Recent advances in LegalAI have primarily focused on individual case judgment analysis, often overlooking the critical appellate process within the judicial system. Appeals serve as a core mechanism for error correction and ensuring fair trials, making them highly significant both in practice and in research. To address this gap, we present the AppealCase dataset, consisting of 10,000 pairs of real-world, matched first-instance and second-instance documents across 91 categories of civil cases. The dataset also includes detailed annotations along five dimensions central to appellate review: judgment reversals, reversal reasons, cited legal provisions, claim-level decisions, and whether there is new information in the second instance. Based on these annotations, we propose five novel LegalAI tasks and conduct a comprehensive evaluation across 20 mainstream models. Experimental results reveal that all current models achieve less than 50% F1 scores on the judgment reversal prediction task, highlighting the complexity and challenge of the appeal scenario. We hope that the AppealCase dataset will spur further research in LegalAI for appellate case analysis and contribute to improving consistency in judicial decision-making.
This study introduces a framework for evaluating consistency in large language model (LLM) binary text classification, addressing the lack of established reliability assessment methods. Adapting psychometric principles, we determine sample size requirements, develop metrics for invalid responses, and evaluate intra- and inter-rater reliability. Our case study examines financial news sentiment classification across 14 LLMs (including claude-3-7-sonnet, gpt-4o, deepseek-r1, gemma3, llama3.2, phi4, and command-r-plus), with five replicates per model on 1,350 articles. Models demonstrated high intra-rater consistency, achieving perfect agreement on 90-98% of examples, with minimal differences between expensive and economical models from the same families. When validated against StockNewsAPI labels, models achieved strong performance (accuracy 0.76-0.88), with smaller models like gemma3:1B, llama3.2:3B, and claude-3-5-haiku outperforming larger counterparts. All models performed at chance when predicting actual market movements, indicating task constraints rather than model limitations. Our framework provides systematic guidance for LLM selection, sample size planning, and reliability assessment, enabling organizations to optimize resources for classification tasks.
The design of optimization algorithms for neural networks remains a critical challenge, with most existing methods relying on heuristic adaptations of gradient-based approaches. This paper introduces KO (Kinetics-inspired Optimizer), a novel neural optimizer inspired by kinetic theory and partial differential equation (PDE) simulations. We reimagine the training dynamics of network parameters as the evolution of a particle system governed by kinetic principles, where parameter updates are simulated via a numerical scheme for the Boltzmann transport equation (BTE) that models stochastic particle collisions. This physics-driven approach inherently promotes parameter diversity during optimization, mitigating the phenomenon of parameter condensation, i.e. collapse of network parameters into low-dimensional subspaces, through mechanisms analogous to thermal diffusion in physical systems. We analyze this property, establishing both a mathematical proof and a physical interpretation. Extensive experiments on image classification (CIFAR-10/100, ImageNet) and text classification (IMDB, Snips) tasks demonstrate that KO consistently outperforms baseline optimizers (e.g., Adam, SGD), achieving accuracy improvements while computation cost remains comparable.
The rapid advancement of large language models (LLMs) calls for a rigorous theoretical framework to explain their empirical success. While significant progress has been made in understanding LLM behaviors, existing theoretical frameworks remain fragmented in explaining emergent phenomena through a unified mathematical lens. We establish the first formal connection between LLM architectures and Algorithmic Information Theory (AIT) by proving two fundamental results: (1) the training process computationally approximates Solomonoff prior through loss minimization interpreted as program length optimization, and (2) next-token prediction implements approximate Solomonoff induction. We leverage AIT to provide a unified theoretical explanation for in-context learning, few-shot learning, and scaling laws. Furthermore, our theoretical insights lead to a principled method for few-shot example selection that prioritizes samples where models exhibit lower predictive confidence. We demonstrate through experiments on diverse text classification benchmarks that this strategy yields significant performance improvements, particularly for smaller model architectures, when compared to selecting high-confidence examples. Our framework bridges the gap between theoretical foundations and practical LLM behaviors, providing both explanatory power and actionable insights for future model development.
