arXiv subjects

Lijie Hu

Publications and source records attributed to Lijie Hu.

At least 73 records · Page 4Linked to original sources

arXiv2025

Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons

Large Language Models (LLMs) trained on massive data capture rich information embedded in the training data. However, this also introduces the risk of privacy leakage, particularly involving personally identifiable information (PII). Although previous studies have shown that this risk can be mitigated through methods such as privacy neurons, they all assume that both the (sensitive) training data and user queries are in English. We show that they cannot defend against the privacy leakage in cross-lingual contexts: even if the training data is exclusively in one language, these (private) models may still reveal private information when queried in another language. In this work, we first investigate the information flow of cross-lingual privacy leakage to give a better understanding. We find that LLMs process private information in the middle layers, where representations are largely shared across languages. The risk of leakage peaks when converted to a language-specific space in later layers. Based on this, we identify privacy-universal neurons and language-specific privacy neurons. Privacy-universal neurons influence privacy leakage across all languages, while language-specific privacy neurons are only related to specific languages. By deactivating these neurons, the cross-lingual privacy leakage risk is reduced by 23.3%-31.6%.

cs.CL↗

arXiv2025

Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment

In the realm of Text-attributed Graphs (TAGs), traditional graph neural networks (GNNs) often fall short due to the complex textual information associated with each node. Recent methods have improved node representations by leveraging large language models (LLMs) to enhance node text features, but these approaches typically require extensive annotations or fine-tuning across all nodes, which is both time-consuming and costly. To overcome these challenges, we introduce GAGA, an efficient framework for TAG representation learning. GAGA reduces annotation time and cost by focusing on annotating only representative nodes and edges. It constructs an annotation graph that captures the topological relationships among these annotations. Furthermore, GAGA employs a two-level alignment module to effectively integrate the annotation graph with the TAG, aligning their underlying structures. Experiments show that GAGA achieves classification accuracies on par with or surpassing state-of-the-art methods while requiring only 1% of the data to be annotated, demonstrating its high efficiency.

cs.LG↗

arXiv2025

Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images

While multimodal large language models excel at various tasks, they still suffer from hallucinations, which limit their reliability and scalability for broader domain applications. To address this issue, recent research mainly focuses on objective hallucination. However, for sequential images, besides objective hallucination, there is also behavioral hallucination, which is less studied. This work aims to fill in the gap. We first reveal that behavioral hallucinations mainly arise from two key factors: prior-driven bias and the snowball effect. Based on these observations, we introduce SHE (Sequence Hallucination Eradication), a lightweight, two-stage framework that (1) detects hallucinations via visual-textual alignment check using our proposed adaptive temporal window and (2) mitigates them via orthogonal projection onto the joint embedding space. We also propose a new metric (BEACH) to quantify behavioral hallucination severity. Empirical results on standard benchmarks demonstrate that SHE reduces behavioral hallucination by over 10% on BEACH while maintaining descriptive accuracy.

cs.AI↗

arXiv2025

Stable Vision Concept Transformers for Medical Diagnosis

Transparency is a paramount concern in the medical field, prompting researchers to delve into the realm of explainable AI (XAI). Among these XAI methods, Concept Bottleneck Models (CBMs) aim to restrict the model's latent space to human-understandable high-level concepts by generating a conceptual layer for extracting conceptual features, which has drawn much attention recently. However, existing methods rely solely on concept features to determine the model's predictions, which overlook the intrinsic feature embeddings within medical images. To address this utility gap between the original models and concept-based models, we propose Vision Concept Transformer (VCT). Furthermore, despite their benefits, CBMs have been found to negatively impact model performance and fail to provide stable explanations when faced with input perturbations, which limits their application in the medical field. To address this faithfulness issue, this paper further proposes the Stable Vision Concept Transformer (SVCT) based on VCT, which leverages the vision transformer (ViT) as its backbone and incorporates a conceptual layer. SVCT employs conceptual features to enhance decision-making capabilities by fusing them with image features and ensures model faithfulness through the integration of Denoised Diffusion Smoothing. Comprehensive experiments on four medical datasets demonstrate that our VCT and SVCT maintain accuracy while remaining interpretable compared to baselines. Furthermore, even when subjected to perturbations, our SVCT model consistently provides faithful explanations, thus meeting the needs of the medical field.

