Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration

• URL: http://arxiv.org/abs/2505.17066v2
• Date: Fri, 27 Jun 2025 10:04:25 GMT
• Title: Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration
• Authors: Tatia Tsmindashvili, Ana Kolkhidashvili, Dachi Kurtskhalia, Nino Maghlakelidze, Elene Mekvabishvili, Guram Dentoshvili, Orkhan Shamilov, Zaal Gachechiladze, Steven Saporta, David Dachi Choladze,
• Abstract summary: Archias is an expert model adept at distinguishing between in-domain and out-of-domain communications.<n>Archias classifies user inquiries into several categories: in-domain (specifically for the automotive industry), malicious questions, price injections, prompt injections, and out-of-domain examples.<n>Archias can be adjusted, fine-tuned, and used for many different purposes due to its small size.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Using LLMs in a production environment presents security challenges that include vulnerabilities to jailbreaks and prompt injections, which can result in harmful outputs for humans or the enterprise. The challenge is amplified when working within a specific domain, as topics generally accepted for LLMs to address may be irrelevant to that field. These problems can be mitigated, for example, by fine-tuning large language models with domain-specific and security-focused data. However, these alone are insufficient, as jailbreak techniques evolve. Additionally, API-accessed models do not offer the flexibility needed to tailor behavior to industry-specific objectives, and in-context learning is not always sufficient or reliable. In response to these challenges, we introduce Archias, an expert model adept at distinguishing between in-domain and out-of-domain communications. Archias classifies user inquiries into several categories: in-domain (specifically for the automotive industry), malicious questions, price injections, prompt injections, and out-of-domain examples. Our methodology integrates outputs from the expert model (Archias) into prompts, which are then processed by the LLM to generate responses. This method increases the model's ability to understand the user's intention and give appropriate answers. Archias can be adjusted, fine-tuned, and used for many different purposes due to its small size. Therefore, it can be easily customized to the needs of any industry. To validate our approach, we created a benchmark dataset for the automotive industry. Furthermore, in the interest of advancing research and development, we release our benchmark dataset to the community.

Related papers

• Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs [60.881609323604685]
  Large Language Models (LLMs) accessed via black-box APIs introduce a trust challenge.<n>Users pay for services based on advertised model capabilities.<n> providers may covertly substitute the specified model with a cheaper, lower-quality alternative to reduce operational costs.<n>This lack of transparency undermines fairness, erodes trust, and complicates reliable benchmarking.
  arXiv  Detail & Related papers  (2025-04-07T03:57:41Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection [0.0]
  Large Language Models (LLMs) are prone to off-topic misuse, where users may prompt these models to perform tasks beyond their intended scope.<n>Current guardrails suffer from high false-positive rates, limited adaptability, and the impracticality of requiring real-world data that is not available in pre-production.<n>We introduce a flexible, data-free guardrail development methodology that addresses these challenges.
  arXiv  Detail & Related papers  (2024-11-20T00:31:23Z)
• Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs [64.83462841029089]
  We introduce an efficient merging-based alignment method called textscMergeAlign that interpolates the domain and alignment vectors, creating safer domain-specific models. We apply textscMergeAlign on Llama3 variants that are experts in medicine and finance, obtaining substantial alignment improvements with minimal to no degradation on domain-specific benchmarks.
  arXiv  Detail & Related papers  (2024-11-11T09:32:20Z)
• Exploring Language Model Generalization in Low-Resource Extractive QA [57.14068405860034]
  We investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift.<n>We devise a series of experiments to explain the performance gap empirically.
  arXiv  Detail & Related papers  (2024-09-27T05:06:43Z)
• A New Pipeline For Generating Instruction Dataset via RAG and Self Fine-Tuning [0.0]
  This research proposes a pipeline to construct high-quality instruction datasets for fine-tuning on specific domains. By ingesting domain-specific documents, the pipeline generates relevant and contextually appropriate instructions. As a case study, we apply this approach to the domain of psychiatry, a field requiring specialized knowledge and sensitive handling of patient information.
  arXiv  Detail & Related papers  (2024-08-12T03:52:11Z)
• Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations [50.81844184210381]
  We propose a general paradigm that augments large language models with DOmain-specific KnowledgE to enhance their performance on practical applications, namely DOKE. This paradigm relies on a domain knowledge extractor, working in three steps: 1) preparing effective knowledge for the task; 2) selecting the knowledge for each specific sample; and 3) expressing the knowledge in an LLM-understandable way.
  arXiv  Detail & Related papers  (2023-11-16T07:09:38Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning [79.53130089003986]
  Large Language Models (LLMs) have become a feasible solution for handling tasks in various domains. In this paper, we introduce how to fine-tune a LLM model that can be privately deployed for content moderation.
  arXiv  Detail & Related papers  (2023-10-05T09:09:44Z)
• Open Sesame! Universal Black Box Jailbreaking of Large Language Models [0.0]
  Large language models (LLMs) are designed to provide helpful and safe responses. LLMs often rely on alignment techniques to align with user intent and social guidelines. We introduce a novel approach that employs a genetic algorithm (GA) to manipulate LLMs when model architecture and parameters are inaccessible.
  arXiv  Detail & Related papers  (2023-09-04T08:54:20Z)
• Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering [36.31193273252256]
  Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks. But its performance in real industrial domain-specific scenarios is average due to its lack of specific domain knowledge. We provide a benchmark Question Answering (QA) dataset named MSQA, centered around Microsoft products and IT technical problems encountered by customers.
  arXiv  Detail & Related papers  (2023-05-19T09:23:25Z)

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.