arXiv subjects

Yunfei Long

Publications and source records attributed to Yunfei Long.

At least 19 recordsLinked to original sources

arXiv2026

CLARA: Clip-Level Multimodal Alignment with VLM-Derived Rationales for Hateful Video Detection

Hateful video detection has become increasingly important with the rapid growth of video-centric social media platforms, given the serious risks that hate speech poses to both individual well-being and social cohesion. Compared with text or static multimodal content, hateful video detection remains underexplored and significantly more challenging, as hateful meaning often arises from complex interactions among multimodal cues, including speech, audio, and visual content. Moreover, such signals are often brief, implicit, and temporally dependent, making them difficult to capture using conventional video-level representations. In this work, we propose CLARA, a clip-level multimodal framework for hateful video detection. Instead of treating a video as a single instance, CLARA models it as a sequence of fine-grained clips, enabling more precise capture of temporally localized hateful signals. We introduce a Mixture-of-Experts clip encoder for adaptive multimodal alignment, a local-global segment contrastive objective to jointly model short-term cues and long-range temporal dependencies, and VLM-derived rationales integrated via a gated Transformer to provide high-level semantic guidance. Extensive experiments on three hateful video datasets demonstrate that CLARA consistently outperforms state-of-the-art methods. Further ablation studies and parameter analyses validate the effectiveness of each component.

cs.CV↗

arXiv2026

NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment

Novelty is a core requirement in academic publishing and a central focus of peer review, yet the growing volume of submissions has placed increasing pressure on human reviewers. While large language models (LLMs), including those fine-tuned on peer review data, have shown promise in generating review comments, the absence of a dedicated benchmark has limited systematic evaluation of their ability to assess research novelty. To address this gap, we introduce NovBench, the first large-scale benchmark designed to evaluate LLMs' capability to generate novelty evaluations in support of human peer review. NovBench comprises 1,684 paper-review pairs from a leading NLP conference, including novelty descriptions extracted from paper introductions and corresponding expert-written novelty evaluations. We focus on both sources because the introduction provides a standardized and explicit articulation of novelty claims, while expert-written novelty evaluations constitute one of the current gold standards of human judgment. Furthermore, we propose a four-dimensional evaluation framework (including Relevance, Correctness, Coverage, and Clarity) to assess the quality of LLM-generated novelty evaluations. Extensive experiments on both general and specialized LLMs under different prompting strategies reveal that current models exhibit limited understanding of scientific novelty, and that fine--tuned models often suffer from instruction-following deficiencies. These findings underscore the need for targeted fine-tuning strategies that jointly improve novelty comprehension and instruction adherence.

cs.CL↗

arXiv2026

CALM: Culturally Self-Aware Language Models

Cultural awareness in language models is the capacity to understand and adapt to diverse cultural contexts. However, most existing approaches treat culture as static background knowledge, overlooking its dynamic and evolving nature. This limitation reduces their reliability in downstream tasks that demand genuine cultural sensitivity. In this work, we introduce CALM, a novel framework designed to endow language models with cultural self-awareness. CALM disentangles task semantics from explicit cultural concepts and latent cultural signals, shaping them into structured cultural clusters through contrastive learning. These clusters are then aligned via cross-attention to establish fine-grained interactions among related cultural features and are adaptively integrated through a Mixture-of-Experts mechanism along culture-specific dimensions. The resulting unified representation is fused with the model's original knowledge to construct a culturally grounded internal identity state, which is further enhanced through self-prompted reflective learning, enabling continual adaptation and self-correction. Extensive experiments conducted on multiple cross-cultural benchmark datasets demonstrate that CALM consistently outperforms state-of-the-art methods.

cs.CL↗

arXiv2025

Learn to Select: Exploring Label Distribution Divergence for In-Context Demonstration Selection in Text Classification

In-context learning (ICL) for text classification, which uses a few input-label demonstrations to describe a task, has demonstrated impressive performance on large language models (LLMs). However, the selection of in-context demonstrations plays a crucial role and can significantly affect LLMs' performance. Most existing demonstration selection methods primarily focus on semantic similarity between test inputs and demonstrations, often overlooking the importance of label distribution alignment. To address this limitation, we propose a two-stage demonstration selection method, TopK + Label Distribution Divergence (L2D), which leverages a fine-tuned BERT-like small language model (SLM) to generate label distributions and calculate their divergence for both test inputs and candidate demonstrations. This enables the selection of demonstrations that are not only semantically similar but also aligned in label distribution with the test input. Extensive experiments across seven text classification benchmarks show that our method consistently outperforms previous demonstration selection strategies. Further analysis reveals a positive correlation between the performance of LLMs and the accuracy of the underlying SLMs used for label distribution estimation.

