DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails

• URL: http://arxiv.org/abs/2502.05163v1
• Date: Fri, 07 Feb 2025 18:45:03 GMT
• Title: DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails
• Authors: Yihe Deng, Yu Yang, Junkai Zhang, Wei Wang, Bo Li,
• Abstract summary: We propose a novel two-player Reinforcement Learning framework, where a generator and a guardrail model co-evolve adversarially to produce high-quality synthetic data for multilingual guardrail training. Empirical evaluations show that our model ours outperforms state-of-the-art models, achieving nearly 10% improvement over LlamaGuard3 on English benchmarks.
• Score: 12.621656255109546
• License:
• Abstract: The rapid advancement of large language models (LLMs) has increased the need for guardrail models to ensure responsible use, particularly in detecting unsafe and illegal content. While substantial safety data exist in English, multilingual guardrail modeling remains underexplored due to the scarcity of open-source safety data in other languages. To address this gap, we propose a novel two-player Reinforcement Learning (RL) framework, where a generator and a guardrail model co-evolve adversarially to produce high-quality synthetic data for multilingual guardrail training. We theoretically formalize this interaction as a two-player game, proving convergence to a Nash equilibrium. Empirical evaluations show that our model \ours outperforms state-of-the-art models, achieving nearly 10% improvement over LlamaGuard3 (8B) on English benchmarks while being 4.5x faster at inference with a significantly smaller model (0.5B). We achieve substantial advancements in multilingual safety tasks, particularly in addressing the imbalance for lower-resource languages in a collected real dataset. Ablation studies emphasize the critical role of synthetic data generation in bridging the imbalance in open-source data between English and other languages. These findings establish a scalable and efficient approach to synthetic data generation, paving the way for improved multilingual guardrail models to enhance LLM safety. Code, model, and data will be open-sourced at https://github.com/yihedeng9/DuoGuard.

Related papers

• Enhancing Code Generation for Low-Resource Languages: No Silver Bullet [55.39571645315926]
  Large Language Models (LLMs) rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages. For low-resource languages, the limited availability of such data hampers the models' ability to generalize effectively. We present an empirical study investigating the effectiveness of several approaches for boosting LLMs' performance on low-resource languages.
  arXiv  Detail & Related papers  (2025-01-31T12:23:28Z)
• Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP [13.662528492286528]
  We present a novel cross-lingual vocabulary transfer strategy, trans-tokenization, designed to tackle this challenge and enable more efficient language adaptation. Our approach focuses on adapting a high-resource monolingual LLM to an unseen target language by initializing the token embeddings of the target language using a weighted average of semantically similar token embeddings from the source language. We introduce Hydra LLMs, models with multiple swappable language modeling heads and embedding tables, which further extend the capabilities of our trans-tokenization strategy.
  arXiv  Detail & Related papers  (2024-08-08T08:37:28Z)
• Unlocking the Potential of Model Merging for Low-Resource Languages [66.7716891808697]
  Adapting large language models to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT) We propose model merging as an alternative for low-resource languages, combining models with distinct capabilities into a single model without additional training. Experiments based on Llama-2-7B demonstrate that model merging effectively endows LLMs for low-resource languages with task-solving abilities, outperforming CT-then-SFT in scenarios with extremely scarce data.
  arXiv  Detail & Related papers  (2024-07-04T15:14:17Z)
• Language Portability Strategies for Open-domain Dialogue with Pre-trained Language Models from High to Low Resource Languages [1.7436854281619139]
  We propose a study of linguistic portability strategies of large pre-trained language models (PLMs) used for open-domain dialogue systems. In particular the target low-resource language (L_T) will be simulated with French, as it lacks of task-specific resources.
  arXiv  Detail & Related papers  (2024-07-01T14:20:54Z)
• Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code [123.7406091753529]
  This paper presents Aurora-M, a 15B parameter multilingual open-source model trained on English, Finnish, Hindi, Japanese, Vietnamese, and code. It is the first open-source multilingual model fine-tuned on human-reviewed safety instructions. We evaluate Aurora-M across a wide range of tasks and languages, showcasing its robustness against catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-03-30T15:38:54Z)
• ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval [10.664434993386523]
  Current approaches circumvent the lack of high-quality labeled data in non-English languages. We present a novel modular dense retrieval model that learns from the rich data of a single high-resource language.
  arXiv  Detail & Related papers  (2024-02-23T02:21:24Z)
• Cross-Lingual NER for Financial Transaction Data in Low-Resource Languages [70.25418443146435]
  We propose an efficient modeling framework for cross-lingual named entity recognition in semi-structured text data. We employ two independent datasets of SMSs in English and Arabic, each carrying semi-structured banking transaction information. With access to only 30 labeled samples, our model can generalize the recognition of merchants, amounts, and other fields from English to Arabic.
  arXiv  Detail & Related papers  (2023-07-16T00:45:42Z)
• Extrapolating Multilingual Understanding Models as Multilingual Generators [82.1355802012414]
  This paper explores methods to empower multilingual understanding models the generation abilities to get a unified model. We propose a textbfSemantic-textbfGuided textbfAlignment-then-Denoising (SGA) approach to adapt an encoder to a multilingual generator with a small number of new parameters.
  arXiv  Detail & Related papers  (2023-05-22T15:33:21Z)
• InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective [84.78604733927887]
  Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks. Recent studies show that such BERT-based models are vulnerable facing the threats of textual adversarial attacks. We propose InfoBERT, a novel learning framework for robust fine-tuning of pre-trained language models.
  arXiv  Detail & Related papers  (2020-10-05T20:49:26Z)

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.