Alignment with Preference Optimization Is All You Need for LLM Safety

• URL: http://arxiv.org/abs/2409.07772v1
• Date: Thu, 12 Sep 2024 06:10:15 GMT
• Title: Alignment with Preference Optimization Is All You Need for LLM Safety
• Authors: Reda Alami, Ali Khalifa Almansoori, Ahmed Alzubaidi, Mohamed El Amine Seddik, Mugariya Farooq, Hakim Hacid,
• Abstract summary: We apply various alignment techniques to the Falcon 11B model using safety datasets. We achieve a significant boost in global safety score as measured by LlamaGuard 3 8B, competing with state-of-the-art models. However, this safety improvement comes at the cost of reduced general capabilities, particularly in math.
• Score: 5.063347837245749
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We demonstrate that preference optimization methods can effectively enhance LLM safety. Applying various alignment techniques to the Falcon 11B model using safety datasets, we achieve a significant boost in global safety score (from $57.64\%$ to $99.90\%$) as measured by LlamaGuard 3 8B, competing with state-of-the-art models. On toxicity benchmarks, average scores in adversarial settings dropped from over $0.6$ to less than $0.07$. However, this safety improvement comes at the cost of reduced general capabilities, particularly in math, suggesting a trade-off. We identify noise contrastive alignment (Safe-NCA) as an optimal method for balancing safety and performance. Our study ultimately shows that alignment techniques can be sufficient for building safe and robust models.

Related papers

• SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection [92.38300626647342]
  SEAL learns a data ranker based on the bilevel optimization to up rank the safe and high-quality fine-tuning data and down rank the unsafe or low-quality ones. Models trained with SEAL demonstrate superior quality over multiple baselines, with 8.5% and 9.7% win rate increase compared to random selection.
  arXiv  Detail & Related papers  (2024-10-09T22:24:22Z)
• Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models [94.39278422567955]
  Fine-tuning large language models (LLMs) on human preferences has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during the fine-tuning remains a critical concern. We propose a supervised learning framework called Bi-Factorial Preference Optimization (BFPO) to address this issue.
  arXiv  Detail & Related papers  (2024-08-27T17:31:21Z)
• What Makes and Breaks Safety Fine-tuning? A Mechanistic Study [64.9691741899956]
  Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. We design a synthetic data generation framework that captures salient aspects of an unsafe input. Using this, we investigate three well-known safety fine-tuning methods.
  arXiv  Detail & Related papers  (2024-07-14T16:12:57Z)
• Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints [15.904640266226023]
  We design a safety model that performs credit assignment to assess contributions of partial state-action trajectories on safety. We derive an effective algorithm for optimizing a safe policy using the learned safety model. We devise a method to dynamically adapt the tradeoff coefficient between safety reward and safety compliance.
  arXiv  Detail & Related papers  (2024-05-05T17:27:22Z)
• Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization [3.425378723819911]
  Safe reinforcement learning (Safe RL) refers to a class of techniques that aim to prevent RL algorithms from violating constraints. In this paper, a novel model-free Safe RL algorithm, formulated based on the multi-objective policy optimization framework is introduced.
  arXiv  Detail & Related papers  (2024-02-23T08:58:38Z)
• Iterative Reachability Estimation for Safe Reinforcement Learning [23.942701020636882]
  We propose a new framework, Reachability Estimation for Safe Policy Optimization (RESPO), for safety-constrained reinforcement learning (RL) environments. In the feasible set where there exist violation-free policies, we optimize for rewards while maintaining persistent safety. We evaluate the proposed methods on a diverse suite of safe RL environments from Safety Gym, PyBullet, and MuJoCo.
  arXiv  Detail & Related papers  (2023-09-24T02:36:42Z)
• Efficient Exploration Using Extra Safety Budget in Constrained Policy Optimization [15.483557012655927]
  We propose an algorithm named Constrained Policy Optimization with Extra Safety Budget (ESB-CPO) to strike a balance between the exploration efficiency and the constraints satisfaction. Our method gains remarkable performance improvement under the same cost limit compared with baselines.
  arXiv  Detail & Related papers  (2023-02-28T06:16:34Z)
• Meta-Learning Priors for Safe Bayesian Optimization [72.8349503901712]
  We build on a meta-learning algorithm, F-PACOH, capable of providing reliable uncertainty quantification in settings of data scarcity. As core contribution, we develop a novel framework for choosing safety-compliant priors in a data-riven manner. On benchmark functions and a high-precision motion system, we demonstrate that our meta-learned priors accelerate the convergence of safe BO approaches.
  arXiv  Detail & Related papers  (2022-10-03T08:38:38Z)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems [81.7983463275447]
  Learning-based control algorithms require data collection with abundant supervision for training. We present a new approach for optimal motion planning with safe exploration that integrates chance-constrained optimal control with dynamics learning and feedback control.
  arXiv  Detail & Related papers  (2020-05-09T05:57:43Z)

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.