cs.CL↗

arXiv2025

EmoPerso: Enhancing Personality Detection with Self-Supervised Emotion-Aware Modelling

Personality detection from text is commonly performed by analysing users' social media posts. However, existing methods heavily rely on large-scale annotated datasets, making it challenging to obtain high-quality personality labels. Moreover, most studies treat emotion and personality as independent variables, overlooking their interactions. In this paper, we propose a novel self-supervised framework, EmoPerso, which improves personality detection through emotion-aware modelling. EmoPerso first leverages generative mechanisms for synthetic data augmentation and rich representation learning. It then extracts pseudo-labeled emotion features and jointly optimizes them with personality prediction via multi-task learning. A cross-attention module is employed to capture fine-grained interactions between personality traits and the inferred emotional representations. To further refine relational reasoning, EmoPerso adopts a self-taught strategy to enhance the model's reasoning capabilities iteratively. Extensive experiments on two benchmark datasets demonstrate that EmoPerso surpasses state-of-the-art models. The source code is available at https://github.com/slz0925/EmoPerso.

cs.CL↗

arXiv2025

Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games

Interactive Fiction games (IF games) are where players interact through natural language commands. While recent advances in Artificial Intelligence agents have reignited interest in IF games as a domain for studying decision-making, existing approaches prioritize task-specific performance metrics over human-like comprehension of narrative context and gameplay logic. This work presents a cognitively inspired framework that guides Large Language Models (LLMs) to learn and play IF games systematically. Our proposed **L**earning to **P**lay **L**ike **H**umans (LPLH) framework integrates three key components: (1) structured map building to capture spatial and narrative relationships, (2) action learning to identify context-appropriate commands, and (3) feedback-driven experience analysis to refine decision-making over time. By aligning LLMs-based agents' behavior with narrative intent and commonsense constraints, LPLH moves beyond purely exploratory strategies to deliver more interpretable, human-like performance. Crucially, this approach draws on cognitive science principles to more closely simulate how human players read, interpret, and respond within narrative worlds. As a result, LPLH reframes the IF games challenge as a learning problem for LLMs-based agents, offering a new path toward robust, context-aware gameplay in complex text-based environments.

cs.CL↗

arXiv2025

RICCARDO: Radar Hit Prediction and Convolution for Camera-Radar 3D Object Detection

Radar hits reflect from points on both the boundary and internal to object outlines. This results in a complex distribution of radar hits that depends on factors including object category, size, and orientation. Current radar-camera fusion methods implicitly account for this with a black-box neural network. In this paper, we explicitly utilize a radar hit distribution model to assist fusion. First, we build a model to predict radar hit distributions conditioned on object properties obtained from a monocular detector. Second, we use the predicted distribution as a kernel to match actual measured radar points in the neighborhood of the monocular detections, generating matching scores at nearby positions. Finally, a fusion stage combines context with the kernel detector to refine the matching scores. Our method achieves the state-of-the-art radar-camera detection performance on nuScenes. Our source code is available at https://github.com/longyunf/riccardo.

cs.CV↗

arXiv2025

Less but Better: Parameter-Efficient Fine-Tuning of Large Language Models for Personality Detection

Personality detection automatically identifies an individual's personality from various data sources, such as social media texts. However, as the parameter scale of language models continues to grow, the computational cost becomes increasingly difficult to manage. Fine-tuning also grows more complex, making it harder to justify the effort and reliably predict outcomes. We introduce a novel parameter-efficient fine-tuning framework, PersLLM, to address these challenges. In PersLLM, a large language model (LLM) extracts high-dimensional representations from raw data and stores them in a dynamic memory layer. PersLLM then updates the downstream layers with a replaceable output network, enabling flexible adaptation to various personality detection scenarios. By storing the features in the memory layer, we eliminate the need for repeated complex computations by the LLM. Meanwhile, the lightweight output network serves as a proxy for evaluating the overall effectiveness of the framework, improving the predictability of results. Experimental results on key benchmark datasets like Kaggle and Pandora show that PersLLM significantly reduces computational cost while maintaining competitive performance and strong adaptability.

cs.CL↗

arXiv2025

LL4G: Self-Supervised Dynamic Optimization for Graph-Based Personality Detection

Graph-based personality detection constructs graph structures from textual data, particularly social media posts. Current methods often struggle with sparse or noisy data and rely on static graphs, limiting their ability to capture dynamic changes between nodes and relationships. This paper introduces LL4G, a self-supervised framework leveraging large language models (LLMs) to optimize graph neural networks (GNNs). LLMs extract rich semantic features to generate node representations and to infer explicit and implicit relationships. The graph structure adaptively adds nodes and edges based on input data, continuously optimizing itself. The GNN then uses these optimized representations for joint training on node reconstruction, edge prediction, and contrastive learning tasks. This integration of semantic and structural information generates robust personality profiles. Experimental results on Kaggle and Pandora datasets show LL4G outperforms state-of-the-art models.

