Shaohua Zhang

Ziyun Dai, Xiaoqiang Li, Shaohua Zhang et al.

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in visual understanding and multimodal reasoning. However, LVLMs frequently exhibit hallucination phenomena, manifesting as the generated textual responses that demonstrate inconsistencies with the provided visual content. Existing hallucination mitigation methods are predominantly text-centric, the challenges of visual-semantic alignment significantly limit their effectiveness, especially when confronted with fine-grained visual understanding scenarios. To this end, this paper presents ViHallu, a Vision-Centric Hallucination mitigation framework that enhances visual-semantic alignment through Visual Variation Image Generation and Visual Instruction Construction. ViHallu introduces visual variation images with controllable visual alterations while maintaining the overall image structure. These images, combined with carefully constructed visual instructions, enable LVLMs to better understand fine-grained visual content through fine-tuning, allowing models to more precisely capture the correspondence between visual content and text, thereby enhancing visual-semantic alignment. Extensive experiments on multiple benchmarks show that ViHallu effectively enhances models' fine-grained visual understanding while significantly reducing hallucination tendencies. Furthermore, we release ViHallu-Instruction, a visual instruction dataset specifically designed for hallucination mitigation and visual-semantic alignment. Code is available at https://github.com/oliviadzy/ViHallu.

Yong Lee, Shaohua Zhang, Miao Li et al.

Unwanted nonlinear gamma distortion frequently occurs in a great diversity of images during the procedures of image acquisition, processing, and/or display. And the gamma distortion often varies with capture setup change and luminance variation. Blind inverse gamma correction, which automatically determines a proper restoration gamma value from a given image, is of paramount importance to attenuate the distortion. For blind inverse gamma correction, an adaptive gamma transformation method (AGT-ME) is proposed directly from a maximized differential entropy model. And the corresponding optimization has a mathematical concise closed-form solution, resulting in efficient implementation and accurate gamma restoration of AGT-ME. Considering the human eye has a non-linear perception sensitivity, a modified version AGT-ME-VISUAL is also proposed to achieve better visual performance. Tested on variable datasets, AGT-ME could obtain an accurate estimation of a large range of gamma distortion (0.1 to 3.0), outperforming the state-of-the-art methods. Besides, the proposed AGT-ME and AGT-ME-VISUAL were applied to three typical applications, including automatic gamma adjustment, natural/medical image contrast enhancement, and fringe projection profilometry image restoration. Furthermore, the AGT-ME/ AGT-ME-VISUAL is general and can be seamlessly extended to the masked image, multi-channel (color or spectrum) image, or multi-frame video, and free of the arbitrary tuning parameter. Besides, the corresponding Python code (https://github.com/yongleex/AGT-ME) is also provided for interested users.

Tianyang Zhang, Zhuoxuan Jiang, Haotian Zhang et al.

We propose a novel system, MathMistake Checker, designed to automate step-by-step mistake finding in mathematical problems with lengthy answers through a two-stage process. The system aims to simplify grading, increase efficiency, and enhance learning experiences from a pedagogical perspective. It integrates advanced technologies, including computer vision and the chain-of-thought capabilities of the latest large language models (LLMs). Our system supports open-ended grading without reference answers and promotes personalized learning by providing targeted feedback. We demonstrate its effectiveness across various types of math problems, such as calculation and word problems.

Shaohua Zhang, Yuan Lin, Hang Li

The remarkable success of large language models (LLMs) stems from their ability to consolidate vast amounts of knowledge into the memory during pre-training and to retrieve it from the memory during inference, enabling advanced capabilities such as knowledge memorization, instruction-following and reasoning. However, the mechanisms of memory retrieval and consolidation in LLMs remain poorly understood. In this paper, we propose the function token hypothesis to explain the workings of LLMs: During inference, function tokens activate the most predictive features from context and govern next token prediction (memory retrieval). During pre-training, predicting the next tokens (usually content tokens) that follow function tokens increases the number of learned features of LLMs and updates the model parameters (memory consolidation). Function tokens here roughly correspond to function words in linguistics, including punctuation marks, articles, prepositions, and conjunctions, in contrast to content tokens. We provide extensive experimental evidence supporting this hypothesis. Using bipartite graph analysis, we show that a small number of function tokens activate the majority of features. Case studies further reveal how function tokens activate the most predictive features from context to direct next token prediction. We also find that during pre-training, the training loss is dominated by predicting the next content tokens following function tokens, which forces the function tokens to select the most predictive features from context.

