arXiv subjects

Minghao Liu

Publications and source records attributed to Minghao Liu.

At least 91 records · Page 5Linked to original sources

arXiv2025

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values

Aligning large language models (LLMs) with human preferences has achieved remarkable success. However, existing Chinese preference datasets are limited by small scale, narrow domain coverage, and lack of rigorous data validation. Additionally, the reliance on human annotators for instruction and response labeling significantly constrains the scalability of human preference datasets. To address these challenges, we design an LLM-based Chinese preference dataset annotation pipeline with no human intervention. Specifically, we crawled and carefully filtered 92k high-quality Chinese queries and employed 15 mainstream LLMs to generate and score chosen-rejected response pairs. Based on it, we introduce COIG-P (Chinese Open Instruction Generalist - Preference), a high-quality, large-scale Chinese preference dataset, comprises 1,009k Chinese preference pairs spanning 6 diverse domains: Chat, Code, Math, Logic, Novel, and Role. Building upon COIG-P, to reduce the overhead of using LLMs for scoring, we trained a 8B-sized Chinese Reward Model (CRM) and meticulously constructed a Chinese Reward Benchmark (CRBench). Evaluation results based on AlignBench \citep{liu2024alignbenchbenchmarkingchinesealignment} show that that COIG-P significantly outperforms other Chinese preference datasets, and it brings significant performance improvements ranging from 2% to 12% for the Qwen2/2.5 and Infinity-Instruct-3M-0625 model series, respectively. The results on CRBench demonstrate that our CRM has a strong and robust scoring ability. We apply it to filter chosen-rejected response pairs in a test split of COIG-P, and our experiments show that it is comparable to GPT-4o in identifying low-quality samples while maintaining efficiency and cost-effectiveness. Our codes and data are released in https://github.com/multimodal-art-projection/COIG-P.

cs.CL↗

arXiv2025

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e.g., the reasoning-focused model DeepSeek-R1 achieved the highest accuracy of 61.82% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.

cs.CL↗

arXiv2025

OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations

Document content extraction is a critical task in computer vision, underpinning the data needs of large language models (LLMs) and retrieval-augmented generation (RAG) systems. Despite recent progress, current document parsing methods have not been fairly and comprehensively evaluated due to the narrow coverage of document types and the simplified, unrealistic evaluation procedures in existing benchmarks. To address these gaps, we introduce OmniDocBench, a novel benchmark featuring high-quality annotations across nine document sources, including academic papers, textbooks, and more challenging cases such as handwritten notes and densely typeset newspapers. OmniDocBench supports flexible, multi-level evaluations--ranging from an end-to-end assessment to the task-specific and attribute--based analysis using 19 layout categories and 15 attribute labels. We conduct a thorough evaluation of both pipeline-based methods and end-to-end vision-language models, revealing their strengths and weaknesses across different document types. OmniDocBench sets a new standard for the fair, diverse, and fine-grained evaluation in document parsing. Dataset and code are available at https://github.com/opendatalab/OmniDocBench.

cs.CV↗

arXiv2025

Kalib: Easy Hand-Eye Calibration with Reference Point Tracking

Hand-eye calibration aims to estimate the transformation between a camera and a robot. Traditional methods rely on fiducial markers, which require considerable manual effort and precise setup. Recent advances in deep learning have introduced markerless techniques but come with more prerequisites, such as retraining networks for each robot, and accessing accurate mesh models for data generation. In this paper, we propose Kalib, an automatic and easy-to-setup hand-eye calibration method that leverages the generalizability of visual foundation models to overcome these challenges. It features only two basic prerequisites, the robot's kinematic chain and a predefined reference point on the robot. During calibration, the reference point is tracked in the camera space. Its corresponding 3D coordinates in the robot coordinate can be inferred by forward kinematics. Then, a PnP solver directly estimates the transformation between the camera and the robot without training new networks or accessing mesh models. Evaluations in simulated and real-world benchmarks show that Kalib achieves good accuracy with a lower manual workload compared with recent baseline methods. We also demonstrate its application in multiple real-world settings with various robot arms and grippers. Kalib's user-friendly design and minimal setup requirements make it a possible solution for continuous operation in unstructured environments.

