Recent large language models (LLMs) have shown remarkable performance in aligning generated text with user intentions across various tasks. When it comes to long-form text generation, there has been a growing interest in generation from a discourse coherence perspective. However, existing lexical or semantic metrics such as BLEU, ROUGE, BertScore cannot effectively capture the discourse coherence. The development of discourse-specific automatic evaluation methods for assessing the output of LLMs warrants greater focus and exploration. In this paper, we present a novel automatic metric designed to quantify the discourse divergence between two long-form articles. Extensive experiments on three datasets from representative domains demonstrate that our metric aligns more closely with human preferences and GPT-4 coherence evaluation, outperforming existing evaluation methods.
While large language models (LLMs) excel at understanding and generating plain text, they are not specifically tailored to handle hierarchical text structures. Extracting the task-desired property from their natural language responses typically necessitates additional processing steps. In fact, selectively comprehending the hierarchical structure of large-scale text is pivotal to understanding its substance. Aligning LLMs more closely with the classification or regression values of specific task through prompting also remains challenging. To this end, we propose a novel framework called Tree-Based Hard Attention with Self-Motivation for Large Language Models (TEAROOM). TEAROOM incorporates a tree-based hard attention mechanism for LLMs to process hierarchically structured text inputs. By leveraging prompting, it enables a frozen LLM to selectively focus on relevant leaves in relation to the root, generating a tailored symbolic representation of their relationship. Moreover, TEAROOM comprises a self-motivation strategy for another LLM equipped with a trainable adapter and a linear layer. The selected symbolic outcomes are integrated into another prompt, along with the predictive value of the task. We iteratively feed output values back into the prompt, enabling the trainable LLM to progressively approximate the golden truth. TEAROOM outperforms existing state-of-the-art methods in experimental evaluations across three benchmark datasets, showing its effectiveness in estimating task-specific properties. Through comprehensive experiments and analysis, we have validated the ability of TEAROOM to gradually approach the underlying golden truth through multiple inferences.
Numerous AI-assisted scholarly applications have been developed to aid different stages of the research process. We present an analysis of AI-assisted scholarly writing generated with ScholaCite, a tool we built that is designed for organizing literature and composing Related Work sections for academic papers. Our evaluation method focuses on the analysis of citation graphs to assess the structural complexity and inter-connectedness of citations in texts and involves a three-way comparison between (1) original human-written texts, (2) purely GPT-generated texts, and (3) human-AI collaborative texts. We find that GPT-4 can generate reasonable coarse-grained citation groupings to support human users in brainstorming, but fails to perform detailed synthesis of related works without human intervention. We suggest that future writing assistant tools should not be used to draft text independently of the human author.
We present MunTTS, an end-to-end text-to-speech (TTS) system specifically for Mundari, a low-resource Indian language of the Austo-Asiatic family. Our work addresses the gap in linguistic technology for underrepresented languages by collecting and processing data to build a speech synthesis system. We begin our study by gathering a substantial dataset of Mundari text and speech and train end-to-end speech models. We also delve into the methods used for training our models, ensuring they are efficient and effective despite the data constraints. We evaluate our system with native speakers and objective metrics, demonstrating its potential as a tool for preserving and promoting the Mundari language in the digital age.
Despite significant advancements in text-to-image models for generating high-quality images, these methods still struggle to ensure the controllability of text prompts over images in the context of complex text prompts, especially when it comes to retaining object attributes and relationships. In this paper, we propose CompAgent, a training-free approach for compositional text-to-image generation, with a large language model (LLM) agent as its core. The fundamental idea underlying CompAgent is premised on a divide-and-conquer methodology. Given a complex text prompt containing multiple concepts including objects, attributes, and relationships, the LLM agent initially decomposes it, which entails the extraction of individual objects, their associated attributes, and the prediction of a coherent scene layout. These individual objects can then be independently conquered. Subsequently, the agent performs reasoning by analyzing the text, plans and employs the tools to compose these isolated objects. The verification and human feedback mechanism is finally incorporated into our agent to further correct the potential attribute errors and refine the generated images. Guided by the LLM agent, we propose a tuning-free multi-concept customization model and a layout-to-image generation model as the tools for concept composition, and a local image editing method as the tool to interact with the agent for verification. The scene layout controls the image generation process among these tools to prevent confusion among multiple objects. Extensive experiments demonstrate the superiority of our approach for compositional text-to-image generation: CompAgent achieves more than 10\% improvement on T2I-CompBench, a comprehensive benchmark for open-world compositional T2I generation. The extension to various related tasks also illustrates the flexibility of our CompAgent for potential applications.
