Almost Surely Safe Alignment of Large Language Models at Inference-Time

• URL: http://arxiv.org/abs/2502.01208v2
• Date: Wed, 05 Feb 2025 10:47:19 GMT
• Title: Almost Surely Safe Alignment of Large Language Models at Inference-Time
• Authors: Xiaotong Ji, Shyam Sundhar Ramesh, Matthieu Zimmer, Ilija Bogunovic, Jun Wang, Haitham Bou Ammar,
• Abstract summary: Even highly capable large language models (LLMs) can produce biased or unsafe responses.<n>This paper introduces a novel inference-time alignment approach.<n>We achieve this by framing the safe generation of inference-time responses as a constrained Markov decision process.
• Score: 20.5164976103514
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Even highly capable large language models (LLMs) can produce biased or unsafe responses, and alignment techniques, such as RLHF, aimed at mitigating this issue, are expensive and prone to overfitting as they retrain the LLM. This paper introduces a novel inference-time alignment approach that ensures LLMs generate safe responses almost surely, i.e., with a probability approaching one. We achieve this by framing the safe generation of inference-time responses as a constrained Markov decision process within the LLM's latent space. Crucially, we augment a safety state that tracks the evolution of safety constraints and enables us to demonstrate formal safety guarantees upon solving the MDP in the latent space. Building on this foundation, we propose InferenceGuard, a practical implementation that safely aligns LLMs without modifying the model weights. Empirically, we demonstrate InferenceGuard effectively balances safety and task performance, outperforming existing inference-time alignment methods in generating safe and aligned responses.

Related papers

• Probabilistic Shielding for Safe Reinforcement Learning [51.35559820893218]
  In real-life scenarios, a Reinforcement Learning (RL) agent must often also behave in a safe manner, including at training time. We present a new, scalable method, which enjoys strict formal guarantees for Safe RL. We show that our approach provides a strict formal safety guarantee that the agent stays safe at training and test time.
  arXiv  Detail & Related papers  (2025-03-09T17:54:33Z)
• Toward Responsible Federated Large Language Models: Leveraging a Safety Filter and Constitutional AI [8.643468777944188]
  In FedLLM, client data used for training may contain harmful content, leading to unsafe LLMs that generate harmful responses. To address this issue, we incorporate two well-known RAI methods into FedLLM: the safety filter and constitutional AI. Our experiments demonstrate that these methods significantly enhance the safety of the LLM, achieving over a 20% improvement on AdvBench, a benchmark for evaluating safety performance.
  arXiv  Detail & Related papers  (2025-02-23T19:12:10Z)
• Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging [43.44112117935541]
  Fine-tuning large language models (LLMs) for downstream tasks often leads to safety degradation in safety-aligned LLMs.<n>We propose a method that maintains the inherent safety of LLMs while enhancing their downstream task performance.
  arXiv  Detail & Related papers  (2024-12-27T08:03:22Z)
• Superficial Safety Alignment Hypothesis [8.297367440457508]
  We propose the Superficial Safety Alignment Hypothesis (SSAH), which posits that safety alignment should teach an otherwise unsafe model to choose the correct reasoning direction. We identify four types of attribute-critical components in safety-aligned large language models (LLMs) Our findings show that freezing certain safety-critical components 7.5% during fine-tuning allows the model to retain its safety attributes while adapting to new tasks.
  arXiv  Detail & Related papers  (2024-10-07T19:53:35Z)
• Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models [8.024771725860127]
  Jailbreak attacks manipulate large language models into generating harmful content. Jailbreak Antidote enables real-time adjustment of safety preferences by manipulating a sparse subset of the model's internal states. Our analysis reveals that safety-related information in LLMs is sparsely distributed.
  arXiv  Detail & Related papers  (2024-10-03T08:34:17Z)
• SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering [56.92068213969036]
  Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. Recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue. We propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns.
  arXiv  Detail & Related papers  (2024-08-21T10:01:34Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position. DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)
• SLM as Guardian: Pioneering AI Safety with Small Language Models [6.799423428734095]
  Internalizing safeguard features into larger models brought challenges of higher training cost and unintended degradation of helpfulness. In this paper, we leverage a smaller LLM for both harmful query detection and safeguard response generation. We demonstrate the effectiveness of our approach, providing on par or surpassing harmful query detection and safeguard response performance compared to the publicly available LLMs.
  arXiv  Detail & Related papers  (2024-05-30T08:03:15Z)
• Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching [74.62818936088065]
  textscSafePatching is a novel framework for comprehensive PSA.<n>textscSafePatching achieves a more comprehensive PSA than baseline methods.<n>textscSafePatching demonstrates its superiority in continual PSA scenarios.
  arXiv  Detail & Related papers  (2024-05-22T16:51:07Z)
• Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models? [2.089112028396727]
  This study explores whether Large Language Models can produce safe, unbiased outputs without sacrificing knowledge or comprehension.<n>We introduce the Safe and Responsible Large Language Model (textbfSR$_textLLM$)<n>Experiments on our specialized dataset and out-of-distribution test sets reveal that textbfSR$_textLLM$ effectively reduces biases while preserving knowledge integrity.
  arXiv  Detail & Related papers  (2024-04-01T18:10:05Z)
• SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models [107.82336341926134]
  SALAD-Bench is a safety benchmark specifically designed for evaluating Large Language Models (LLMs) It transcends conventional benchmarks through its large scale, rich diversity, intricate taxonomy spanning three levels, and versatile functionalities.
  arXiv  Detail & Related papers  (2024-02-07T17:33:54Z)
• The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness [56.174255970895466]
  Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications. This paper presents Safety and Over-Defensiveness Evaluation (SODE) benchmark.
  arXiv  Detail & Related papers  (2023-12-30T17:37:06Z)

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.