arXiv subjects

Nuo Chen

Publications and source records attributed to Nuo Chen.

At least 127 records · Page 7Linked to original sources

arXiv2024

Apollo: A Lightweight Multilingual Medical LLM towards Democratizing Medical AI to 6B People

Despite the vast repository of global medical knowledge predominantly being in English, local languages are crucial for delivering tailored healthcare services, particularly in areas with limited medical resources. To extend the reach of medical AI advancements to a broader population, we aim to develop medical LLMs across the six most widely spoken languages, encompassing a global population of 6.1 billion. This effort culminates in the creation of the ApolloCorpora multilingual medical dataset and the XMedBench benchmark. In the multilingual medical benchmark, the released Apollo models, at various relatively-small sizes (i.e., 0.5B, 1.8B, 2B, 6B, and 7B), achieve the best performance among models of equivalent size. Especially, Apollo-7B is the state-of-the-art multilingual medical LLMs up to 70B. Additionally, these lite models could be used to improve the multi-lingual medical capabilities of larger models without fine-tuning in a proxy-tuning fashion. We will open-source training corpora, code, model weights and evaluation benchmark.

cs.CL↗

arXiv2024

AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment

Cognitive biases are systematic deviations in thinking that lead to irrational judgments and problematic decision-making, extensively studied across various fields. Recently, large language models (LLMs) have shown advanced understanding capabilities but may inherit human biases from their training data. While social biases in LLMs have been well-studied, cognitive biases have received less attention, with existing research focusing on specific scenarios. The broader impact of cognitive biases on LLMs in various decision-making contexts remains underexplored. We investigated whether LLMs are influenced by the threshold priming effect in relevance judgments, a core task and widely-discussed research topic in the Information Retrieval (IR) coummunity. The priming effect occurs when exposure to certain stimuli unconsciously affects subsequent behavior and decisions. Our experiment employed 10 topics from the TREC 2019 Deep Learning passage track collection, and tested AI judgments under different document relevance scores, batch lengths, and LLM models, including GPT-3.5, GPT-4, LLaMa2-13B and LLaMa2-70B. Results showed that LLMs tend to give lower scores to later documents if earlier ones have high relevance, and vice versa, regardless of the combination and model used. Our finding demonstrates that LLM%u2019s judgments, similar to human judgments, are also influenced by threshold priming biases, and suggests that researchers and system engineers should take into account potential human-like cognitive biases in designing, evaluating, and auditing LLMs in IR tasks and beyond.

cs.CL↗

arXiv2024

Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation

Recent Retrieval Augmented Generation (RAG) aims to enhance Large Language Models (LLMs) by incorporating extensive knowledge retrieved from external sources. However, such approach encounters some challenges: Firstly, the original queries may not be suitable for precise retrieval, resulting in erroneous contextual knowledge; Secondly, the language model can easily generate inconsistent answer with external references due to their knowledge boundary limitation. To address these issues, we propose the chain-of-verification (CoV-RAG) to enhance the external retrieval correctness and internal generation consistency. Specifically, we integrate the verification module into the RAG, engaging in scoring, judgment, and rewriting. To correct external retrieval errors, CoV-RAG retrieves new knowledge using a revised query. To correct internal generation errors, we unify QA and verification tasks with a Chain-of-Thought (CoT) reasoning during training. Our comprehensive experiments across various LLMs demonstrate the effectiveness and adaptability compared with other strong baselines. Especially, our CoV-RAG can significantly surpass the state-of-the-art baselines using different LLM backbones.

cs.CL↗

arXiv2024

Decoy Effect In Search Interaction: Understanding User Behavior and Measuring System Vulnerability

This study examines the decoy effect's underexplored influence on user search interactions and methods for measuring information retrieval (IR) systems' vulnerability to this effect. It explores how decoy results alter users' interactions on search engine result pages, focusing on metrics like click-through likelihood, browsing time, and perceived document usefulness. By analyzing user interaction logs from multiple datasets, the study demonstrates that decoy results significantly affect users' behavior and perceptions. Furthermore, it investigates how different levels of task difficulty and user knowledge modify the decoy effect's impact, finding that easier tasks and lower knowledge levels lead to higher engagement with target documents. In terms of IR system evaluation, the study introduces the DEJA-VU metric to assess systems' susceptibility to the decoy effect, testing it on specific retrieval tasks. The results show differences in systems' effectiveness and vulnerability, contributing to our understanding of cognitive biases in search behavior and suggesting pathways for creating more balanced and bias-aware IR evaluations.

