Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs

As video large language models (Video-LLMs) become increasingly integrated into real-world applications that demand grounded multimodal reasoning, ensuring their factual consistency and reliability is of critical importance. However, sycophancy, the tendency of these models to align with user input even when it contradicts the visual evidence, undermines their trustworthiness in such contexts. Current sycophancy research has largely overlooked its specific manifestations in the video-language domain, resulting in a notable absence of systematic benchmarks and targeted evaluations to understand how Video-LLMs respond under misleading user input. To fill this gap, we propose VISE (Video-LLM Sycophancy Benchmarking and Evaluation), the first dedicated benchmark designed to evaluate sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks. Specifically, VISE pioneeringly brings linguistic perspectives on sycophancy into the visual domain, enabling fine-grained analysis across multiple sycophancy types and interaction patterns. In addition, we explore key-frame selection as an interpretable, training-free mitigation strategy, which reveals potential paths for reducing sycophantic bias by strengthening visual grounding.

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.

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.

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.

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.

Understanding the Repeat Curse in Large Language Models from a Feature Perspective

Large language models (LLMs) have made remarkable progress in various domains, yet they often suffer from repetitive text generation, a phenomenon we refer to as the "Repeat Curse". While previous studies have proposed decoding strategies to mitigate repetition, the underlying mechanism behind this issue remains insufficiently explored. In this work, we investigate the root causes of repetition in LLMs through the lens of mechanistic interpretability. Inspired by recent advances in Sparse Autoencoders (SAEs), which enable monosemantic feature extraction, we propose a novel approach, "Duplicatus Charm", to induce and analyze the Repeat Curse. Our method systematically identifies "Repetition Features" -the key model activations responsible for generating repetitive outputs. First, we locate the layers most involved in repetition through logit analysis. Next, we extract and stimulate relevant features using SAE-based activation manipulation. To validate our approach, we construct a repetition dataset covering token and paragraph level repetitions and introduce an evaluation pipeline to quantify the influence of identified repetition features. Furthermore, by deactivating these features, we have effectively mitigated the Repeat Curse.

C^2 ATTACK: Towards Representation Backdoor on CLIP via Concept Confusion

Backdoor attacks pose a significant threat to deep learning models, enabling adversaries to embed hidden triggers that manipulate the behavior of the model during inference. Traditional backdoor attacks typically rely on inserting explicit triggers (e.g., external patches, or perturbations) into input data, but they often struggle to evade existing defense mechanisms. To address this limitation, we investigate backdoor attacks through the lens of the reasoning process in deep learning systems, drawing insights from interpretable AI. We conceptualize backdoor activation as the manipulation of learned concepts within the model's latent representations. Thus, existing attacks can be seen as implicit manipulations of these activated concepts during inference. This raises interesting questions: why not manipulate the concepts explicitly? This idea leads to our novel backdoor attack framework, Concept Confusion Attack (C^2 ATTACK), which leverages internal concepts in the model's reasoning as "triggers" without introducing explicit external modifications. By avoiding the use of real triggers and directly activating or deactivating specific concepts in latent spaces, our approach enhances stealth, making detection by existing defenses significantly harder. Using CLIP as a case study, experimental results demonstrate the effectiveness of C^2 ATTACK, achieving high attack success rates while maintaining robustness against advanced defenses.

Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation

We present a comprehensive evaluation framework for assessing Large Language Models' (LLMs) capabilities in suicide prevention, focusing on two critical aspects: the Identification of Implicit Suicidal ideation (IIS) and the Provision of Appropriate Supportive responses (PAS). We introduce \ourdata, a novel dataset of 1,308 test cases built upon psychological frameworks including D/S-IAT and Negative Automatic Thinking, alongside real-world scenarios. Through extensive experiments with 8 widely used LLMs under different contextual settings, we find that current models struggle significantly with detecting implicit suicidal ideation and providing appropriate support, highlighting crucial limitations in applying LLMs to mental health contexts. Our findings underscore the need for more sophisticated approaches in developing and evaluating LLMs for sensitive psychological applications.

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.

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

Transformer-based language models have achieved notable success, yet their internal reasoning mechanisms remain largely opaque due to complex non-linear interactions and high-dimensional operations. While previous research suggests that these models implicitly encode reasoning structures, it is still unclear which specific multi-step thought processes they employ to solve complex tasks. To address this gap, we propose a novel mechanistic interpretability framework, SICAF, designed to trace and analyze the reasoning strategies that language models use in multi-step inference tasks. By employing circuit analysis and self-influence functions, we quantify the evolving importance of each token throughout the reasoning process, thereby mapping the pathways the model uses for inference. Applying SICAF to the GPT-2 model on the Indirect Object Identification (IOI) prediction task, we demonstrate how underlying circuits can reveal a reasoning process that aligns with human interpretability, offering new insights into the model's internal logic.