cs.RO↗

arXiv2025

KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks

In this paper, we introduce Knowledge-Orthogonal Reasoning (KOR), a concept aimed at minimizing reliance on domain-specific knowledge, enabling more accurate evaluation of models' reasoning abilities in out-of-distribution settings. Based on this concept, we propose the Knowledge-Orthogonal Reasoning Benchmark (KOR-Bench), encompassing five task categories: Operation, Logic, Cipher, Puzzle, and Counterfactual. KOR-Bench emphasizes models' effectiveness in applying new rule descriptions to solve novel rule-driven questions. O1-Preview and O1-Mini achieve accuracies of 72.88% and 70.16%, surpassing Claude-3.5-Sonnet and GPT-4o (58.96% and 58.00%), highlighting the effectiveness of KOR-Bench. We perform detailed analyses, identifying bottlenecks in the Cipher task with Stepwise Prompting, where two rounds of Self-Correction yield optimal results. We evaluate performance across three integrated tasks, explore the impact of Tricks on the Puzzle task, and visualize rule-focused attention. Additionally, we conduct an ablation study on dataset size, benchmark correlations, and zero-shot and three-shot "only questions" experiments. KOR-Bench aims to enhance reasoning evaluation and support further research in this area.

cs.DB↗

arXiv2025

Human and AI Perceptual Differences in Image Classification Errors

Artificial intelligence (AI) models for computer vision trained with supervised machine learning are assumed to solve classification tasks by imitating human behavior learned from training labels. Most efforts in recent vision research focus on measuring the model task performance using standardized benchmarks such as accuracy. However, limited work has sought to understand the perceptual difference between humans and machines. To fill this gap, this study first analyzes the statistical distributions of mistakes from the two sources and then explores how task difficulty level affects these distributions. We find that even when AI learns an excellent model from the training data, one that outperforms humans in overall accuracy, these AI models have significant and consistent differences from human perception. We demonstrate the importance of studying these differences with a simple human-AI teaming algorithm that outperforms humans alone, AI alone, or AI-AI teaming.

cs.CV↗

arXiv2024

AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions

Data science tasks involving tabular data present complex challenges that require sophisticated problem-solving approaches. We propose AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data pipelines through a collaborative multi-agent system. AutoKaggle implements an iterative development process that combines code execution, debugging, and comprehensive unit testing to ensure code correctness and logic consistency. The framework offers highly customizable workflows, allowing users to intervene at each phase, thus integrating automated intelligence with human expertise. Our universal data science toolkit, comprising validated functions for data cleaning, feature engineering, and modeling, forms the foundation of this solution, enhancing productivity by streamlining common tasks. We selected 8 Kaggle competitions to simulate data processing workflows in real-world application scenarios. Evaluation results demonstrate that AutoKaggle achieves a validation submission rate of 0.85 and a comprehensive score of 0.82 in typical data science pipelines, fully proving its effectiveness and practicality in handling complex data science tasks.

cs.AI↗

arXiv2024

A Comparative Study on Reasoning Patterns of OpenAI's o1 Model

Enabling Large Language Models (LLMs) to handle a wider range of complex tasks (e.g., coding, math) has drawn great attention from many researchers. As LLMs continue to evolve, merely increasing the number of model parameters yields diminishing performance improvements and heavy computational costs. Recently, OpenAI's o1 model has shown that inference strategies (i.e., Test-time Compute methods) can also significantly enhance the reasoning capabilities of LLMs. However, the mechanisms behind these methods are still unexplored. In our work, to investigate the reasoning patterns of o1, we compare o1 with existing Test-time Compute methods (BoN, Step-wise BoN, Agent Workflow, and Self-Refine) by using OpenAI's GPT-4o as a backbone on general reasoning benchmarks in three domains (i.e., math, coding, commonsense reasoning). Specifically, first, our experiments show that the o1 model has achieved the best performance on most datasets. Second, as for the methods of searching diverse responses (e.g., BoN), we find the reward models' capability and the search space both limit the upper boundary of these methods. Third, as for the methods that break the problem into many sub-problems, the Agent Workflow has achieved better performance than Step-wise BoN due to the domain-specific system prompt for planning better reasoning processes. Fourth, it is worth mentioning that we have summarized six reasoning patterns of o1, and provided a detailed analysis on several reasoning benchmarks.

