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.

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.

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.

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.

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.

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.

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.

Pre-trained language models (PLMs) leverage chains-of-thought (CoT) to simulate human reasoning and inference processes, achieving proficient performance in multi-hop QA. However, a gap persists between PLMs' reasoning abilities and those of humans when tackling complex problems. Psychological studies suggest a vital connection between explicit information in passages and human prior knowledge during reading. Nevertheless, current research has given insufficient attention to linking input passages and PLMs' pre-training-based knowledge from the perspective of human cognition studies. In this study, we introduce a Prompting Explicit and Implicit knowledge (PEI) framework, which uses prompts to connect explicit and implicit knowledge, aligning with human reading process for multi-hop QA. We consider the input passages as explicit knowledge, employing them to elicit implicit knowledge through unified prompt reasoning. Furthermore, our model incorporates type-specific reasoning via prompts, a form of implicit knowledge. Experimental results show that PEI performs comparably to the state-of-the-art on HotpotQA. Ablation studies confirm the efficacy of our model in bridging and integrating explicit and implicit knowledge.

Deep learning (DL) has substantially enhanced natural language processing (NLP) in healthcare research. However, the increasing complexity of DL-based NLP necessitates transparent model interpretability, or at least explainability, for reliable decision-making. This work presents a thorough scoping review of explainable and interpretable DL in healthcare NLP. The term "eXplainable and Interpretable Artificial Intelligence" (XIAI) is introduced to distinguish XAI from IAI. Different models are further categorized based on their functionality (model-, input-, output-based) and scope (local, global). Our analysis shows that attention mechanisms are the most prevalent emerging IAI technique. The use of IAI is growing, distinguishing it from XAI. The major challenges identified are that most XIAI does not explore "global" modelling processes, the lack of best practices, and the lack of systematic evaluation and benchmarks. One important opportunity is to use attention mechanisms to enhance multi-modal XIAI for personalized medicine. Additionally, combining DL with causal logic holds promise. Our discussion encourages the integration of XIAI in Large Language Models (LLMs) and domain-specific smaller models. In conclusion, XIAI adoption in healthcare requires dedicated in-house expertise. Collaboration with domain experts, end-users, and policymakers can lead to ready-to-use XIAI methods across NLP and medical tasks. While challenges exist, XIAI techniques offer a valuable foundation for interpretable NLP algorithms in healthcare.

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.