cs.CV↗

arXiv2025

COMPKE: Complex Question Answering under Knowledge Editing

Knowledge Editing, which efficiently modifies the knowledge in large language models, has gathered great attention. Current benchmarks primarily use multi-hop question answering to assess and analyze newly injected or updated knowledge. However, we argue that these benchmarks fail to effectively evaluate how well the updated models apply this knowledge in real-life scenarios, particularly when questions require complex reasoning, involving one-to-many relationships or multi-step logical intersections. To fill in this gap, we introduce a new benchmark, COMPKE: Complex Question Answering under Knowledge Editing, which includes 11,924 complex questions that reflect real-life situations. We conduct an extensive evaluation of four knowledge editing methods on COMPKE, revealing that their effectiveness varies notably across different models. For instance, MeLLo attains an accuracy of 39.47 on GPT-4O-MINI, but this drops sharply to 3.83 on QWEN2.5-3B. We further investigate the underlying causes of these disparities from both methodological and model-specific perspectives. The datasets are available at https://github.com/kzjkzj666/CompKE.

cs.CL↗

arXiv2025

CODEMENV: Benchmarking Large Language Models on Code Migration

Large language models (LLMs) have shown remarkable capabilities across various software engineering tasks; however, their effectiveness in code migration, adapting code to run in different environments, remains insufficiently studied. In this work, we introduce CODEMENV: Code Migration Across Environment, a new benchmark specifically designed to assess LLMs' abilities in code migration scenarios. CODEMENV consists of 922 examples spanning 19 Python and Java packages, and covers three core tasks: (1) identifying functions incompatible with specific versions, (2) detecting changes in function definitions, and (3) adapting code to target environments. Experimental evaluation with seven LLMs on CODEMENV yields an average pass@1 rate of 26.50%, with GPT-4O achieving the highest score at 43.84%. Key findings include: (i) LLMs tend to be more proficient with newer function versions, which aids in migrating legacy code, and (ii) LLMs sometimes exhibit logical inconsistencies by identifying function changes irrelevant to the intended migration environment. The datasets are available at https://github.com/xdshen-ai/Benchmark-of-Code-Migration.

cs.SE↗

arXiv2025

Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements

We introduce Fraud-R1, a benchmark designed to evaluate LLMs' ability to defend against internet fraud and phishing in dynamic, real-world scenarios. Fraud-R1 comprises 8,564 fraud cases sourced from phishing scams, fake job postings, social media, and news, categorized into 5 major fraud types. Unlike previous benchmarks, Fraud-R1 introduces a multi-round evaluation pipeline to assess LLMs' resistance to fraud at different stages, including credibility building, urgency creation, and emotional manipulation. Furthermore, we evaluate 15 LLMs under two settings: 1. Helpful-Assistant, where the LLM provides general decision-making assistance, and 2. Role-play, where the model assumes a specific persona, widely used in real-world agent-based interactions. Our evaluation reveals the significant challenges in defending against fraud and phishing inducement, especially in role-play settings and fake job postings. Additionally, we observe a substantial performance gap between Chinese and English, underscoring the need for improved multilingual fraud detection capabilities.

cs.CL↗

arXiv2025

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs

Rapid integration of large language models (LLMs) into societal applications has intensified concerns about their alignment with universal ethical principles, as their internal value representations remain opaque despite behavioral alignment advancements. Current approaches struggle to systematically interpret how values are encoded in neural architectures, limited by datasets that prioritize superficial judgments over mechanistic analysis. We introduce ValueLocate, a mechanistic interpretability framework grounded in the Schwartz Values Survey, to address this gap. Our method first constructs ValueInsight, a dataset that operationalizes four dimensions of universal value through behavioral contexts in the real world. Leveraging this dataset, we develop a neuron identification method that calculates activation differences between opposing value aspects, enabling precise localization of value-critical neurons without relying on computationally intensive attribution methods. Our proposed validation method demonstrates that targeted manipulation of these neurons effectively alters model value orientations, establishing causal relationships between neurons and value representations. This work advances the foundation for value alignment by bridging psychological value frameworks with neuron analysis in LLMs.

cs.CL↗

arXiv2025

Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era

Explainable AI (XAI) refers to techniques that provide human-understandable insights into the workings of AI models. Recently, the focus of XAI is being extended toward explaining Large Language Models (LLMs). This extension calls for a significant transformation in the XAI methodologies for two reasons. First, many existing XAI methods cannot be directly applied to LLMs due to their complexity and advanced capabilities. Second, as LLMs are increasingly deployed in diverse applications, the role of XAI shifts from merely opening the ``black box'' to actively enhancing the productivity and applicability of LLMs in real-world settings. Meanwhile, the conversation and generation abilities of LLMs can reciprocally enhance XAI. Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can explain and improve LLM-based AI systems and (2) how XAI techniques can be improved by using LLMs. We introduce 10 strategies, introducing the key techniques for each and discussing their associated challenges. We also provide case studies to demonstrate how to obtain and leverage explanations. The code used in this paper can be found at: https://github.com/JacksonWuxs/UsableXAI_LLM.