cs.CL↗

arXiv2024

Reactor neutrino liquid xenon coherent elastic scattering experiment

Coherent elastic neutrino-nucleus scattering (CEvNS) provides a unique probe for neutrino properties Beyond the Standard Model (BSM) physics. REactor neutrino LIquid xenon Coherent Scattering experiment (RELICS), a proposed reactor neutrino program using liquid xenon time projection chamber (LXeTPC) technology, aims to investigate the CEvNS process of antineutrinos off xenon atomic nuclei. In this work, the design of the experiment is studied and optimized based on Monte Carlo (MC) simulations. To achieve a sufficiently low energy threshold for CEvNS detection, an ionization-only analysis channel is adopted for RELICS. A high emission rate of delayed electrons after a big ionization signal is the major background, leading to an analysis threshold of 120 photo-electrons in the CEvNS search. The second largest background, nuclear recoils induced by cosmic-ray neutrons, is suppressed via a passive water shield. The physics potential of RELICS is explored with a 32 kg*yr exposure at a baseline of 25 m from a reactor core with a 3 GW thermal power. In an energy range of 120 to 300 PE, corresponding to an average nuclear recoil from 0.63 to 1.36 keV considering the liquid xenon response and detector-related effect, we expect 4639.7 CEvNS and 1687.8 background events. The sensitivity of RELICS to the weak mixing angle is investigated at a low momentum transfer. Our study shows that RELICS can further improve the constraints on the non-standard neutrino interaction (NSI) compared to the current best results.

hep-ex↗

arXiv2024

CA-BERT: Leveraging Context Awareness for Enhanced Multi-Turn Chat Interaction

Effective communication in automated chat systems hinges on the ability to understand and respond to context. Traditional models often struggle with determining when additional context is necessary for generating appropriate responses. This paper introduces Context-Aware BERT (CA-BERT), a transformer-based model specifically fine-tuned to address this challenge. CA-BERT innovatively applies deep learning techniques to discern context necessity in multi-turn chat interactions, enhancing both the relevance and accuracy of responses. We describe the development of CA-BERT, which adapts the robust architecture of BERT with a novel training regimen focused on a specialized dataset of chat dialogues. The model is evaluated on its ability to classify context necessity, demonstrating superior performance over baseline BERT models in terms of accuracy and efficiency. Furthermore, CA-BERT's implementation showcases significant reductions in training time and resource usage, making it feasible for real-time applications. The results indicate that CA-BERT can effectively enhance the functionality of chatbots by providing a nuanced understanding of context, thereby improving user experience and interaction quality in automated systems. This study not only advances the field of NLP in chat applications but also provides a framework for future research into context-sensitive AI developments.

cs.CL↗

arXiv2024

IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce

Enhancing Language Models' (LMs) ability to understand purchase intentions in E-commerce scenarios is crucial for their effective assistance in various downstream tasks. However, previous approaches that distill intentions from LMs often fail to generate meaningful and human-centric intentions applicable in real-world E-commerce contexts. This raises concerns about the true comprehension and utilization of purchase intentions by LMs. In this paper, we present IntentionQA, a double-task multiple-choice question answering benchmark to evaluate LMs' comprehension of purchase intentions in E-commerce. Specifically, LMs are tasked to infer intentions based on purchased products and utilize them to predict additional purchases. IntentionQA consists of 4,360 carefully curated problems across three difficulty levels, constructed using an automated pipeline to ensure scalability on large E-commerce platforms. Human evaluations demonstrate the high quality and low false-negative rate of our benchmark. Extensive experiments across 19 language models show that they still struggle with certain scenarios, such as understanding products and intentions accurately, jointly reasoning with products and intentions, and more, in which they fall far behind human performances. Our code and data are publicly available at https://github.com/HKUST-KnowComp/IntentionQA.

