 74.4 on HumanEval, and 58.9 on MATH.

The rapid advancements in Large Language Models (LLMs) have revolutionized natural language processing (NLP) and related fields. However, fine-tuning these models for specific tasks remains computationally expensive and risks degrading pre-learned features. To address these challenges, we propose Propulsion, a novel parameter efficient fine-tuning (PEFT) method designed to optimize task-specific performance while drastically reducing computational overhead. Inspired by the concept of controlled adjustments in physical motion, Propulsion selectively re-scales specific dimensions of a pre-trained model, guiding output predictions toward task objectives without modifying the model's parameters. By introducing lightweight, trainable Propulsion parameters at the pre-trained layer, we minimize the number of parameters updated during fine-tuning, preventing overfitting or overwriting of existing knowledge. Our theoretical analysis, supported by Neural Tangent Kernel (NTK) theory, shows that Propulsion approximates the performance of full fine-tuning with far fewer trainable parameters. Empirically, Propulsion reduces the parameter count from 355.3 million to just 0.086 million, achieving over a 10x reduction compared to standard approaches like LoRA while maintaining competitive performance across benchmarks.

The rapid expansion of online content has intensified the issue of information redundancy, underscoring the need for solutions that can identify genuinely new information. Despite this challenge, the research community has seen a decline in focus on novelty detection, particularly with the rise of large language models (LLMs). Additionally, previous approaches have relied heavily on human annotation, which is time-consuming, costly, and particularly challenging when annotators must compare a target document against a vast number of historical documents. In this work, we introduce NovAScore (Novelty Evaluation in Atomicity Score), an automated metric for evaluating document-level novelty. NovAScore aggregates the novelty and salience scores of atomic information, providing high interpretability and a detailed analysis of a document's novelty. With its dynamic weight adjustment scheme, NovAScore offers enhanced flexibility and an additional dimension to assess both the novelty level and the importance of information within a document. Our experiments show that NovAScore strongly correlates with human judgments of novelty, achieving a 0.626 Point-Biserial correlation on the TAP-DLND 1.0 dataset and a 0.920 Pearson correlation on an internal human-annotated dataset.

Large language models (LLMs) have enabled a range of applications in zero-shot and few-shot learning settings, including the generation of synthetic datasets for training and testing. However, to reliably use these synthetic datasets, it is essential to understand how representative they are of real-world data. We investigate this by assessing the effectiveness of generating synthetic data through LLM and using it as a benchmark for various NLP tasks. Our experiments across six datasets, and three different tasks, show that while synthetic data can effectively capture performance of various methods for simpler tasks, such as intent classification, it falls short for more complex tasks like named entity recognition. Additionally, we propose a new metric called the bias factor, which evaluates the biases introduced when the same LLM is used to both generate benchmarking data and to perform the tasks. We find that smaller LLMs exhibit biases towards their own generated data, whereas larger models do not. Overall, our findings suggest that the effectiveness of synthetic data as a benchmark varies depending on the task, and that practitioners should rely on data generated from multiple larger models whenever possible.

Large language models (LLMs) are increasingly employed in information-seeking and decision-making tasks. Despite their broad utility, LLMs tend to generate information that conflicts with real-world facts, and their persuasive style can make these inaccuracies appear confident and convincing. As a result, end-users struggle to consistently align the confidence expressed by LLMs with the accuracy of their predictions, often leading to either blind trust in all outputs or a complete disregard for their reliability. In this work, we explore supervised finetuning on uncertainty-augmented predictions as a method to develop models that produce linguistic expressions of uncertainty. Specifically, we measure the calibration of pre-trained models and then fine-tune language models to generate calibrated linguistic expressions of uncertainty. Through experiments on various question-answering datasets, we demonstrate that LLMs are well-calibrated in assessing their predictions, and supervised finetuning based on the model's own confidence leads to well-calibrated expressions of uncertainty, particularly for single-claim answers.

