AI Policy Projector: Grounding LLM Policy Design in Iterative Mapmaking

• URL: http://arxiv.org/abs/2409.18203v1
• Date: Thu, 26 Sep 2024 18:34:16 GMT
• Title: AI Policy Projector: Grounding LLM Policy Design in Iterative Mapmaking
• Abstract summary: We introduce an AI policy design process inspired by mapmaking. Policy Projector supports interactive policy authoring using LLM classification and steering. In an evaluation with 12 AI safety experts, our system helps policy designers to address problematic model behaviors.
• Score: 34.86215885364356
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Whether a large language model policy is an explicit constitution or an implicit reward model, it is challenging to assess coverage over the unbounded set of real-world situations that a policy must contend with. We introduce an AI policy design process inspired by mapmaking, which has developed tactics for visualizing and iterating on maps even when full coverage is not possible. With Policy Projector, policy designers can survey the landscape of model input-output pairs, define custom regions (e.g., "violence"), and navigate these regions with rules that can be applied to LLM outputs (e.g., if output contains "violence" and "graphic details," then rewrite without "graphic details"). Policy Projector supports interactive policy authoring using LLM classification and steering and a map visualization reflecting the policy designer's work. In an evaluation with 12 AI safety experts, our system helps policy designers to address problematic model behaviors extending beyond an existing, comprehensive harm taxonomy.