cs.CL↗

arXiv2024

Draw Like an Artist: Complex Scene Generation with Diffusion Model via Composition, Painting, and Retouching

Recent advances in text-to-image diffusion models have demonstrated impressive capabilities in image quality. However, complex scene generation remains relatively unexplored, and even the definition of `complex scene' itself remains unclear. In this paper, we address this gap by providing a precise definition of complex scenes and introducing a set of Complex Decomposition Criteria (CDC) based on this definition. Inspired by the artists painting process, we propose a training-free diffusion framework called Complex Diffusion (CxD), which divides the process into three stages: composition, painting, and retouching. Our method leverages the powerful chain-of-thought capabilities of large language models (LLMs) to decompose complex prompts based on CDC and to manage composition and layout. We then develop an attention modulation method that guides simple prompts to specific regions to complete the complex scene painting. Finally, we inject the detailed output of the LLM into a retouching model to enhance the image details, thus implementing the retouching stage. Extensive experiments demonstrate that our method outperforms previous SOTA approaches, significantly improving the generation of high-quality, semantically consistent, and visually diverse images for complex scenes, even with intricate prompts.

cs.CV↗

arXiv2024

Scalable Knowledge Refactoring using Constrained Optimisation

Knowledge refactoring compresses a logic program by introducing new rules. Current approaches struggle to scale to large programs. To overcome this limitation, we introduce a constrained optimisation refactoring approach. Our first key idea is to encode the problem with decision variables based on literals rather than rules. Our second key idea is to focus on linear invented rules. Our empirical results on multiple domains show that our approach can refactor programs quicker and with more compression than the previous state-of-the-art approach, sometimes by 60%.

cs.LO↗

arXiv2024

MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series

Large Language Models (LLMs) have made great strides in recent years to achieve unprecedented performance across different tasks. However, due to commercial interest, the most competitive models like GPT, Gemini, and Claude have been gated behind proprietary interfaces without disclosing the training details. Recently, many institutions have open-sourced several strong LLMs like LLaMA-3, comparable to existing closed-source LLMs. However, only the model's weights are provided with most details (e.g., intermediate checkpoints, pre-training corpus, and training code, etc.) being undisclosed. To improve the transparency of LLMs, the research community has formed to open-source truly open LLMs (e.g., Pythia, Amber, OLMo), where more details (e.g., pre-training corpus and training code) are being provided. These models have greatly advanced the scientific study of these large models including their strengths, weaknesses, biases and risks. However, we observe that the existing truly open LLMs on reasoning, knowledge, and coding tasks are still inferior to existing state-of-the-art LLMs with similar model sizes. To this end, we open-source MAP-Neo, a highly capable and transparent bilingual language model with 7B parameters trained from scratch on 4.5T high-quality tokens. Our MAP-Neo is the first fully open-sourced bilingual LLM with comparable performance compared to existing state-of-the-art LLMs. Moreover, we open-source all details to reproduce our MAP-Neo, where the cleaned pre-training corpus, data cleaning pipeline, checkpoints, and well-optimized training/evaluation framework are provided. Finally, we hope our MAP-Neo will enhance and strengthen the open research community and inspire more innovations and creativities to facilitate the further improvements of LLMs.

