Zhejiang University
Abstract:The task of issue resolving is to modify a codebase to generate a patch that addresses a given issue. However, existing benchmarks, such as SWE-bench, focus almost exclusively on Python, making them insufficient for evaluating Large Language Models (LLMs) across diverse software ecosystems. To address this, we introduce a multilingual issue-resolving benchmark, called Multi-SWE-bench, covering Java, TypeScript, JavaScript, Go, Rust, C, and C++. It includes a total of 1,632 high-quality instances, which were carefully annotated from 2,456 candidates by 68 expert annotators, ensuring that the benchmark can provide an accurate and reliable evaluation. Based on Multi-SWE-bench, we evaluate a series of state-of-the-art models using three representative methods (Agentless, SWE-agent, and OpenHands) and present a comprehensive analysis with key empirical insights. In addition, we launch a Multi-SWE-RL open-source community, aimed at building large-scale reinforcement learning (RL) training datasets for issue-resolving tasks. As an initial contribution, we release a set of 4,723 well-structured instances spanning seven programming languages, laying a solid foundation for RL research in this domain. More importantly, we open-source our entire data production pipeline, along with detailed tutorials, encouraging the open-source community to continuously contribute and expand the dataset. We envision our Multi-SWE-bench and the ever-growing Multi-SWE-RL community as catalysts for advancing RL toward its full potential, bringing us one step closer to the dawn of AGI.
Abstract:Grasp-based manipulation tasks are fundamental to robots interacting with their environments, yet gripper state ambiguity significantly reduces the robustness of imitation learning policies for these tasks. Data-driven solutions face the challenge of high real-world data costs, while simulation data, despite its low costs, is limited by the sim-to-real gap. We identify the root cause of gripper state ambiguity as the lack of tactile feedback. To address this, we propose a novel approach employing pseudo-tactile as feedback, inspired by the idea of using a force-controlled gripper as a tactile sensor. This method enhances policy robustness without additional data collection and hardware involvement, while providing a noise-free binary gripper state observation for the policy and thus facilitating pure simulation learning to unleash the power of simulation. Experimental results across three real-world grasp-based tasks demonstrate the necessity, effectiveness, and efficiency of our approach.
Abstract:Task-specific instruction tuning enhances the performance of large language models (LLMs) on specialized tasks, yet efficiently selecting relevant data for this purpose remains a challenge. Inspired by neural coactivation in the human brain, we propose a novel data selection method called NAS, which leverages neuronal activation states as embeddings for samples in the feature space. Extensive experiments show that NAS outperforms classical data selection methods in terms of both effectiveness and robustness across different models, datasets, and selection ratios.
Abstract:Traffic prediction targets forecasting future traffic conditions using historical traffic data, serving a critical role in urban computing and transportation management. To mitigate the scarcity of traffic data while maintaining data privacy, numerous Federated Traffic Knowledge Transfer (FTT) approaches have been developed, which use transfer learning and federated learning to transfer traffic knowledge from data-rich cities to data-scarce cities, enhancing traffic prediction capabilities for the latter. However, current FTT approaches face challenges such as privacy leakage, cross-city data distribution discrepancies, low data quality, and inefficient knowledge transfer, limiting their privacy protection, effectiveness, robustness, and efficiency in real-world applications. To this end, we propose FedTT, an effective, efficient, and privacy-aware cross-city traffic knowledge transfer framework that transforms the traffic data domain from the data-rich cities and trains traffic models using the transformed data for the data-scarce cities. First, to safeguard data privacy, we propose a traffic secret transmission method that securely transmits and aggregates traffic domain-transformed data from source cities using a lightweight secret aggregation approach. Second, to mitigate the impact of traffic data distribution discrepancies on model performance, we introduce a traffic domain adapter to uniformly transform traffic data from the source cities' domains to that of the target city. Third, to improve traffic data quality, we design a traffic view imputation method to fill in and predict missing traffic data. Finally, to enhance transfer efficiency, FedTT is equipped with a federated parallel training method that enables the simultaneous training of multiple modules. Extensive experiments using 4 real-life datasets demonstrate that FedTT outperforms the 14 state-of-the-art baselines.
Abstract:Huawei has always been committed to exploring the AI application in historical research. Biography generation, as a specialized form of abstractive summarization, plays a crucial role in historical research but faces unique challenges that existing large language models (LLMs) struggle to address. These challenges include maintaining stylistic adherence to historical writing conventions, ensuring factual fidelity, and handling fragmented information across multiple documents. We present AIstorian, a novel end-to-end agentic system featured with a knowledge graph (KG)-powered retrieval-augmented generation (RAG) and anti-hallucination multi-agents. Specifically, AIstorian introduces an in-context learning based chunking strategy and a KG-based index for accurate and efficient reference retrieval. Meanwhile, AIstorian orchestrates multi-agents to conduct on-the-fly hallucination detection and error-type-aware correction. Additionally, to teach LLMs a certain language style, we finetune LLMs based on a two-step training approach combining data augmentation-enhanced supervised fine-tuning with stylistic preference optimization. Extensive experiments on a real-life historical Jinshi dataset demonstrate that AIstorian achieves a 3.8x improvement in factual accuracy and a 47.6% reduction in hallucination rate compared to existing baselines. The data and code are available at: https://github.com/ZJU-DAILY/AIstorian.