As Large Language Models (LLMs) advance in natural language processing, there is growing interest in leveraging their capabilities to simplify software interactions. In this paper, we propose a novel system that integrates LLMs for both classifying natural language inputs into corresponding API calls and automating the creation of sample datasets tailored to specific API functions. By classifying natural language commands, our system allows users to invoke complex software functionalities through simple inputs, improving interaction efficiency and lowering the barrier to software utilization. Our dataset generation approach also enables the efficient and systematic evaluation of different LLMs in classifying API calls, offering a practical tool for developers or business owners to assess the suitability of LLMs for customized API management. We conduct experiments on several prominent LLMs using generated sample datasets for various API functions. The results show that GPT-4 achieves a high classification accuracy of 0.996, while LLaMA-3-8B performs much worse at 0.759. These findings highlight the potential of LLMs to transform API management and validate the effectiveness of our system in guiding model testing and selection across diverse applications.

Mixed Integer Programming (MIP) has been extensively applied in areas requiring mathematical solvers to address complex instances within tight time constraints. However, as the problem scale increases, the complexity of model formulation and finding feasible solutions escalates significantly. In contrast, the model-building cost for end-to-end models, such as large language models (LLMs), remains largely unaffected by problem scale due to their pattern recognition capabilities. While LLMs, like GPT-4, without fine-tuning, can handle some traditional medium-scale MIP problems, they struggle with uncommon or highly specialized MIP scenarios. Fine-tuning LLMs can yield some feasible solutions for medium-scale MIP instances, but these models typically fail to explore diverse solutions when constrained by a low and constant temperature, limiting their performance. In this paper, we propose and evaluate a recursively dynamic temperature method integrated with a chain-of-thought approach. Our findings show that starting with a high temperature and gradually lowering it leads to better feasible solutions compared to other dynamic temperature strategies. Additionally, by comparing results generated by the LLM with those from Gurobi, we demonstrate that the LLM can produce solutions that complement traditional solvers by accelerating the pruning process and improving overall efficiency.

Personalization plays a critical role in numerous language tasks and applications, since users with the same requirements may prefer diverse outputs based on their individual interests. This has led to the development of various personalized approaches aimed at adapting large language models (LLMs) to generate customized outputs aligned with user preferences. Some of them involve fine-tuning a unique personalized LLM for each user, which is too expensive for widespread application. Alternative approaches introduce personalization information in a plug-and-play manner by retrieving the user's relevant historical texts as demonstrations. However, this retrieval-based strategy may break the continuity of the user history and fail to capture the user's overall styles and patterns, hence leading to sub-optimal performance. To address these challenges, we propose a novel personalized LLM model, \ours{}. It constructs a user-specific embedding for each individual by modeling all her historical contexts through a lightweight plug-in user embedder module. By attaching this embedding to the task input, LLMs can better understand and capture user habits and preferences, thereby producing more personalized outputs without tuning their own parameters. Extensive experiments on various tasks in the language model personalization (LaMP) benchmark demonstrate that the proposed model significantly outperforms existing personalized LLM approaches.

Large language model (LLM) role-playing has gained widespread attention, where the authentic character knowledge is crucial for constructing realistic LLM role-playing agents. However, existing works usually overlook the exploration of LLMs' ability to detect characters' known knowledge errors (KKE) and unknown knowledge errors (UKE) while playing roles, which would lead to low-quality automatic construction of character trainable corpus. In this paper, we propose a probing dataset to evaluate LLMs' ability to detect errors in KKE and UKE. The results indicate that even the latest LLMs struggle to effectively detect these two types of errors, especially when it comes to familiar knowledge. We experimented with various reasoning strategies and propose an agent-based reasoning method, Self-Recollection and Self-Doubt (S2RD), to further explore the potential for improving error detection capabilities. Experiments show that our method effectively improves the LLMs' ability to detect error character knowledge, but it remains an issue that requires ongoing attention.