cs.LG↗

arXiv2025

Semi-supervised Concept Bottleneck Models

Concept Bottleneck Models (CBMs) have garnered increasing attention due to their ability to provide concept-based explanations for black-box deep learning models while achieving high final prediction accuracy using human-like concepts. However, the training of current CBMs is heavily dependent on the precision and richness of the annotated concepts in the dataset. These concept labels are typically provided by experts, which can be costly and require significant resources and effort. Additionally, concept saliency maps frequently misalign with input saliency maps, causing concept predictions to correspond to irrelevant input features - an issue related to annotation alignment. To address these limitations, we propose a new framework called SSCBM (Semi-supervised Concept Bottleneck Model). Our SSCBM is suitable for practical situations where annotated data is scarce. By leveraging joint training on both labeled and unlabeled data and aligning the unlabeled data at the concept level, we effectively solve these issues. We proposed a strategy to generate pseudo labels and an alignment loss. Experiments demonstrate that our SSCBM is both effective and efficient. With only 10% labeled data, our model's concept and task accuracy on average across four datasets is only 2.44% and 3.93% lower, respectively, compared to the best baseline in the fully supervised learning setting.

cs.CV↗

arXiv2025

Backdooring Vision-Language Models with Out-Of-Distribution Data

The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs. Despite their growing importance, the security of VLMs, particularly against backdoor attacks, is under explored. Moreover, prior works often assume attackers have access to the original training data, which is often unrealistic. In this paper, we address a more practical and challenging scenario where attackers must rely solely on Out-Of-Distribution (OOD) data. We introduce VLOOD (Backdooring Vision-Language Models with Out-of-Distribution Data), a novel approach with two key contributions: (1) demonstrating backdoor attacks on VLMs in complex image-to-text tasks while minimizing degradation of the original semantics under poisoned inputs, and (2) proposing innovative techniques for backdoor injection without requiring any access to the original training data. Our evaluation on image captioning and visual question answering (VQA) tasks confirms the effectiveness of VLOOD, revealing a critical security vulnerability in VLMs and laying the foundation for future research on securing multimodal models against sophisticated threats.

cs.CV↗

arXiv2025

Exploring the Personality Traits of LLMs through Latent Features Steering

Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities, the mechanisms through which these models encode and express specific personality traits remain poorly understood. To address this, we investigate how various factors, such as cultural norms and environmental stressors, encoded within LLMs, shape their personality traits, guided by the theoretical framework of social determinism. Inspired by related work on LLM interpretability, we propose a training-free approach to modify the model's behavior by extracting and steering latent features corresponding to factors within the model, thereby eliminating the need for retraining. Furthermore, we analyze the implications of these factors for model safety, focusing on their impact through the lens of personality.

cs.CL↗

arXiv2025

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning

Transformer-based language models have achieved significant success; however, their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. While previous studies have demonstrated that these models implicitly embed reasoning trees, humans typically employ various distinct logical reasoning mechanisms to complete the same task. It is still unclear which multi-step reasoning mechanisms are used by language models to solve such tasks. In this paper, we aim to address this question by investigating the mechanistic interpretability of language models, particularly in the context of multi-step reasoning tasks. Specifically, we employ circuit analysis and self-influence functions to evaluate the changing importance of each token throughout the reasoning process, allowing us to map the reasoning paths adopted by the model. We apply this methodology to the GPT-2 model on a prediction task (IOI) and demonstrate that the underlying circuits reveal a human-interpretable reasoning process used by the model.

cs.AI↗

arXiv2025

EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

Understanding the internal mechanisms of transformer-based language models remains challenging. Mechanistic interpretability based on circuit discovery aims to reverse engineer neural networks by analyzing their internal processes at the level of computational subgraphs. In this paper, we revisit existing gradient-based circuit identification methods and find that their performance is either affected by the zero-gradient problem or saturation effects, where edge attribution scores become insensitive to input changes, resulting in noisy and unreliable attribution evaluations for circuit components. To address the saturation effect, we propose Edge Attribution Patching with GradPath (EAP-GP), EAP-GP introduces an integration path, starting from the input and adaptively following the direction of the difference between the gradients of corrupted and clean inputs to avoid the saturated region. This approach enhances attribution reliability and improves the faithfulness of circuit identification. We evaluate EAP-GP on 6 datasets using GPT-2 Small, GPT-2 Medium, and GPT-2 XL. Experimental results demonstrate that EAP-GP outperforms existing methods in circuit faithfulness, achieving improvements up to 17.7%. Comparisons with manually annotated ground-truth circuits demonstrate that EAP-GP achieves precision and recall comparable to or better than previous approaches, highlighting its effectiveness in identifying accurate circuits.