We present a Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards effective and efficient zero-shot video-text retrieval, dubbed M2-RAAP. Upon popular image-text models like CLIP, most current adaptation-based video-text pre-training methods are confronted by three major issues, i.e., noisy data corpus, time-consuming pre-training, and limited performance gain. Towards this end, we conduct a comprehensive study including four critical steps in video-text pre-training. Specifically, we investigate 1) data filtering and refinement, 2) video input type selection, 3) temporal modeling, and 4) video feature enhancement. We then summarize this empirical study into the M2-RAAP recipe, where our technical contributions lie in 1) the data filtering and text re-writing pipeline resulting in 1M high-quality bilingual video-text pairs, 2) the replacement of video inputs with key-frames to accelerate pre-training, and 3) the Auxiliary-Caption-Guided (ACG) strategy to enhance video features. We conduct extensive experiments by adapting three image-text foundation models on two refined video-text datasets from different languages, validating the robustness and reproducibility of M2-RAAP for adaptation-based pre-training. Results demonstrate that M2-RAAP yields superior performance with significantly reduced data (-90%) and time consumption (-95%), establishing a new SOTA on four English zero-shot retrieval datasets and two Chinese ones. We are preparing our refined bilingual data annotations and codebase, which will be available at https://github.com/alipay/Ant-Multi-Modal-Framework/tree/main/prj/M2_RAAP.
Foundation models like ChatGPT and GPT-4 have revolutionized artificial intelligence, exhibiting remarkable abilities to generalize across a wide array of tasks and applications beyond their initial training objectives. However, when this concept is applied to graph learning, a stark contrast emerges. Graph learning has predominantly focused on single-graph models, tailored to specific tasks or datasets, lacking the ability to transfer learned knowledge to different domains. This limitation stems from the inherent complexity and diversity of graph structures, along with the different feature and label spaces specific to graph data. In this paper, we present our UniGraph framework, designed to train a graph foundation model capable of generalizing to unseen graphs and tasks across diverse domains. Unlike single-graph models that use pre-computed node features of varying dimensions as input, our approach leverages Text-Attributed Graphs (TAGs) for unifying node representations. We propose a cascaded architecture of Language Models (LMs) and Graph Neural Networks (GNNs) as backbone networks with a self-supervised training objective based on Masked Graph Modeling (MGM). We introduce graph instruction tuning using Large Language Models (LLMs) to enable zero-shot prediction ability. Our comprehensive experiments across various graph learning tasks and domains demonstrate the model's effectiveness in self-supervised representation learning on unseen graphs, few-shot in-context transfer, and zero-shot transfer, even surpassing or matching the performance of GNNs that have undergone supervised training on target datasets.
Digital note-taking is gaining popularity, offering a durable, editable, and easily indexable way of storing notes in the vectorized form, known as digital ink. However, a substantial gap remains between this way of note-taking and traditional pen-and-paper note-taking, a practice still favored by a vast majority. Our work, InkSight, aims to bridge the gap by empowering physical note-takers to effortlessly convert their work (offline handwriting) to digital ink (online handwriting), a process we refer to as Derendering. Prior research on the topic has focused on the geometric properties of images, resulting in limited generalization beyond their training domains. Our approach combines reading and writing priors, allowing training a model in the absence of large amounts of paired samples, which are difficult to obtain. To our knowledge, this is the first work that effectively derenders handwritten text in arbitrary photos with diverse visual characteristics and backgrounds. Furthermore, it generalizes beyond its training domain into simple sketches. Our human evaluation reveals that 87% of the samples produced by our model on the challenging HierText dataset are considered as a valid tracing of the input image and 67% look like a pen trajectory traced by a human. Interactive visualizations of 100 word-level model outputs for each of the three public datasets are available in our Hugging Face space: https://huggingface.co/spaces/Derendering/Model-Output-Playground. Model release is in progress.
Surrogate modeling is of great practical significance for parametric differential equation systems. In contrast to classical numerical methods, using physics-informed deep learning methods to construct simulators for such systems is a promising direction due to its potential to handle high dimensionality, which requires minimizing a loss over a training set of random samples. However, the random samples introduce statistical errors, which may become the dominant errors for the approximation of low-regularity and high-dimensional problems. In this work, we present a deep adaptive sampling method for surrogate modeling ($\text{DAS}^2$), where we generalize the deep adaptive sampling (DAS) method [62] [Tang, Wan and Yang, 2023] to build surrogate models for low-regularity parametric differential equations. In the parametric setting, the residual loss function can be regarded as an unnormalized probability density function (PDF) of the spatial and parametric variables. This PDF is approximated by a deep generative model, from which new samples are generated and added to the training set. Since the new samples match the residual-induced distribution, the refined training set can further reduce the statistical error in the current approximate solution. We demonstrate the effectiveness of $\text{DAS}^2$ with a series of numerical experiments, including the parametric lid-driven 2D cavity flow problem with a continuous range of Reynolds numbers from 100 to 1000.
Touch is an important sensing modality for humans, but it has not yet been incorporated into a multimodal generative language model. This is partially due to the difficulty of obtaining natural language labels for tactile data and the complexity of aligning tactile readings with both visual observations and language descriptions. As a step towards bridging that gap, this work introduces a new dataset of 44K in-the-wild vision-touch pairs, with English language labels annotated by humans (10%) and textual pseudo-labels from GPT-4V (90%). We use this dataset to train a vision-language-aligned tactile encoder for open-vocabulary classification and a touch-vision-language (TVL) model for text generation using the trained encoder. Results suggest that by incorporating touch, the TVL model improves (+29% classification accuracy) touch-vision-language alignment over existing models trained on any pair of those modalities. Although only a small fraction of the dataset is human-labeled, the TVL model demonstrates improved visual-tactile understanding over GPT-4V (+12%) and open-source vision-language models (+32%) on a new touch-vision understanding benchmark. Code and data: https://tactile-vlm.github.io.