TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts

• URL: http://arxiv.org/abs/2604.16542v1
• Date: Fri, 17 Apr 2026 01:55:37 GMT
• Title: TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts
• Abstract summary: Safety guardrails have become an active area of research in AI safety, aimed at ensuring the appropriate behavior of large language models (LLMs)<n>Existing research lacks consideration of nuances across linguistic and cultural contexts, resulting in a gap between reported performance and in-the-wild effectiveness.<n>This paper proposes an approach to optimize guardrail models for a designated linguistic context by leveraging a curated dataset tailored to local linguistic characteristics.
• Score: 0.1019561860229868
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safety guardrails have become an active area of research in AI safety, aimed at ensuring the appropriate behavior of large language models (LLMs). However, existing research lacks consideration of nuances across linguistic and cultural contexts, resulting in a gap between reported performance and in-the-wild effectiveness. To address this issue, this paper proposes an approach to optimize guardrail models for a designated linguistic context by leveraging a curated dataset tailored to local linguistic characteristics, targeting the Taiwan linguistic context as a representative example of localized deployment challenges. The proposed approach yields TWGuard, a linguistic context-optimized guardrail model that achieves a huge gain (+0.289 in F1) compared to the foundation model and significantly outperforms the strongest baseline in practical use (-0.037 in false positive rate, a 94.9\% reduction). Together, this work lays a foundation for regional communities to establish AI safety standards grounded in their own linguistic contexts, rather than accepting boundaries imposed by dominant languages. The inadequacy of the latter is reconfirmed by our findings.

Related papers

• Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs [51.56484100374058]
  Large Language Models (LLMs) demonstrate remarkable multilingual fluency, but their internal knowledge representations remain disproportionately biased toward high-resource languages.<n>We investigate whether these biases can be mitigated at inference time, forcing an English-prompted model to answer as if it were queried in target languages.<n>Experiments on Gemma 3 12B Instruct reveal persona prompting to be the strongest overall intervention, balancing efficacy, safety, and out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-07-21T16:15:05Z)
• IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages [2.584263027095689]
  We introduce IndicGuard, a multilingual safety guard model and dataset for Indic languages.<n>We construct a high-volume, culturally nuanced safety dataset encompassing ten major Indic languages.<n>We fine-tune a 4B- parameter instruction-tuned model based on Gemma-3-4B-IT to serve as a multilingual safety guardrail.
  arXiv  Detail & Related papers  (2026-06-22T04:36:57Z)
• STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning [80.78140312980484]
  We propose language-driven stepwise trajectory redirection, termed as STRIDE.<n>We co-train a generator and a generative verifier using only outcome-based rewards, eliminating external annotations.<n> Experiments on diverse reasoning benchmarks show that STRIDE significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-13T11:04:31Z)
• Multilingual Refusal Alignment for Safer Large Language Models [53.64286756804503]
  We investigate whether single-language alignment transfers cross-lingually, how language consistency is preserved during training, and the resulting trade-offs with general knowledge capabilities.<n>We introduce RefusEU, a novel refusal alignment dataset covering 12 European languages, including a dedicated test set for evaluating current state-of-the-art models.<n>Our controlled Direct Preference Optimization (DPO) experiments provide two key insights: aligning models exclusively in English is insufficient to ensure cross-lingual safety, even for the same harm categories, whereas training on multilingual datasets can improve safety without degrading general performance, as measured by the Global MMLU benchmark.
  arXiv  Detail & Related papers  (2026-04-24T09:29:14Z)
• LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety [88.98698230989186]
  Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities in low-resource languages.<n>We attribute this gap to a mismatch between language-agnostic semantic understanding ability and language-dominant safety alignment biased toward high-resource languages.<n>We propose Language-Agnostic Semantic Alignment (LASA), which anchors safety alignment directly in semantic bottlenecks.
  arXiv  Detail & Related papers  (2026-04-13T15:59:50Z)
• CREST: Universal Safety Guardrails Through Cluster-Guided Cross-Lingual Transfer [0.5729426778193399]
  CREST is a parameter-efficient multilingual safety classification model that supports 100 languages with only 0.5B parameters.<n>By training on a strategically chosen subset of only 13 high-resource languages, our model utilizes cluster-based cross-lingual transfer.<n>This approach addresses the challenge of limited training data in low-resource settings.
  arXiv  Detail & Related papers  (2025-12-02T12:41:48Z)
• MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety [56.77103365251923]
  Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking.<n>This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is often limited.<n>We introduce a multilingual guardrail with reasoning for prompt classification.
  arXiv  Detail & Related papers  (2025-04-21T17:15:06Z)
• Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents [13.63944785085617]
  Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications.<n>Inspired by a paradigm shift to first curate data before tuning, we introduce a new framework for safe language alignment.<n>We formalize the framework within a Constrained Markov Decision Process (CMDP) and validate it via a text-based navigation environment.
  arXiv  Detail & Related papers  (2025-04-04T05:26:28Z)
• Enhancing adversarial robustness in Natural Language Inference using explanations [41.46494686136601]
  We cast the spotlight on the underexplored task of Natural Language Inference (NLI) We validate the usage of natural language explanation as a model-agnostic defence strategy through extensive experimentation. We research the correlation of widely used language generation metrics with human perception, in order for them to serve as a proxy towards robust NLI models.
  arXiv  Detail & Related papers  (2024-09-11T17:09:49Z)
• Sharif-STR at SemEval-2024 Task 1: Transformer as a Regression Model for Fine-Grained Scoring of Textual Semantic Relations [2.3145162209342685]
  This paper investigates the investigation of sentence-level STR within Track A (Supervised) by leveraging fine-tuning techniques on the RoBERTa transformer. Our findings indicate promising advancements in STR performance, particularly in Latin languages. However, our approach encounters challenges in languages like Arabic, where we observed a correlation of only 0.38, resulting in a 20th rank.
  arXiv  Detail & Related papers  (2024-07-17T09:25:18Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.