cs.LG↗

arXiv2025

Editable Concept Bottleneck Models

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a humanunderstandable concept layer. However, most previous studies focused on cases where the data, including concepts, are clean. In many scenarios, we often need to remove/insert some training data or new concepts from trained CBMs for reasons such as privacy concerns, data mislabelling, spurious concepts, and concept annotation errors. Thus, deriving efficient editable CBMs without retraining from scratch remains a challenge, particularly in large-scale applications. To address these challenges, we propose Editable Concept Bottleneck Models (ECBMs). Specifically, ECBMs support three different levels of data removal: concept-label-level, concept-level, and data-level. ECBMs enjoy mathematically rigorous closed-form approximations derived from influence functions that obviate the need for retraining. Experimental results demonstrate the efficiency and adaptability of our ECBMs, affirming their practical value in CBMs.

cs.LG↗

arXiv2025

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing

The locate-then-edit paradigm has shown significant promise for knowledge editing (KE) in Large Language Models (LLMs). While previous methods perform well on single-hop fact recall tasks, they consistently struggle with multi-hop factual recall tasks involving newly edited knowledge. In this paper, leveraging tools in mechanistic interpretability, we first identify that in multi-hop tasks, LLMs tend to retrieve knowledge with implicit subject information from deeper MLP layers, unlike single-hop tasks, which rely on shallow layers. This distinction explains the poor performance of current methods in multi-hop queries, as they primarily focus on editing shallow layers with single-hop edit prompts, leaving deeper layers unchanged. To address this, we propose IFMET, a novel locate-then-edit KE approach designed to edit both shallow and deep MLP layers. Beyond single-hop editing prompts, IFMET further incorporates multi-hop editing prompts to locate and modify knowledge across different stages of reasoning. Experimental results demonstrate that IFMET significantly improves performance on multi-hop factual recall tasks, overcoming the limitations of previous locate-then-edit methods

cs.CL↗

arXiv2025

Dissecting Representation Misalignment in Contrastive Learning via Influence Function

Contrastive learning, commonly applied in large-scale multimodal models, often relies on data from diverse and often unreliable sources, which can include misaligned or mislabeled text-image pairs. This frequently leads to robustness issues and hallucinations, ultimately causing performance degradation. Data valuation is an efficient way to detect and trace these misalignments. Nevertheless, existing methods are computationally expensive for large-scale models. Although computationally efficient, classical influence functions are inadequate for contrastive learning models, as they were initially designed for pointwise loss. Furthermore, contrastive learning involves minimizing the distance between positive sample modalities while maximizing the distance between negative sample modalities. This necessitates evaluating the influence of samples from both perspectives. To tackle these challenges, we introduce the Extended Influence Function for Contrastive Loss (ECIF), an influence function crafted for contrastive loss. ECIF considers both positive and negative samples and provides a closed-form approximation of contrastive learning models, eliminating the need for retraining. Building upon ECIF, we develop a series of algorithms for data evaluation, misalignment detection, and misprediction trace-back tasks. Experimental results demonstrate our ECIF advances the transparency and interpretability of CLIP-style embedding models by offering a more accurate assessment of data impact and model alignment compared to traditional baseline methods.

cs.LG↗

arXiv2025

Evaluating Data Influence in Meta Learning

As one of the most fundamental models, meta learning aims to effectively address few-shot learning challenges. However, it still faces significant issues related to the training data, such as training inefficiencies due to numerous low-contribution tasks in large datasets and substantial noise from incorrect labels. Thus, training data attribution methods are needed for meta learning. However, the dual-layer structure of mata learning complicates the modeling of training data contributions because of the interdependent influence between meta-parameters and task-specific parameters, making existing data influence evaluation tools inapplicable or inaccurate. To address these challenges, based on the influence function, we propose a general data attribution evaluation framework for meta-learning within the bilevel optimization framework. Our approach introduces task influence functions (task-IF) and instance influence functions (instance-IF) to accurately assess the impact of specific tasks and individual data points in closed forms. This framework comprehensively models data contributions across both the inner and outer training processes, capturing the direct effects of data points on meta-parameters as well as their indirect influence through task-specific parameters. We also provide several strategies to enhance computational efficiency and scalability. Experimental results demonstrate the framework's effectiveness in training data evaluation via several downstream tasks.

cs.LG↗