cs.IR↗

arXiv2024

Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision

Training a convolutional neural network (CNN) to detect infrared small targets in a fully supervised manner has gained remarkable research interests in recent years, but is highly labor expensive since a large number of per-pixel annotations are required. To handle this problem, in this paper, we make the first attempt to achieve infrared small target detection with point-level supervision. Interestingly, during the training phase supervised by point labels, we discover that CNNs first learn to segment a cluster of pixels near the targets, and then gradually converge to predict groundtruth point labels. Motivated by this "mapping degeneration" phenomenon, we propose a label evolution framework named label evolution with single point supervision (LESPS) to progressively expand the point label by leveraging the intermediate predictions of CNNs. In this way, the network predictions can finally approximate the updated pseudo labels, and a pixel-level target mask can be obtained to train CNNs in an end-to-end manner. We conduct extensive experiments with insightful visualizations to validate the effectiveness of our method. Experimental results show that CNNs equipped with LESPS can well recover the target masks from corresponding point labels, {and can achieve over 70% and 95% of their fully supervised performance in terms of pixel-level intersection over union (IoU) and object-level probability of detection (Pd), respectively. Code is available at https://github.com/XinyiYing/LESPS.

cs.CV↗

arXiv2024

SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving

Monocular scene understanding is a foundational component of autonomous systems. Within the spectrum of monocular perception topics, one crucial and useful task for holistic 3D scene understanding is semantic scene completion (SSC), which jointly completes semantic information and geometric details from RGB input. However, progress in SSC, particularly in large-scale street views, is hindered by the scarcity of high-quality datasets. To address this issue, we introduce SSCBench, a comprehensive benchmark that integrates scenes from widely used automotive datasets (e.g., KITTI-360, nuScenes, and Waymo). SSCBench follows an established setup and format in the community, facilitating the easy exploration of SSC methods in various street views. We benchmark models using monocular, trinocular, and point cloud input to assess the performance gap resulting from sensor coverage and modality. Moreover, we have unified semantic labels across diverse datasets to simplify cross-domain generalization testing. We commit to including more datasets and SSC models to drive further advancements in this field.

cs.CV↗

arXiv2024

ControlMath: Controllable Data Generation Promotes Math Generalist Models

Utilizing large language models (LLMs) for data augmentation has yielded encouraging results in mathematical reasoning. However, these approaches face constraints in problem diversity, potentially restricting them to in-domain/distribution data generation. To this end, we propose ControlMath, an iterative method involving an equation-generator module and two LLM-based agents. The module creates diverse equations, which the Problem-Crafter agent then transforms into math word problems. The Reverse-Agent filters and selects high-quality data, adhering to the "less is more" principle, achieving better results with fewer data points. This approach enables the generation of diverse math problems, not limited to specific domains or distributions. As a result, we collect ControlMathQA, which involves 190k math word problems. Extensive results prove that combining our dataset with in-domain datasets like GSM8K can help improve the model's mathematical ability to generalize, leading to improved performances both within and beyond specific domains.

cs.LG↗

arXiv2024

MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria

Multimodal large language models (MLLMs) have broadened the scope of AI applications. Existing automatic evaluation methodologies for MLLMs are mainly limited in evaluating queries without considering user experiences, inadequately addressing the nuances of creative and associative multimodal tasks. However, the open-ended and subjective nature of such tasks poses a significant challenge to the evaluation methodology, where it is difficult to define the ground-truth answers for them. To this end, in our paper, we propose a new evaluation paradigm for MLLMs, which is evaluating MLLMs with per-sample criteria using potent MLLM as the judge. To validate the feasibility and effectiveness of this paradigm, we design a benchmark, dubbed MLLM-Bench, by curating the evaluation samples across six comprehensive cognitive levels. We benchmark 21 popular MLLMs in a pairwise-comparison fashion, showing diverse performance across models. Moreover, the validity of our benchmark manifests itself in reaching 88.02% agreement with human evaluation. We contend that the proposed paradigm explores the potential of MLLMs as effective evaluation tools with the help of per-sample criteria. See online leaderboard at \url{https://mllm-bench.llmzoo.com}.

