Adversarial Alignment: Ensuring Value Consistency in Large Language Models for Sensitive Domains

• URL: http://arxiv.org/abs/2601.13137v2
• Date: Thu, 22 Jan 2026 10:39:44 GMT
• Title: Adversarial Alignment: Ensuring Value Consistency in Large Language Models for Sensitive Domains
• Authors: Yuan Gao, Zhigang Liu, Xinyu Yao, Bo Chen, Xiaobing Zhao,
• Abstract summary: We propose an adversarial alignment framework, which enhances the value consistency of the model in sensitive domains.<n>In adversarial training, we use the Attacker to generate controversial queries, the Actor to generate responses with value consistency, and the Critic to filter and ensure response quality.<n>The experimental results show that VC-LLM performs better than the existing mainstream models in both Chinese and English tests.
• Score: 9.949435875140523
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the wide application of large language models (LLMs), the problems of bias and value inconsistency in sensitive domains have gradually emerged, especially in terms of race, society and politics. In this paper, we propose an adversarial alignment framework, which enhances the value consistency of the model in sensitive domains through continued pre-training, instruction fine-tuning and adversarial training. In adversarial training, we use the Attacker to generate controversial queries, the Actor to generate responses with value consistency, and the Critic to filter and ensure response quality. Furthermore, we train a Value-Consistent Large Language Model, VC-LLM, for sensitive domains, and construct a bilingual evaluation dataset in Chinese and English. The experimental results show that VC-LLM performs better than the existing mainstream models in both Chinese and English tests, verifying the effectiveness of the method. Warning: This paper contains examples of LLMs that are offensive or harmful in nature.

Related papers

• IndicEval: A Bilingual Indian Educational Evaluation Framework for Large Language Models [0.0]
  This paper introduces IndicEval, a scalable benchmarking platform to assess large language models (LLMs) performance.<n>IndicEval grounds evaluation in real examination standards, enabling realistic measurement of reasoning, domain knowledge, and bilingual adaptability.<n>Experiments conducted on Gemini 2.0 Flash, GPT-4, Claude, and LLaMA 3-70B reveal three major findings.
  arXiv  Detail & Related papers  (2026-02-18T13:55:57Z)
• Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation [49.2073409243885]
  Large language models (LLMs) excel at generating English counterfactuals and demonstrate multilingual proficiency.<n>We conduct automatic evaluations on both directly generated counterfactuals in the target languages and those derived via English translation across six languages.<n>We identify and categorize four main types of errors that consistently appear in the generated counterfactuals across languages.
  arXiv  Detail & Related papers  (2026-01-01T08:53:49Z)
• LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs [73.27182315028021]
  LANPO is a framework that cleanly separates the roles of feedback: language guides exploration, while numerical rewards drive optimization.<n>Our work provides a robust method for integrating historical experiences into the LLM RL loop, creating more effective and data-efficient learning agents.
  arXiv  Detail & Related papers  (2025-10-18T15:51:19Z)
• On the Entity-Level Alignment in Crosslingual Consistency [62.33186691736433]
  SubSub and SubInj integrate English translations of subjects into prompts across languages, leading to substantial gains in factual recall accuracy and consistency.<n>These interventions reinforce the entity representation alignment in the conceptual space through model's internal pivot-language processing.
  arXiv  Detail & Related papers  (2025-10-11T16:26:50Z)
• Influence Guided Context Selection for Effective Retrieval-Augmented Generation [23.188397777606095]
  Retrieval-Augmented Generation (RAG) addresses large language model (LLM) hallucinations by grounding responses in external knowledge.<n>Existing approaches attempt to improve performance through context selection based on predefined context quality assessment metrics.<n>We reconceptualize context quality assessment as an inference-time data valuation problem and introduce the Contextual Influence Value (CI value)<n>This novel metric quantifies context quality by measuring the performance degradation when removing each context from the list.
  arXiv  Detail & Related papers  (2025-09-21T07:19:09Z)
• Adversarial Attack Classification and Robustness Testing for Large Language Models for Code [19.47426054151291]
  This study investigates how adversarial perturbations in natural language inputs affect Large Language Models for Code (LLM4Code)<n>It examines the effects of perturbations at the character, word, and sentence levels to identify the most impactful vulnerabilities.
  arXiv  Detail & Related papers  (2025-06-09T17:02:29Z)
• Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge [1.1666234644810893]
  Small models outperform larger ones in safety, suggesting that training and architecture may matter more than scale.<n>No model is fully robust to adversarial elicitation, with jailbreak attacks using low-resource languages or refusal suppression proving effective.
  arXiv  Detail & Related papers  (2025-04-10T16:00:59Z)
• Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories [14.605576275135522]
  evaluating value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts.<n>We propose an upgraded value alignment benchmark that moves beyond single-sentence prompts by incorporating multi-turn dialogues and narrative-based scenarios.
  arXiv  Detail & Related papers  (2025-03-28T03:31:37Z)
• Harnessing the Intrinsic Knowledge of Pretrained Language Models for Challenging Text Classification Settings [5.257719744958367]
  This thesis explores three challenging settings in text classification by leveraging the intrinsic knowledge of pretrained language models (PLMs) We develop models that utilize features based on contextualized word representations from PLMs, achieving performance that rivals or surpasses human accuracy. Lastly, we tackle the sensitivity of large language models to in-context learning prompts by selecting effective demonstrations.
  arXiv  Detail & Related papers  (2024-08-28T09:07:30Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models [86.02610674750345]
  Adversarial GLUE (AdvGLUE) is a new multi-task benchmark to explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks. We apply 14 adversarial attack methods to GLUE tasks to construct AdvGLUE, which is further validated by humans for reliable annotations. All the language models and robust training methods we tested perform poorly on AdvGLUE, with scores lagging far behind the benign accuracy.
  arXiv  Detail & Related papers  (2021-11-04T12:59:55Z)
• Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension [96.62963688510035]
  Reading comprehension models often overfit to nuances of training datasets and fail at adversarial evaluation. We present several effective adversaries and automated data augmentation policy search methods with the goal of making reading comprehension models more robust to adversarial evaluation.
  arXiv  Detail & Related papers  (2020-04-13T17:20:08Z)

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.