cs.CL↗

arXiv2025

XIFBench: Evaluating Large Language Models on Multilingual Instruction Following

Large Language Models (LLMs) have demonstrated remarkable instruction-following capabilities across various applications. However, their performance in multilingual settings lacks systematic investigation, with existing evaluations lacking fine-grained constraint analysis across diverse linguistic contexts. We introduce XIFBench, a comprehensive constraint-based benchmark for evaluating multilingual instruction-following abilities of LLMs, comprising 558 instructions with 0-5 additional constraints across five categories (Content, Style, Situation, Format, and Numerical) in six languages spanning different resource levels. To support reliable and consistent cross-lingual evaluation, we implement three methodological innovations: cultural accessibility annotation, constraint-level translation validation, and requirement-based evaluation using English requirements as semantic anchors across languages. Extensive experiments with various LLMs not only quantify performance disparities across resource levels but also provide detailed insights into how language resources, constraint categories, instruction complexity, and cultural specificity influence multilingual instruction-following. Our code and data are available at https://github.com/zhenyuli801/XIFBench.

cs.CL↗

arXiv2025

Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent

Large language model (LLM) agents typically adopt a step-by-step reasoning framework, in which they interleave the processes of thinking and acting to accomplish the given task. However, this paradigm faces a deep-rooted one-pass issue whereby each generated intermediate thought is plugged into the trajectory regardless of its correctness, which can cause irreversible error propagation. To address the issue, this paper proposes a novel framework called Generator-Assistant Stepwise Rollback (GA-Rollback) to induce better decision-making for LLM agents. Particularly, GA-Rollback utilizes a generator to interact with the environment and an assistant to examine each action produced by the generator, where the assistant triggers a rollback operation upon detection of incorrect actions. Moreover, we introduce two additional strategies tailored for the rollback scenario to further improve its effectiveness. Extensive experiments show that GA-Rollback achieves significant improvements over several strong baselines on three widely used benchmarks. Our analysis further reveals that GA-Rollback can function as a robust plug-and-play module, integrating seamlessly with other methods.

cs.CL↗

arXiv2025

Irony Detection, Reasoning and Understanding in Zero-shot Learning

The generalisation of irony detection faces significant challenges, leading to substantial performance deviations when detection models are applied to diverse real-world scenarios. In this study, we find that irony-focused prompts, as generated from our IDADP framework for LLMs, can not only overcome dataset-specific limitations but also generate coherent, human-readable reasoning, transforming ironic text into its intended meaning. Based on our findings and in-depth analysis, we identify several promising directions for future research aimed at enhancing LLMs' zero-shot capabilities in irony detection, reasoning, and comprehension. These include advancing contextual awareness in irony detection, exploring hybrid symbolic-neural methods, and integrating multimodal data, among others.

cs.CL↗

arXiv2025

Detecting harassment and defamation in cyberbullying with emotion-adaptive training

Existing research on detecting cyberbullying incidents on social media has primarily concentrated on harassment and is typically approached as a binary classification task. However, cyberbullying encompasses various forms, such as denigration and harassment, which celebrities frequently face. Furthermore, suitable training data for these diverse forms of cyberbullying remains scarce. In this study, we first develop a celebrity cyberbullying dataset that encompasses two distinct types of incidents: harassment and defamation. We investigate various types of transformer-based models, namely masked (RoBERTa, Bert and DistilBert), replacing(Electra), autoregressive (XLnet), masked&permuted (Mpnet), text-text (T5) and large language models (Llama2 and Llama3) under low source settings. We find that they perform competitively on explicit harassment binary detection. However, their performance is substantially lower on harassment and denigration multi-classification tasks. Therefore, we propose an emotion-adaptive training framework (EAT) that helps transfer knowledge from the domain of emotion detection to the domain of cyberbullying detection to help detect indirect cyberbullying events. EAT consistently improves the average macro F1, precision and recall by 20% in cyberbullying detection tasks across nine transformer-based models under low-resource settings. Our claims are supported by intuitive theoretical insights and extensive experiments.

cs.CL↗

arXiv2024

GAMED: Knowledge Adaptive Multi-Experts Decoupling for Multimodal Fake News Detection