cs.CL↗

arXiv2024

Assessing the Impact of Prompting Methods on ChatGPT's Mathematical Capabilities

This study critically evaluates the efficacy of prompting methods in enhancing the mathematical reasoning capability of large language models (LLMs). The investigation uses three prescriptive prompting methods - simple, persona, and conversational prompting - known for their effectiveness in enhancing the linguistic tasks of LLMs. We conduct this analysis on OpenAI's LLM chatbot, ChatGPT-3.5, on extensive problem sets from the MATH, GSM8K, and MMLU datasets, encompassing a broad spectrum of mathematical challenges. A grading script adapted to each dataset is used to determine the effectiveness of these prompting interventions in enhancing the model's mathematical analysis power. Contrary to expectations, our empirical analysis reveals that none of the investigated methods consistently improves over ChatGPT-3.5's baseline performance, with some causing significant degradation. Our findings suggest that prompting strategies do not necessarily generalize to new domains, in this study failing to enhance mathematical performance.

cs.AI↗

arXiv2023

KDE-Based Coarse-graining of Semicrystalline Systems with Correlated Three-body Intramolecular Interaction

We present an extension to the iterative Boltzmann inversion method to generate coarse-grained models with three-body intramolecular potentials that can reproduce correlations in structural distribution functions. The coarse-grained structural distribution functions are computed using kernel density estimates to produce analytically differentiable distribution functions with controllable smoothening via the kernel bandwidth parameters. Bicubic interpolation is used to accurately interpolate the three-body potentials trained by the method. To demonstrate this new approach, a coarse-grained model of polyethylene is constructed in which each bead represents an ethylene monomer. The resulting model reproduces the radial density function as well as the joint probability distribution of bond-length and bond-angles sampled from target atomistic simulations with only a 10% increase in the computational cost compared to models with independent bond-length and bond-angle potentials. Analysis of the predicted crystallization kinetics of the model developed by the new approach reveals that the bandwidth parameters can be tuned to accelerate the modeling of polymer crystallization. Specifically, computing target RDF with larger bandwidth slows down the secondary crystallization, and increasing the bandwidth in $θ$-direction of bond-length and bond-angle distribution reduces the primary crystallization rate.

physics.comp-ph↗

arXiv2023

Tag-Based Annotation for Avatar Face Creation

Currently, digital avatars can be created manually using human images as reference. Systems such as Bitmoji are excellent producers of detailed avatar designs, with hundreds of choices for customization. A supervised learning model could be trained to generate avatars automatically, but the hundreds of possible options create difficulty in securing non-noisy data to train a model. As a solution, we train a model to produce avatars from human images using tag-based annotations. This method provides better annotator agreement, leading to less noisy data and higher quality model predictions. Our contribution is an application of tag-based annotation to train a model for avatar face creation. We design tags for 3 different facial facial features offered by Bitmoji, and train a model using tag-based annotation to predict the nose.

cs.CV↗

arXiv2023

Ferroelectric Domain and Switching Dynamics in Curved In2Se3: First Principle and Deep Learning Molecular Dynamics Simulations

Complex strain status can exist in 2D materials during their synthesis process, resulting in significant impacts on the physical and chemical properties. Despite their prevalence in experiments, their influence on the material properties and the corresponding mechanism are often understudied due to the lack of effective simulation methods. In this work, we investigated the effects of bending, rippling, and bubbling on the ferroelectric domains in In2Se3 monolayer by density functional theory (DFT) and deep learning molecular dynamics (DLMD) simulations. The analysis of the tube model shows that bending deformation imparts asymmetry into the system, and the polarization direction tends to orient towards the tensile side, which has a lower energy state than the opposite polarization direction. The energy barrier for polarization switching can be reduced by compressive strain according DFT results. The dynamics of the polarization switching is investigated by the DLMD simulations. The influence of curvature and temperature on the switching time follows the Arrhenius-style function. For the complex strain status in the rippling and bubbling model, the lifetime of the local transient polarization is analyzed by the autocorrelation function, and the size of the stable polarization domain is identified. Local curvature and temperature can influence the local polarization dynamics following the proposed Arrhenius-style equation. Through cross-scale simulations, this study demonstrates the capability of deep-learning potentials in simulating polarization for ferroelectric materials. It further reveals the potential to manipulate local polarization in ferroelectric materials through strain engineering.

cond-mat.mtrl-sci↗