Query routing, the task to route user queries to different large language model (LLM) endpoints, can be considered as a text classification problem. However, out-of-distribution queries must be handled properly, as those could be questions about unrelated domains, queries in other languages, or even contain unsafe text. Here, we thus study a \emph{guarded} query routing problem, for which we first introduce the Guarded Query Routing Benchmark (GQR-Bench), which covers three exemplary target domains (law, finance, and healthcare), and seven datasets to test robustness against out-of-distribution queries. We then use GQR-Bench to contrast the effectiveness and efficiency of LLM-based routing mechanisms (GPT-4o-mini, Llama-3.2-3B, and Llama-3.1-8B), standard LLM-based guardrail approaches (LlamaGuard and NVIDIA NeMo Guardrails), continuous bag-of-words classifiers (WideMLP, fastText), and traditional machine learning models (SVM, XGBoost). Our results show that WideMLP, enhanced with out-of-domain detection capabilities, yields the best trade-off between accuracy (88\%) and speed (<4ms). The embedding-based fastText excels at speed (<1ms) with acceptable accuracy (80\%), whereas LLMs yield the highest accuracy (91\%) but are comparatively slow (62ms for local Llama-3.1:8B and 669ms for remote GPT-4o-mini calls). Our findings challenge the automatic reliance on LLMs for (guarded) query routing and provide concrete recommendations for practical applications. GQR-Bench will be released as a Python package -- \texttt{gqr}.
Effective prompt engineering remains a central challenge in fully harnessing the capabilities of LLMs. While well-designed prompts can dramatically enhance performance, crafting them typically demands expert intuition and a nuanced understanding of the task. Moreover, the most impactful prompts often hinge on subtle semantic cues, ones that may elude human perception but are crucial for guiding LLM behavior. In this paper, we introduce PRL (Prompts from Reinforcement Learning), a novel RL-based approach for automatic prompt generation. Unlike previous methods, PRL can produce novel few-shot examples that were not seen during training. Our approach achieves state-of-the-art performance across a range of benchmarks, including text classification, simplification, and summarization. On the classification task, it surpasses prior methods by 2.58% over APE and 1.00% over EvoPrompt. Additionally, it improves the average ROUGE scores on the summarization task by 4.32 over APE and by 2.12 over EvoPrompt and the SARI score on simplification by 6.93 over APE and by 6.01 over EvoPrompt. Our code is available at https://github.com/Batorskq/prl .
Hausa Natural Language Processing (NLP) has gained increasing attention in recent years, yet remains understudied as a low-resource language despite having over 120 million first-language (L1) and 80 million second-language (L2) speakers worldwide. While significant advances have been made in high-resource languages, Hausa NLP faces persistent challenges, including limited open-source datasets and inadequate model representation. This paper presents an overview of the current state of Hausa NLP, systematically examining existing resources, research contributions, and gaps across fundamental NLP tasks: text classification, machine translation, named entity recognition, speech recognition, and question answering. We introduce HausaNLP (https://catalog.hausanlp.org), a curated catalog that aggregates datasets, tools, and research works to enhance accessibility and drive further development. Furthermore, we discuss challenges in integrating Hausa into large language models (LLMs), addressing issues of suboptimal tokenization and dialectal variation. Finally, we propose strategic research directions emphasizing dataset expansion, improved language modeling approaches, and strengthened community collaboration to advance Hausa NLP. Our work provides both a foundation for accelerating Hausa NLP progress and valuable insights for broader multilingual NLP research.
Recent research highlights concerns about the trustworthiness of third-party Pre-Trained Language Models (PTLMs) due to potential backdoor attacks. These backdoored PTLMs, however, are effective only for specific pre-defined downstream tasks. In reality, these PTLMs can be adapted to many other unrelated downstream tasks. Such adaptation may lead to unforeseen consequences in downstream model outputs, consequently raising user suspicion and compromising attack stealthiness. We refer to this phenomenon as backdoor complications. In this paper, we undertake the first comprehensive quantification of backdoor complications. Through extensive experiments using 4 prominent PTLMs and 16 text classification benchmark datasets, we demonstrate the widespread presence of backdoor complications in downstream models fine-tuned from backdoored PTLMs. The output distribution of triggered samples significantly deviates from that of clean samples. Consequently, we propose a backdoor complication reduction method leveraging multi-task learning to mitigate complications without prior knowledge of downstream tasks. The experimental results demonstrate that our proposed method can effectively reduce complications while maintaining the efficacy and consistency of backdoor attacks. Our code is available at https://github.com/zhangrui4041/Backdoor_Complications.