cs.CL↗

arXiv2024

Cross-Domain Foundation Model Adaptation: Pioneering Computer Vision Models for Geophysical Data Analysis

We explore adapting foundation models (FMs) from the computer vision domain to geoscience. FMs, large neural networks trained on massive datasets, excel in diverse tasks with remarkable adaptability and generality. However, geoscience faces challenges like lacking curated training datasets and high computational costs for developing specialized FMs. This study considers adapting FMs from computer vision to geoscience, analyzing their scale, adaptability, and generality for geoscientific data analysis. We introduce a workflow that leverages existing computer vision FMs, fine-tuning them for geoscientific tasks, reducing development costs while enhancing accuracy. Through experiments, we demonstrate this workflow's effectiveness in broad applications to process and interpret geoscientific data of lunar images, seismic data, DAS arrays and so on. Our findings introduce advanced ML techniques to geoscience, proving the feasibility and advantages of cross-domain FMs adaptation, driving further advancements in geoscientific data analysis and offering valuable insights for FMs applications in other scientific domains.

cs.CV↗

arXiv2024

Room-Temperature Multiferroic Skyrmions in LiNbO3 with enhancement in electric-optical property

LiNbO3 (LN) is renowned for its exceptional ferroelectric properties, particularly its notable linear electro-optical (EO) effect, which is highly advantageous for various applications such as high-speed communication, optical computation, and quantum information processing. Compared to its ferroelectric properties, the magnetism of LN is not attractive enough due to its weak ferromagnetic nature. Theoretical studies suggest that LN may exhibit a novel magnetoelectric coupling via ferroelectrically-induced ferromagnetism. However, this mechanism has not yet been experimentally validated in any materials, presenting significant challenges for research. In this study, we provide the first experimental evidence supporting the mechanism of ferroelectrically-induced ferromagnetism in LN, including observations of the Dzyaloshinskii-Moriya interaction (DMI) and magnetoelectric coupling. Additionally, we have identified various multiferroic skyrmions, within which ferroelectric polarization signals are detectable. These signals can be influenced by the magnetic vortex structures, indicating a magnetoelectric coupling nature. Currently, they are the only multiferroic skyrmions that can keep stable at room temperature. Moreover, these magnetic textures significantly affect the ferroelectric properties, as demonstrated by an enhancement of the linear electro-optic effect of LN by over 200%. Given the novel magnetoelectric coupling mechanism, the potential of multiferroic skyrmions in spintronics and advanced data storage, and the extensive use of LN EO modulators, our research has significant implications for condensed matter physics, multiferroic materials, and optoelectronics.

cond-mat.mtrl-sci↗

arXiv2024

Vision-Based Dexterous Motion Planning by Dynamic Movement Primitives with Human Hand Demonstration

This paper proposes a vision-based framework for a 7-degree-of-freedom robotic manipulator, with the primary objective of facilitating its capacity to acquire information from human hand demonstrations for the execution of dexterous pick-and-place tasks. Most existing works only focus on the position demonstration without considering the orientations. In this paper, by employing a single depth camera, MediaPipe is applied to generate the three-dimensional coordinates of a human hand, thereby comprehensively recording the hand's motion, encompassing the trajectory of the wrist, orientation of the hand, and the grasp motion. A mean filter is applied during data pre-processing to smooth the raw data. The demonstration is designed to pick up an object at a specific angle, navigate around obstacles in its path and subsequently, deposit it within a sloped container. The robotic system demonstrates its learning capabilities, facilitated by the implementation of Dynamic Movement Primitives, enabling the assimilation of user actions into its trajectories with different start and end poi

cs.RO↗

arXiv2024

Stable room-temperature multiferroic skyrmions in lithium niobate with enhanced Pockels effect

