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 remains poorly understood, as existing evaluations lack fine-grained constraint analysis. We introduce XIFBench, a comprehensive constraint-based benchmark for assessing multilingual instruction-following abilities of LLMs, featuring a novel taxonomy of five constraint categories and 465 parallel instructions across six languages spanning different resource levels. To ensure consistent cross-lingual evaluation, we develop a requirement-based protocol that leverages English requirements as semantic anchors. These requirements are then used to validate the translations across languages. Extensive experiments with various LLMs reveal notable variations in instruction-following performance across resource levels, identifying key influencing factors such as constraint categories, instruction complexity, and cultural specificity.

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.

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.

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.

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.

Similarity-Dissimilarity Loss with Supervised Contrastive Learning for Multi-label Classification

Supervised contrastive learning has been explored in making use of label information for multi-label classification, but determining positive samples in multi-label scenario remains challenging. Previous studies have examined strategies for identifying positive samples, considering label overlap proportion between anchors and samples. However, they ignore various relations between given anchors and samples, as well as how to dynamically adjust the weights in contrastive loss functions based on different relations, leading to great ambiguity. In this paper, we introduce five distinct relations between multi-label samples and propose a Similarity-Dissimilarity Loss with contrastive learning for multi-label classification. Our loss function re-weights the loss by computing the similarity and dissimilarity between positive samples and a given anchor based on the introduced relations. We mainly conduct experiments for multi-label text classification on MIMIC datasets, then further extend the evaluation on MS-COCO. The Experimental results show that our proposed loss effectively improves the performance on all encoders under supervised contrastive learning paradigm, demonstrating its effectiveness and robustness.

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.

LLM with Relation Classifier for Document-Level Relation Extraction

Large language models (LLMs) create 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. This paper investigates the causes of this performance gap, identifying the dispersion of attention by LLMs due to entity pairs without relations as a primary factor. We then introduce a novel classifier-LLM approach to DocRE. The proposed approach begins with a classifier specifically designed to select entity pair candidates exhibiting potential relations and thereby feeds them to LLM for the final relation extraction. This method ensures that during inference, the LLM's focus is directed primarily at entity pairs with relations. Experiments on DocRE benchmarks reveal that our method significantly outperforms recent LLM-based DocRE models and achieves competitive performance with several leading traditional DocRE models.

Augmenting emotion features in irony detection with Large language modeling

This study introduces a novel method for irony detection, applying Large Language Models (LLMs) with prompt-based learning to facilitate emotion-centric text augmentation. Traditional irony detection techniques typically fall short due to their reliance on static linguistic features and predefined knowledge bases, often overlooking the nuanced emotional dimensions integral to irony. In contrast, our methodology augments the detection process by integrating subtle emotional cues, augmented through LLMs, into three benchmark pre-trained NLP models - BERT, T5, and GPT-2 - which are widely recognized as foundational in irony detection. We assessed our method using the SemEval-2018 Task 3 dataset and observed substantial enhancements in irony detection capabilities.

SensoryT5: Infusing Sensorimotor Norms into T5 for Enhanced Fine-grained Emotion Classification

In traditional research approaches, sensory perception and emotion classification have traditionally been considered separate domains. Yet, the significant influence of sensory experiences on emotional responses is undeniable. The natural language processing (NLP) community has often missed the opportunity to merge sensory knowledge with emotion classification. To address this gap, we propose SensoryT5, a neuro-cognitive approach that integrates sensory information into the T5 (Text-to-Text Transfer Transformer) model, designed specifically for fine-grained emotion classification. This methodology incorporates sensory cues into the T5's attention mechanism, enabling a harmonious balance between contextual understanding and sensory awareness. The resulting model amplifies the richness of emotional representations. In rigorous tests across various detailed emotion classification datasets, SensoryT5 showcases improved performance, surpassing both the foundational T5 model and current state-of-the-art works. Notably, SensoryT5's success signifies a pivotal change in the NLP domain, highlighting the potential influence of neuro-cognitive data in refining machine learning models' emotional sensitivity.