While transformer-based models achieve strong performance on text classification, we explore whether masking input tokens can further enhance their effectiveness. We propose token masking regularization, a simple yet theoretically motivated method that randomly replaces input tokens with a special [MASK] token at probability p. This introduces stochastic perturbations during training, leading to implicit gradient averaging that encourages the model to capture deeper inter-token dependencies. Experiments on language identification and sentiment analysis -- across diverse models (mBERT, Qwen2.5-0.5B, TinyLlama-1.1B) -- show consistent improvements over standard regularization techniques. We identify task-specific optimal masking rates, with p = 0.1 as a strong general default. We attribute the gains to two key effects: (1) input perturbation reduces overfitting, and (2) gradient-level smoothing acts as implicit ensembling.
Recently, training-free methods for improving large language models (LLMs) have attracted growing interest, with token-level attention tuning emerging as a promising and interpretable direction. However, existing methods typically rely on auxiliary mechanisms to identify important or irrelevant task-specific tokens, introducing potential bias and limiting applicability. In this paper, we uncover a surprising and elegant alternative: the semantically empty initial token is a powerful and underexplored control point for optimizing model behavior. Through theoretical analysis, we show that tuning the initial token's attention sharpens or flattens the attention distribution over subsequent tokens, and its role as an attention sink amplifies this effect. Empirically, we find that: (1) tuning its attention improves LLM performance more effectively than tuning other task-specific tokens; (2) the effect follows a consistent trend across layers, with earlier layers having greater impact, but varies across attention heads, with different heads showing distinct preferences in how they attend to this token. Based on these findings, we propose ZeroTuning, a training-free approach that improves LLM performance by applying head-specific attention adjustments to this special token. Despite tuning only one token, ZeroTuning achieves higher performance on text classification, multiple-choice, and multi-turn conversation tasks across models such as Llama, Qwen, and DeepSeek. For example, ZeroTuning improves Llama-3.1-8B by 11.71% on classification, 2.64% on QA tasks, and raises its multi-turn score from 7.804 to 7.966. The method is also robust to limited resources, few-shot settings, long contexts, quantization, decoding strategies, and prompt variations. Our work sheds light on a previously overlooked control point in LLMs, offering new insights into both inference-time tuning and model interpretability.
The increasing volume of healthcare textual data requires computationally efficient, yet highly accurate classification approaches able to handle the nuanced and complex nature of medical terminology. This research presents Knowledge Distillation for Healthcare Multi-Label Text Classification (KDH-MLTC), a framework leveraging model compression and Large Language Models (LLMs). The proposed approach addresses conventional healthcare Multi-Label Text Classification (MLTC) challenges by integrating knowledge distillation and sequential fine-tuning, subsequently optimized through Particle Swarm Optimization (PSO) for hyperparameter tuning. KDH-MLTC transfers knowledge from a more complex teacher LLM (i.e., BERT) to a lighter student LLM (i.e., DistilBERT) through sequential training adapted to MLTC that preserves the teacher's learned information while significantly reducing computational requirements. As a result, the classification is enabled to be conducted locally, making it suitable for healthcare textual data characterized by sensitivity and, therefore, ensuring HIPAA compliance. The experiments conducted on three medical literature datasets of different sizes, sampled from the Hallmark of Cancer (HoC) dataset, demonstrate that KDH-MLTC achieves superior performance compared to existing approaches, particularly for the largest dataset, reaching an F1 score of 82.70%. Additionally, statistical validation and an ablation study are carried out, proving the robustness of KDH-MLTC. Furthermore, the PSO-based hyperparameter optimization process allowed the identification of optimal configurations. The proposed approach contributes to healthcare text classification research, balancing efficiency requirements in resource-constrained healthcare settings with satisfactory accuracy demands.