Lithium Niobate (LN) is a ferroelectric material with exceptional electrical characteristics, including high piezoelectricity, high Pockels effect, etc. These properties make it a promising platform for numerous fields such as high-speed communication, optical computation, and quantum information processing. Besides these, the introduction of magnetic structures to LN holds significant potential to achieve magnetoelectric coupling, which can be applied in magnetic memory and data-processing devices with high efficiency. Here, for the first time, we observe a special topological magnetic structure called magnetic skyrmion in LN (SK-LN) by the combination of magnetic field annealing and rapid annealing processes . Compared to the magnetic skyrmions reported in magnetic systems, SK-LN exhibit exceptionally high stability. Additionally, the center of the magnetic vortex exhibits spontaneous ferroelectric polarization, indicating its multiferroic characteristic. With the excitation of these multiferroic skyrmions, the modulation efficiency of the electro-optical (EO) modulator fabricated on thin film lithium niobate on insulator (LNOI) wafer was found to be enhanced from 1.98 V*cm to 0.63 V*cm. It is considered that the multiferroic skyrmions significantly enhance the Pockels coefficient of LN to 101 pm/V, nearly three times the result (32pm/V) reported previously.

cond-mat.mtrl-sci↗

arXiv2024

GraphWiz: An Instruction-Following Language Model for Graph Problems

Large language models (LLMs) have achieved impressive success across several fields, but their proficiency in understanding and resolving complex graph problems is less explored. To bridge this gap, we introduce GraphInstruct, a novel and comprehensive instruction-tuning dataset designed to equip language models with the ability to tackle a broad spectrum of graph problems using explicit reasoning paths. Utilizing GraphInstruct, we build GraphWiz, an open-source language model capable of resolving various graph problem types while generating clear reasoning processes. To enhance the model's capability and reliability, we incorporate the Direct Preference Optimization (DPO) framework into the graph problem-solving context. The enhanced model, GraphWiz-DPO, achieves an average accuracy of 65% across nine tasks with different complexity levels, surpassing GPT-4 which has an average accuracy of 43.8%. Moreover, our research delves into the delicate balance between training data volume and model performance, highlighting the potential for overfitting with increased data. We also explore the transferability of the model's reasoning ability across different graph tasks, indicating the model's adaptability and practical application potential. Our investigation offers a new blueprint and valuable insights for developing LLMs specialized in graph reasoning and problem-solving.

cs.CL↗

arXiv2024

Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations

Existing retrieval-based methods have made significant strides in maintaining long-term conversations. However, these approaches face challenges in memory database management and accurate memory retrieval, hindering their efficacy in dynamic, real-world interactions. This study introduces a novel framework, COmpressive Memory-Enhanced Dialogue sYstems (COMEDY), which eschews traditional retrieval modules and memory databases. Instead, COMEDY adopts a "One-for-All" approach, utilizing a single language model to manage memory generation, compression, and response generation. Central to this framework is the concept of compressive memory, which intergrates session-specific summaries, user-bot dynamics, and past events into a concise memory format. To support COMEDY, we curated a large-scale Chinese instruction-tuning dataset, Dolphin, derived from real user-chatbot interactions. Comparative evaluations demonstrate COMEDY's superiority over traditional retrieval-based methods in producing more nuanced and human-like conversational experiences. Our codes are available at https://github.com/nuochenpku/COMEDY.

cs.CL↗

arXiv2024

Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset

Large-scale datasets have fueled recent advancements in AI-based autonomous vehicle research. However, these datasets are usually collected from a single vehicle's one-time pass of a certain location, lacking multiagent interactions or repeated traversals of the same place. Such information could lead to transformative enhancements in autonomous vehicles' perception, prediction, and planning capabilities. To bridge this gap, in collaboration with the self-driving company May Mobility, we present the MARS dataset which unifies scenarios that enable MultiAgent, multitraveRSal, and multimodal autonomous vehicle research. More specifically, MARS is collected with a fleet of autonomous vehicles driving within a certain geographical area. Each vehicle has its own route and different vehicles may appear at nearby locations. Each vehicle is equipped with a LiDAR and surround-view RGB cameras. We curate two subsets in MARS: one facilitates collaborative driving with multiple vehicles simultaneously present at the same location, and the other enables memory retrospection through asynchronous traversals of the same location by multiple vehicles. We conduct experiments in place recognition and neural reconstruction. More importantly, MARS introduces new research opportunities and challenges such as multitraversal 3D reconstruction, multiagent perception, and unsupervised object discovery. Our data and codes can be found at https://ai4ce.github.io/MARS/.

