Large language models now draft news, legal analyses, and software code with human-level fluency. At the same time, regulations such as the EU AI Act mandate that each synthetic passage carry an imperceptible, machine-verifiable mark for provenance. Conventional logit-based watermarks satisfy this requirement by selecting a pseudorandom green vocabulary at every decoding step and boosting its logits, yet the random split can exclude the highest-probability token and thus erode fluency. WaterMod mitigates this limitation through a probability-aware modular rule. The vocabulary is first sorted in descending model probability; the resulting ranks are then partitioned by the residue rank mod k, which distributes adjacent—and therefore semantically similar—tokens across different classes. A fixed bias of small magnitude is applied to one selected class. In the zero-bit setting (k=2), an entropy-adaptive gate selects either the even or the odd parity as the green list. Because the top two ranks fall into different parities, this choice embeds a detectable signal while guaranteeing that at least one high-probability token remains available for sampling. In the multi-bit regime (k>2), the current payload digit d selects the color class whose ranks satisfy rank mod k = d. Biasing the logits of that class embeds exactly one base-k digit—equivalently log2(k) bits—per decoding step, thereby enabling fine-grained provenance tracing. The same modular arithmetic therefore supports both binary attribution and rich payloads. Experimental results demonstrate that WaterMod consistently attains strong watermark detection performance while maintaining generation quality in both zero-bit and multi-bit settings. This robustness holds across a range of tasks, including natural language generation, mathematical reasoning, and code synthesis.

Implicit hate speech detection is challenging due to its subjectivity and context dependence, with existing models often struggling in outof-domain scenarios. We propose CONELA, a novel data refinement strategy that enhances model performance and generalization by integrating human annotation agreement with model training dynamics. By removing both easy and hard instances from the model’s perspective, while also considering whether humans agree or disagree and retaining ambiguous cases crucial for out-of-distribution generalization, CONELA consistently improves performance across multiple datasets and models. We also observe significant improvements in F1 scores and cross-domain generalization with the use of our CONELA strategy. Addressing data scarcity in smaller datasets, we introduce a weighted loss function and an ensemble strategy incorporating disagreement maximization, effectively balancing learning from limited data. Our findings demonstrate that refining datasets by integrating both model and human perspectives significantly enhances the effectiveness and generalization of implicit hate speech detection models. This approach lays a strong foundation for future research on dataset refinement and model robustness.

Implicit hate speech involves subtle and indirect expressions of prejudice or hostility toward a group.Detecting it is challenging because it relies on nuanced context and implication rather than explicit offensive language.Current approaches rely on contrastive learning, which is shown to be effective on distinguishing hate and non-hate sentences.Humans, however, detect implicit hate speech by first identifying specific targets within the text and subsequently interpreting how these targets relate to their surrounding context.Motivated by this reasoning process, we propose Ample-Hate, a novel approach designed to mirror human inference for implicit hate detection.Am-pleHate identifies explicit targets using a pretrained Named Entity Recognition model and captures implicit target information via [CLS] tokens.It computes attention-based relationships between explicit, implicit targets and sentence context and then, directly injects these relational vectors into the final sentence representation.This amplifies the critical signals of target-context relations for determining implicit hate.Experiments demonstrate that Am-pleHate achieves state-of-the-art performance, outperforming contrastive learning baselines by an average of 82.14% and achieves faster convergence.Qualitative analyses further reveal that attention patterns produced by Am-pleHate closely align with human judgement, underscoring its interpretability and robustness.

Joonghyuk Hahn, Hyeseon Ahn, Jungin Kim, Soohan Lim, Yo-Sub Han. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.