We extend and study a semi-supervised model for text classification proposed earlier by Hatefi et al. for classification tasks in which document classes are described by a small number of gold-labeled examples, while the majority of training examples is unlabeled. The model leverages the teacher-student architecture of Meta Pseudo Labels in which a ''teacher'' generates labels for originally unlabeled training data to train the ''student'' and updates its own model iteratively based on the performance of the student on the gold-labeled portion of the data. We extend the original model of Hatefi et al. by an unsupervised pre-training phase based on objective masking, and conduct in-depth performance evaluations of the original model, our extension, and various independent baselines. Experiments are performed using three different datasets in two different languages (English and Swedish).
Robustness to label noise within data is a significant challenge in federated learning (FL). From the data-centric perspective, the data quality of distributed datasets can not be guaranteed since annotations of different clients contain complicated label noise of varying degrees, which causes the performance degradation. There have been some early attempts to tackle noisy labels in FL. However, there exists a lack of benchmark studies on comprehensively evaluating their practical performance under unified settings. To this end, we propose the first benchmark study FNBench to provide an experimental investigation which considers three diverse label noise patterns covering synthetic label noise, imperfect human-annotation errors and systematic errors. Our evaluation incorporates eighteen state-of-the-art methods over five image recognition datasets and one text classification dataset. Meanwhile, we provide observations to understand why noisy labels impair FL, and additionally exploit a representation-aware regularization method to enhance the robustness of existing methods against noisy labels based on our observations. Finally, we discuss the limitations of this work and propose three-fold future directions. To facilitate related communities, our source code is open-sourced at https://github.com/Sprinter1999/FNBench.
Hierarchical Text Classification (HTC) involves assigning documents to labels organized within a taxonomy. Most previous research on HTC has focused on supervised methods. However, in real-world scenarios, employing supervised HTC can be challenging due to a lack of annotated data. Moreover, HTC often faces issues with large label spaces and long-tail distributions. In this work, we present Knowledge Graphs for zero-shot Hierarchical Text Classification (KG-HTC), which aims to address these challenges of HTC in applications by integrating knowledge graphs with Large Language Models (LLMs) to provide structured semantic context during classification. Our method retrieves relevant subgraphs from knowledge graphs related to the input text using a Retrieval-Augmented Generation (RAG) approach. Our KG-HTC can enhance LLMs to understand label semantics at various hierarchy levels. We evaluate KG-HTC on three open-source HTC datasets: WoS, DBpedia, and Amazon. Our experimental results show that KG-HTC significantly outperforms three baselines in the strict zero-shot setting, particularly achieving substantial improvements at deeper levels of the hierarchy. This evaluation demonstrates the effectiveness of incorporating structured knowledge into LLMs to address HTC's challenges in large label spaces and long-tailed label distributions. Our code is available at: https://github.com/QianboZang/KG-HTC.
Few-shot text classification has important application value in low-resource environments. This paper proposes a strategy that combines adaptive fine-tuning, contrastive learning, and regularization optimization to improve the classification performance of Transformer-based models. Experiments on the FewRel 2.0 dataset show that T5-small, DeBERTa-v3, and RoBERTa-base perform well in few-shot tasks, especially in the 5-shot setting, which can more effectively capture text features and improve classification accuracy. The experiment also found that there are significant differences in the classification difficulty of different relationship categories. Some categories have fuzzy semantic boundaries or complex feature distributions, making it difficult for the standard cross entropy loss to learn the discriminative information required to distinguish categories. By introducing contrastive loss and regularization loss, the generalization ability of the model is enhanced, effectively alleviating the overfitting problem in few-shot environments. In addition, the research results show that the use of Transformer models or generative architectures with stronger self-attention mechanisms can help improve the stability and accuracy of few-shot classification.
Reliance on spurious correlations (shortcuts) has been shown to underlie many of the successes of language models. Previous work focused on identifying the input elements that impact prediction. We investigate how shortcuts are actually processed within the model's decision-making mechanism. We use actor names in movie reviews as controllable shortcuts with known impact on the outcome. We use mechanistic interpretability methods and identify specific attention heads that focus on shortcuts. These heads gear the model towards a label before processing the complete input, effectively making premature decisions that bypass contextual analysis. Based on these findings, we introduce Head-based Token Attribution (HTA), which traces intermediate decisions back to input tokens. We show that HTA is effective in detecting shortcuts in LLMs and enables targeted mitigation by selectively deactivating shortcut-related attention heads.