cs.CV↗

arXiv2024

Towards unveiling the Cosmic Reionization: the ionizing photon production efficiency ($ξ_{ion}$) of Low-mass H$α$ emitters at $z \sim 2.3$

We investigate the galaxy properties of $\sim$400 low-mass ($<10^9\,M_{\odot}$) H$α$ emitters (HAEs) at z $\sim$ 2.3 in the ZFOURGE survey. The selection of these HAEs is based on the excess in the observed $K_s$ broad-band flux compared to the stellar continuum estimated from the best-fit SED. These low-mass HAEs have elevated SFR(H$α$) above the star formation main sequence (SFMS), making them potential analogs of the galaxies that reionized the universe during the epoch of reionization. The ionizing photon production efficiencies ($ξ_{ion}$) of the low-mass HAEs have a median value of $\mathrm{log}(ξ_{ion}/erg^{-1} Hz)=25.24^{+0.10}_{-0.13}\ (25.35^{+0.12}_{-0.15})$, assuming the Calzetti (SMC) curve for the stellar continuum dust correction. This value is higher than that of main sequence galaxies by $\sim$0.2 dex at similar redshift, indicating that the low-mass HAEs are more efficient in producing ionizing photons. Our results also consolidate the trend of increasing $ξ_{ion}$ with redshift, but reveal a "downsizing" relationship between $ξ_{ion}$ and stellar mass ($M_{\odot}$) with increasing redshift. We further explore the dependence of $ξ_{ion}$ on other galaxy properties, such as the UV spectral slope ($β_{\mathrm{UV}}$), the UV magnitude ($M_{\mathrm{UV}}$), the equivalent widths ($EWs$) of H$α$ and [O{\sc iii}] emission lines. Galaxies with the bluer UV slopes, fainter UV luminosities and higher equivalent widths exhibit elevated $ξ_{ion}$ by a factor of $\sim$2 compared to the median $ξ_{ion}$ of our sample. JWST data will provide an opportunity to extend our method and further investigate the properties of low-mass galaxies at high redshifts.

astro-ph.GA↗

arXiv2024

ChatDev: Communicative Agents for Software Development

Software development is a complex task that necessitates cooperation among multiple members with diverse skills. Numerous studies used deep learning to improve specific phases in a waterfall model, such as design, coding, and testing. However, the deep learning model in each phase requires unique designs, leading to technical inconsistencies across various phases, which results in a fragmented and ineffective development process. In this paper, we introduce ChatDev, a chat-powered software development framework in which specialized agents driven by large language models (LLMs) are guided in what to communicate (via chat chain) and how to communicate (via communicative dehallucination). These agents actively contribute to the design, coding, and testing phases through unified language-based communication, with solutions derived from their multi-turn dialogues. We found their utilization of natural language is advantageous for system design, and communicating in programming language proves helpful in debugging. This paradigm demonstrates how linguistic communication facilitates multi-agent collaboration, establishing language as a unifying bridge for autonomous task-solving among LLM agents. The code and data are available at https://github.com/OpenBMB/ChatDev.

cs.SE↗

arXiv2024

TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills

Code pre-trained models (CodePTMs) have recently demonstrated a solid capacity to process various software intelligence tasks, e.g., code clone detection, code translation, and code summarization. The current mainstream method that deploys these models to downstream tasks is to fine-tune them on individual tasks, which is generally costly and needs sufficient data for large models. To tackle the issue, in this paper, we present TransCoder, a unified Transferable fine-tuning strategy for Code representation learning. Inspired by human inherent skills of knowledge generalization, TransCoder drives the model to learn better code-related meta-knowledge like human programmers. Specifically, we employ a tunable prefix encoder as the meta-learner to capture cross-task and cross-language transferable knowledge, respectively. Besides, tasks with minor training sample sizes and languages with small corpus can be remarkably benefited from our approach. Extensive experiments conducted on benchmark datasets clearly demonstrate that our method can lead to superior performance on various code-related tasks and encourage mutual reinforcement. We also show that TransCoder is applicable in low-resource scenarios. Our codes are available at https://github.com/QiushiSun/TransCoder.

cs.SE↗