Flexible word boundaries and linguistic obfuscation, particularly slang, challenge precise span-level hate speech detection in Chinese. While benchmarks such as STATE ToxiCN demand the exact extraction of Target-Argument-Hateful-Group quadruples, generative Large Language Models (LLMs) often fail strict boundary constraints. In contrast, discriminative 2D Grid Tagging methods frequently encounter label collisions. To resolve these problems, this study presents a Slang-aware Label-Aligned Framework. A Structural-Semantic Lexicon Fusion (SSLF) module reduces ambiguity by mapping obscure slang to explicit hate semantics. Additionally, the proposed Label-Disentangled Volumetric Tagging (LDVT) projects token interactions into a volumetric space. LDVT uses task-specific branches and dedicated label channels to structurally mitigate feature interference. This approach removes label collisions without heuristic post-processing. Empirical outcomes on STATE ToxiCN indicate a Hard-F1 of 30.09%. This performance is 5.82% higher than the best fine-tuned LLM baseline and confirms the method is effective for exact-match extraction.

Spurious correlations cause deep learning models to rely on predictive shortcuts that hold in the training data but break under distribution shifts, leading to large performance drops for minority groups. Existing strategies often rely on costly group annotations or employ unstable adversarial training. In this paper, we propose Prototype-guided debiasing using Robust Invariant Feature Transformations (PRIFT), a novel framework that mitigates spurious correlations by manipulating latent space geometry. Specifically, we introduce a prototype-guided modeling approach that leverages natural language prompts to represent confounders, transforming abstract biases into interpretable geometric anchors without auxiliary classifiers. Based on these anchors, we introduce a centered projection operator that adaptively purifies representations by removing confounding deviations specific to instances while preserving essential semantic structure. Furthermore, PRIFT can handle confounding factor information at different levels, ranging from true labels to unsupervised latent inference. Experiments on four text classification benchmarks demonstrate the superiority of our method; notably, PRIFT outperforms state-of-the-art baselines and improves worst-group accuracy by over 20% on the CivilComments dataset compared to standard empirical risk minimization.

Natural language processing (NLP) systems often inadvertently encode and amplify social biases through entangled representations of demographic attributes and task-related attributes. To mitigate this, we propose a novel framework that combines causal analysis with practical intervention strategies. The method leverages attribute-specific prompting to isolate sensitive attributes while applying information-theoretic constraints to minimize spurious correlations. Experiments across six language models and two classification tasks demonstrate its effectiveness. We hope this work will provide the NLP community with a causal disentanglement perspective for achieving fairness in NLP systems.