Related papers

• PolicyMem: Geometric Policy Memory for LLM Governance [72.04962480384322]
  We introduce PolicyMem, a geometric policy memory that externalizes natural-language policies as reusable geometric memory objects.<n>A memory writer compiles natural-language policies into policy memory slots, and query-response pairs read the policy memory through projection energy.<n>The resulting policy-evidence profile directly mediates the safety verdict and is reused for policy attribution and post-intervention verification.
  arXiv  Detail & Related papers  (2026-09-12T06:07:43Z)
• READ: Learning Risk-Informed Fields for End-to-End Autonomous Driving [24.54780591783853]
  We introduce READ, a framework that learns an explicit, planning-aligned risk representation from complementary geometric and behavioral constraints.<n> READ instantiates this representation as a continuoustemporal field, enabling differentiable queries along candidate trajectories.<n> Experiments on NAVSIM show consistent gains across matched end-to-end backbones and strong performance in a VLA setting.
  arXiv  Detail & Related papers  (2026-09-11T02:40:51Z)
• Learning Policy Representations for Steerable Behavior Synthesis [80.4542176039074]
  Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering at test time.<n>We show that these representations can be approximated uniformly for a range of policies using a set-based architecture.<n>We use variational generative approach to induce a smooth latent space, and further shape it with contrastive learning so that latent distances align with differences in value functions.
  arXiv  Detail & Related papers  (2026-01-29T21:52:06Z)
• Policy-Conditioned Policies for Multi-Agent Task Solving [53.67744322553693]
  In this work, we propose a paradigm shift that bridges the gap by representing policies as human-interpretable source code.<n>We reformulate the learning problem by utilizing Large Language Models (LLMs) as approximate interpreters.<n>We formalize this process as textitProgrammatic Iterated Best Response (PIBR), an algorithm where the policy code is optimized by textual gradients.
  arXiv  Detail & Related papers  (2025-12-24T07:42:10Z)
• Towards Harnessing the Power of LLMs for ABAC Policy Mining [0.0468771281852187]
  This paper presents an empirical investigation into the capabilities of Large Language Models (LLMs) to perform automated Attribute-based Access Control (ABAC) policy mining.<n>We evaluate the performance of some of the state-of-the-art LLMs, specifically Google Gemini (Flash and Pro) and OpenAI ChatGPT, as potential policy mining engines.
  arXiv  Detail & Related papers  (2025-11-22T15:49:36Z)
• Dense Policy: Bidirectional Autoregressive Learning of Actions [51.60428100831717]
  This paper introduces a bidirectionally expanded learning approach, termed Dense Policy, to establish a new paradigm for autoregressive policies in action prediction. It employs a lightweight encoder-only architecture to iteratively unfold the action sequence from an initial single frame into the target sequence in a coarse-to-fine manner. Experiments validate that our dense policy has superior autoregressive learning capabilities and can surpass existing holistic generative policies.
  arXiv  Detail & Related papers  (2025-03-17T14:28:08Z)
• Few-shot Policy (de)composition in Conversational Question Answering [54.259440408606515]
  We propose a neuro-symbolic framework to detect policy compliance using large language models (LLMs) in a few-shot setting. We show that our approach soundly reasons about policy compliance conversations by extracting sub-questions to be answered, assigning truth values from contextual information, and explicitly producing a set of logic statements from the given policies. We apply this approach to the popular PCD and conversational machine reading benchmark, ShARC, and show competitive performance with no task-specific finetuning.
  arXiv  Detail & Related papers  (2025-01-20T08:40:15Z)
• Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues [31.92843134331582]
  We introduce a novel dialogue policy planning framework, LDPP. It fully automates the process from mining policies in dialogue records to learning policy planning. Our experiments demonstrate that LDPP outperforms existing methods on two proactive scenarios.
  arXiv  Detail & Related papers  (2024-12-19T07:06:01Z)
• ForPKG-1.0: A Framework for Constructing Forestry Policy Knowledge Graph and Application Analysis [0.0]
  A policy knowledge graph can provide decision support for tasks such as project compliance, policy analysis, and intelligent question answering. This paper, focusing on the forestry field, designs a complete policy knowledge graph construction framework. The knowledge graph resource will be released on an open-source platform and can serve as the basic knowledge base for forestry policy-related intelligent systems.
  arXiv  Detail & Related papers  (2024-11-17T14:45:52Z)
• Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
  Large language models (LLMs) have transformed the development of embodied intelligence. This paper uncovers a significant backdoor security threat within this process. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
  arXiv  Detail & Related papers  (2024-08-06T01:20:12Z)
• Towards Interpretable Foundation Models of Robot Behavior: A Task Specific Policy Generation Approach [1.7205106391379026]
  Foundation models are a promising path toward general-purpose and user-friendly robots. In particular, the lack of modularity between tasks means that when model weights are updated, the behavior in other, unrelated tasks may be affected. We present an alternative approach to the design of robot foundation models, which generates stand-alone, task-specific policies.
  arXiv  Detail & Related papers  (2024-07-10T21:55:44Z)
• Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization [53.510942601223626]
  Large Language Models (LLMs) exhibit robust problem-solving capabilities for diverse tasks. These task solvers necessitate manually crafted prompts to inform task rules and regulate behaviors. We propose Agent-Pro: an LLM-based Agent with Policy-level Reflection and Optimization.
  arXiv  Detail & Related papers  (2024-02-27T15:09:20Z)
• Residual Q-Learning: Offline and Online Policy Customization without Value [53.47311900133564]
  Imitation Learning (IL) is a widely used framework for learning imitative behavior from demonstrations. We formulate a new problem setting called policy customization. We propose a novel framework, Residual Q-learning, which can solve the formulated MDP by leveraging the prior policy.
  arXiv  Detail & Related papers  (2023-06-15T22:01:19Z)
• Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation [26.47544415550067]
  We propose to distill a state-based motion planner augmented policy to a visual control policy. We evaluate our method on three manipulation tasks in obstructed environments. Our framework is highly sample-efficient and outperforms the state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2021-11-11T18:52:00Z)
• Intrusion Prevention through Optimal Stopping [0.0]
  We study automated intrusion prevention using reinforcement learning. We show that our approach can produce effective defender policies for a practical IT infrastructure of limited size.
  arXiv  Detail & Related papers  (2021-10-30T17:03:28Z)
• Building a Foundation for Data-Driven, Interpretable, and Robust Policy Design using the AI Economist [67.08543240320756]
  We show that the AI Economist framework enables effective, flexible, and interpretable policy design using two-level reinforcement learning and data-driven simulations. We find that log-linear policies trained using RL significantly improve social welfare, based on both public health and economic outcomes, compared to past outcomes.
  arXiv  Detail & Related papers  (2021-08-06T01:30:41Z)
• Goal-Conditioned Reinforcement Learning with Imagined Subgoals [89.67840168694259]
  We propose to incorporate imagined subgoals into policy learning to facilitate learning of complex tasks. Imagined subgoals are predicted by a separate high-level policy, which is trained simultaneously with the policy and its critic. We evaluate our approach on complex robotic navigation and manipulation tasks and show that it outperforms existing methods by a large margin.
  arXiv  Detail & Related papers  (2021-07-01T15:30:59Z)
• Policy Supervectors: General Characterization of Agents by their Behaviour [18.488655590845163]
  We propose policy supervectors for characterizing agents by the distribution of states they visit. Policy supervectors can characterize policies regardless of their design philosophy and scale to thousands of policies on a single workstation machine. We demonstrate method's applicability by studying the evolution of policies during reinforcement learning, evolutionary training and imitation learning.
  arXiv  Detail & Related papers  (2020-12-02T14:43:16Z)
• Continuous Action Reinforcement Learning from a Mixture of Interpretable Experts [35.80418547105711]
  We propose a policy scheme that retains a complex function approxor for its internal value predictions but constrains the policy to have a concise, hierarchical, and human-readable structure. The main technical contribution of the paper is to address the challenges introduced by this non-differentiable state selection procedure.
  arXiv  Detail & Related papers  (2020-06-10T16:02:08Z)
• Preventing Imitation Learning with Adversarial Policy Ensembles [79.81807680370677]
  Imitation learning can reproduce policies by observing experts, which poses a problem regarding policy privacy. How can we protect against external observers cloning our proprietary policies? We introduce a new reinforcement learning framework, where we train an ensemble of near-optimal policies.
  arXiv  Detail & Related papers  (2020-01-31T01:57:16Z)

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.