The application of large language models (LLMs) to healthcare information extraction has emerged as a promising approach. This study evaluates the classification performance of five open-source LLMs: GEMMA-3-27B-IT, LLAMA3-70B, LLAMA4-109B, DEEPSEEK-R1-DISTILL-LLAMA-70B, and DEEPSEEK-V3-0324-UD-Q2_K_XL, across six healthcare-related classification tasks involving both social media data (breast cancer, changes in medication regimen, adverse pregnancy outcomes, potential COVID-19 cases) and clinical data (stigma labeling, medication change discussion). We report precision, recall, and F1 scores with 95% confidence intervals for all model-task combinations. Our findings reveal significant performance variability between LLMs, with DeepSeekV3 emerging as the strongest overall performer, achieving the highest F1 scores in four tasks. Notably, models generally performed better on social media tasks compared to clinical data tasks, suggesting potential domain-specific challenges. GEMMA-3-27B-IT demonstrated exceptionally high recall despite its smaller parameter count, while LLAMA4-109B showed surprisingly underwhelming performance compared to its predecessor LLAMA3-70B, indicating that larger parameter counts do not guarantee improved classification results. We observed distinct precision-recall trade-offs across models, with some favoring sensitivity over specificity and vice versa. These findings highlight the importance of task-specific model selection for healthcare applications, considering the particular data domain and precision-recall requirements rather than model size alone. As healthcare increasingly integrates AI-driven text classification tools, this comprehensive benchmarking provides valuable guidance for model selection and implementation while underscoring the need for continued evaluation and domain adaptation of LLMs in healthcare contexts.
Large open-source projects receive a large number of issues (known as bugs), including software defect (i.e., bug) reports and new feature requests from their user and developer communities at a fast rate. The often limited project resources do not allow them to deal with all issues. Instead, they have to prioritize them according to the project's priorities and the issues' severities. In this paper, we propose a novel approach to automated bug prioritization based on the natural language text of the bug reports that are stored in the open bug repositories of the issue-tracking systems. We conduct topic modeling using a variant of LDA called TopicMiner-MTM and text classification with the BERT large language model to achieve a higher performance level compared to the state-of-the-art. Experimental results using an existing reference dataset containing 85,156 bug reports of the Eclipse Platform project indicate that we outperform existing approaches in terms of Accuracy, Precision, Recall, and F1-measure of the bug report priority prediction.
This paper presents a survey of Abstract Meaning Representation (AMR), a semantic representation framework that captures the meaning of sentences through a graph-based structure. AMR represents sentences as rooted, directed acyclic graphs, where nodes correspond to concepts and edges denote relationships, effectively encoding the meaning of complex sentences. This survey investigates AMR and its extensions, focusing on AMR capabilities. It then explores the parsing (text-to-AMR) and generation (AMR-to-text) tasks by showing traditional, current, and possible futures approaches. It also reviews various applications of AMR including text generation, text classification, and information extraction and information seeking. By analyzing recent developments and challenges in the field, this survey provides insights into future directions for research and the potential impact of AMR on enhancing machine understanding of human language.
Recent advances in large language models (LLMs) have demonstrated strong performance on simple text classification tasks, frequently under zero-shot settings. However, their efficacy declines when tackling complex social media challenges such as propaganda detection, hateful meme classification, and toxicity identification. Much of the existing work has focused on using LLMs to generate synthetic training data, overlooking the potential of LLM-based text preprocessing and semantic augmentation. In this paper, we introduce an approach that prompts LLMs to clean noisy text and provide context-rich explanations, thereby enhancing training sets without substantial increases in data volume. We systematically evaluate on the SemEval 2024 multi-label Persuasive Meme dataset and further validate on the Google Jigsaw toxic comments and Facebook hateful memes datasets to assess generalizability. Our results reveal that zero-shot LLM classification underperforms on these high-context tasks compared to supervised models. In contrast, integrating LLM-based semantic augmentation yields performance on par with approaches that rely on human-annotated data, at a fraction of the cost. These findings underscore the importance of strategically incorporating LLMs into machine learning (ML) pipeline for social media classification tasks, offering broad implications for combating harmful content online.