Zhuoxuan Jiang, Tianyang Zhang, Peiyan Peng et al.

Generating high-quality geometry problems is both an important and challenging task in education. Compared to math word problems, geometry problems further emphasize multi-modal formats and the translation between informal and formal languages. In this paper, we introduce a novel task for geometry problem generation and propose a new pipeline method: the Symbolic Deduction Engine-based Geometry Problem Generation framework (SDE-GPG). The framework leverages a symbolic deduction engine and contains four main steps: (1) searching a predefined mapping table from knowledge points to extended definitions, (2) sampling extended definitions and performing symbolic deduction, (3) filtering out unqualified problems, and (4) generating textual problems and diagrams. Specifically, our method supports to avoid inherent biases in translating natural language into formal language by designing the mapping table, and guarantees to control the generated problems in terms of knowledge points and difficulties by an elaborate checking function. With obtained formal problems, they are translated to natural language and the accompanying diagrams are automatically drew by rule-based methods. We conduct experiments using real-world combinations of knowledge points from two public datasets. The results demonstrate that the SDE-GPG can effectively generate readable, solvable and controllable geometry problems.

Hongqiu Wu, Shaohua Zhang, Yuchen Zhang et al.

In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model. Through empirical analysis, we find that fine-tuning BERT tends to over-fit the error model while under-fit the language model, resulting in poor generalization to out-of-distribution error patterns. Given that BERT is the backbone of most CSC models, this phenomenon has a significant negative impact. To address this issue, we are releasing a multi-domain benchmark LEMON, with higher quality and diversity than existing benchmarks, to allow a comprehensive assessment of the open domain generalization of CSC models. Then, we demonstrate that a very simple strategy, randomly masking 20\% non-error tokens from the input sequence during fine-tuning is sufficient for learning a much better language model without sacrificing the error model. This technique can be applied to any model architecture and achieves new state-of-the-art results on SIGHAN, ECSpell, and LEMON.

Shaohua Zhang, Haoran Huang, Jicong Liu et al.

Spelling error correction is an important yet challenging task because a satisfactory solution of it essentially needs human-level language understanding ability. Without loss of generality we consider Chinese spelling error correction (CSC) in this paper. A state-of-the-art method for the task selects a character from a list of candidates for correction (including non-correction) at each position of the sentence on the basis of BERT, the language representation model. The accuracy of the method can be sub-optimal, however, because BERT does not have sufficient capability to detect whether there is an error at each position, apparently due to the way of pre-training it using mask language modeling. In this work, we propose a novel neural architecture to address the aforementioned issue, which consists of a network for error detection and a network for error correction based on BERT, with the former being connected to the latter with what we call soft-masking technique. Our method of using `Soft-Masked BERT' is general, and it may be employed in other language detection-correction problems. Experimental results on two datasets demonstrate that the performance of our proposed method is significantly better than the baselines including the one solely based on BERT.

Wenmian Yang, Wenyuan Gao, Xiaojie Zhou et al.

Time-sync comment (TSC) is a new form of user-interaction review associated with real-time video contents, which contains a user's preferences for videos and therefore well suited as the data source for video recommendations. However, existing review-based recommendation methods ignore the context-dependent (generated by user-interaction), real-time, and time-sensitive properties of TSC data. To bridge the above gaps, in this paper, we use video images and users' TSCs to design an Image-Text Fusion model with a novel Herding Effect Attention mechanism (called ITF-HEA), which can predict users' favorite videos with model-based collaborative filtering. Specifically, in the HEA mechanism, we weight the context information based on the semantic similarities and time intervals between each TSC and its context, thereby considering influences of the herding effect in the model. Experiments show that ITF-HEA is on average 3.78\% higher than the state-of-the-art method upon F1-score in baselines.