Abstract:Natural and lifelike locomotion remains a fundamental challenge for humanoid robots to interact with human society. However, previous methods either neglect motion naturalness or rely on unstable and ambiguous style rewards. In this paper, we propose a novel Generative Motion Prior (GMP) that provides fine-grained motion-level supervision for the task of natural humanoid robot locomotion. To leverage natural human motions, we first employ whole-body motion retargeting to effectively transfer them to the robot. Subsequently, we train a generative model offline to predict future natural reference motions for the robot based on a conditional variational auto-encoder. During policy training, the generative motion prior serves as a frozen online motion generator, delivering precise and comprehensive supervision at the trajectory level, including joint angles and keypoint positions. The generative motion prior significantly enhances training stability and improves interpretability by offering detailed and dense guidance throughout the learning process. Experimental results in both simulation and real-world environments demonstrate that our method achieves superior motion naturalness compared to existing approaches. Project page can be found at https://sites.google.com/view/humanoid-gmp
Abstract:Recent advancements in tool learning have enabled large language models (LLMs) to integrate external tools, enhancing their task performance by expanding their knowledge boundaries. However, relying on tools often introduces tradeoffs between performance, speed, and cost, with LLMs sometimes exhibiting overreliance and overconfidence in tool usage. This paper addresses the challenge of aligning LLMs with their knowledge boundaries to make more intelligent decisions about tool invocation. We propose a multi objective alignment framework that combines probabilistic knowledge boundary estimation with dynamic decision making, allowing LLMs to better assess when to invoke tools based on their confidence. Our framework includes two methods for knowledge boundary estimation, consistency based and absolute estimation, and two training strategies for integrating these estimates into the model decision making process. Experimental results on various tool invocation scenarios demonstrate the effectiveness of our framework, showing significant improvements in tool efficiency by reducing unnecessary tool usage.
Abstract:Large Language Models often generate factually incorrect but plausible outputs, known as hallucinations. We identify a more insidious phenomenon, LLM delusion, defined as high belief hallucinations, incorrect outputs with abnormally high confidence, making them harder to detect and mitigate. Unlike ordinary hallucinations, delusions persist with low uncertainty, posing significant challenges to model reliability. Through empirical analysis across different model families and sizes on several Question Answering tasks, we show that delusions are prevalent and distinct from hallucinations. LLMs exhibit lower honesty with delusions, which are harder to override via finetuning or self reflection. We link delusion formation with training dynamics and dataset noise and explore mitigation strategies such as retrieval augmented generation and multi agent debating to mitigate delusions. By systematically investigating the nature, prevalence, and mitigation of LLM delusions, our study provides insights into the underlying causes of this phenomenon and outlines future directions for improving model reliability.
Abstract:Large language models (LLMs) frequently hallucinate due to misaligned self-awareness, generating erroneous outputs when addressing queries beyond their knowledge boundaries. While existing approaches mitigate hallucinations via uncertainty estimation or query rejection, they suffer from computational inefficiency or sacrificed helpfulness. To address these issues, we propose the Explicit Knowledge Boundary Modeling (EKBM) framework, integrating fast and slow reasoning systems to harmonize reliability and usability. The framework first employs a fast-thinking model to generate confidence-labeled responses, enabling immediate use of high-confidence outputs. For uncertain predictions, a slow refinement model conducts targeted reasoning to improve accuracy. To align model behavior with our proposed object, we propose a hybrid training pipeline, enhancing self-awareness without degrading task performance. Evaluations on dialogue state tracking tasks demonstrate that EKBM achieves superior model reliability over uncertainty-based baselines. Further analysis reveals that refinement substantially boosts accuracy while maintaining low computational overhead. Our work establishes a scalable paradigm for advancing LLM reliability and balancing accuracy and practical utility in error-sensitive applications.
Abstract:Large language models (LLMs), particularly those with reasoning capabilities, have rapidly advanced in recent years, demonstrating significant potential across a wide range of applications. However, their deployment in healthcare, especially in disease reasoning tasks, is hindered by the challenge of acquiring expert-level cognitive data. In this paper, we introduce Citrus, a medical language model that bridges the gap between clinical expertise and AI reasoning by emulating the cognitive processes of medical experts. The model is trained on a large corpus of simulated expert disease reasoning data, synthesized using a novel approach that accurately captures the decision-making pathways of clinicians. This approach enables Citrus to better simulate the complex reasoning processes involved in diagnosing and treating medical conditions. To further address the lack of publicly available datasets for medical reasoning tasks, we release the last-stage training data, including a custom-built medical diagnostic dialogue dataset. This open-source contribution aims to support further research and development in the field. Evaluations using authoritative benchmarks such as MedQA, covering tasks in medical reasoning and language understanding, show that Citrus achieves superior performance compared to other models of similar size. These results highlight Citrus potential to significantly enhance medical decision support systems, providing a more accurate and efficient tool for clinical decision-making.