Multimodal fake news detection often involves modelling heterogeneous data sources, such as vision and language. Existing detection methods typically rely on fusion effectiveness and cross-modal consistency to model the content, complicating understanding how each modality affects prediction accuracy. Additionally, these methods are primarily based on static feature modelling, making it difficult to adapt to the dynamic changes and relationships between different data modalities. This paper develops a significantly novel approach, GAMED, for multimodal modelling, which focuses on generating distinctive and discriminative features through modal decoupling to enhance cross-modal synergies, thereby optimizing overall performance in the detection process. GAMED leverages multiple parallel expert networks to refine features and pre-embed semantic knowledge to improve the experts' ability in information selection and viewpoint sharing. Subsequently, the feature distribution of each modality is adaptively adjusted based on the respective experts' opinions. GAMED also introduces a novel classification technique to dynamically manage contributions from different modalities, while improving the explainability of decisions. Experimental results on the Fakeddit and Yang datasets demonstrate that GAMED performs better than recently developed state-of-the-art models. The source code can be accessed at https://github.com/slz0925/GAMED.

cs.LG↗

arXiv2024

MLD-EA: Check and Complete Narrative Coherence by Introducing Emotions and Actions

Narrative understanding and story generation are critical challenges in natural language processing (NLP), with much of the existing research focused on summarization and question-answering tasks. While previous studies have explored predicting plot endings and generating extended narratives, they often neglect the logical coherence within stories, leaving a significant gap in the field. To address this, we introduce the Missing Logic Detector by Emotion and Action (MLD-EA) model, which leverages large language models (LLMs) to identify narrative gaps and generate coherent sentences that integrate seamlessly with the story's emotional and logical flow. The experimental results demonstrate that the MLD-EA model enhances narrative understanding and story generation, highlighting LLMs' potential as effective logic checkers in story writing with logical coherence and emotional consistency. This work fills a gap in NLP research and advances border goals of creating more sophisticated and reliable story-generation systems.

cs.CL↗

arXiv2024

Similarity-Dissimilarity Loss for Multi-label Supervised Contrastive Learning

Supervised contrastive learning has achieved remarkable success by leveraging label information; however, determining positive samples in multi-label scenarios remains a critical challenge. In multi-label supervised contrastive learning (MSCL), multi-label relations are not yet fully defined, leading to ambiguity in identifying positive samples and formulating contrastive loss functions to construct the representation space. To address these challenges, we: (i) systematically formulate multi-label relations in MSCL, (ii) propose a novel Similarity-Dissimilarity Loss, which dynamically re-weights samples based on similarity and dissimilarity factors, (iii) further provide theoretically grounded proofs for our method through rigorous mathematical analysis that supports the formulation and effectiveness, and (iv) offer a unified form and paradigm for both single-label and multi-label supervised contrastive loss. We conduct experiments on both image and text modalities and further extend the evaluation to the medical domain. The results show that our method consistently outperforms baselines in comprehensive evaluations, demonstrating its effectiveness and robustness.

cs.LG↗

arXiv2024

Mitigating the Bias of Large Language Model Evaluation

Recently, there has been a trend of evaluating the Large Language Model (LLM) quality in the flavor of LLM-as-a-Judge, namely leveraging another LLM to evaluate the current output quality. However, existing judges are proven to be biased, namely they would favor answers which present better superficial quality (such as verbosity, fluency) while ignoring the instruction following ability. In this work, we propose systematic research about the bias of LLM-as-a-Judge. Specifically, for closed-source judge models, we apply calibration to mitigate the significance of superficial quality, both on probability level and prompt level. For open-source judge models, we propose to mitigate the bias by contrastive training, with curated negative samples that deviate from instruction but present better superficial quality. We apply our methods on the bias evaluation benchmark, and experiment results show our methods mitigate the bias by a large margin while maintaining a satisfactory evaluation accuracy.

cs.CL↗

arXiv2024

LLM with Relation Classifier for Document-Level Relation Extraction

Large language models (LLMs) have created a new paradigm for natural language processing. Despite their advancement, LLM-based methods still lag behind traditional approaches in document-level relation extraction (DocRE), a critical task for understanding complex entity relations within long context. This paper investigates the causes of this performance gap, identifying the dispersion of attention by LLMs due to entity pairs without relations as a key factor. We then introduce a novel classifier-LLM approach to DocRE. Particularly, the proposed approach begins with a classifier designed to select entity pair candidates that exhibit potential relations and then feed them to LLM for final relation classification. This method ensures that the LLM's attention is directed at relation-expressing entity pairs instead of those without relations during inference. Experiments on DocRE benchmarks reveal that our method significantly outperforms recent LLM-based DocRE models and narrows the performance gap with state-of-the-art BERT-based models.

cs.CL↗