Beyond Single-Policy: Evaluating Composed Organization-Specific Policy Alignment in LLM Chatbots

• URL: http://arxiv.org/abs/2606.04394v1
• Date: Wed, 03 Jun 2026 03:17:26 GMT
• Title: Beyond Single-Policy: Evaluating Composed Organization-Specific Policy Alignment in LLM Chatbots
• Abstract summary: COPAL is an automated tool for evaluating composed-policy alignment in chatbots.<n>It generates queries that trigger composed-policy failures via empirically derived interaction patterns and explicit handling contracts.
• Score: 17.833004955025125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model chatbots are increasingly deployed in organizational settings such as healthcare, finance, and public services. Evaluating policy alignment is therefore critical to reliable chatbot deployment. By analyzing real-world user queries, we identify composed-policy violation is prevalent in various chatbots but overlooked by existing benchmarks. This paper present COPAL, an automated tool for evaluating composed-policy alignment in chatbots. COPAL efficiently generates queries that trigger composed-policy failures in chatbots via empirically derived interaction patterns and explicit handling contracts. Queries generated by COPAL expose substantial query handling failures: across 9 served models, composed-policy queries yield a 33.1% error rate on average, indicating that composed-policy alignment warrants further investigation.

Related papers

• A Tri-Agent Framework for Evaluating and Aligning Question Clarification Capabilities of Large Language Models [2.332848751256598]
  Large Language Models (LLMs) are increasingly deployed in interactive systems where understanding user intent precisely is paramount.<n>This paper introduces a novel tri-agent framework for the robust evaluation of an LLM's ability to engage in clarifying dialogue.
  arXiv  Detail & Related papers  (2026-09-02T03:33:40Z)
• EMERGE-Policy: A Robot Mind Emerges Beyond a Single Policy [48.898967774856466]
  EMERGE-Policy coordinates both capability invocation and information exchange.<n>Main Agent retains task-level state within an active context window.<n>Role-specific Sub Agents process perception, execution monitoring, verification, and memory consolidation.
  arXiv  Detail & Related papers  (2026-08-30T16:46:06Z)
• End-to-End Chatbot Evaluation with Adaptive Reasoning and Uncertainty Filtering [3.2434811678562685]
  Large language models (LLMs) combined with retrieval augmented generation have enabled the deployment of domain-specific chatbots, but these systems remain prone to generating unsupported or incorrect answers.<n>We propose an end-to-end automatic evaluator designed to substantially reduce human effort.<n>Our system generates Q&A pairs directly from the underlying knowledge base, uses LLMs to judge responses against reference answers, and applies confidence-based filtering to highlight uncertain cases.
  arXiv  Detail & Related papers  (2026-03-11T09:25:35Z)
• Analyzing and Internalizing Complex Policy Documents for LLM Agents [53.14898416858099]
  Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules.<n>This motivates developing internalization methods that embed policy documents into model priors while preserving performance.<n>We introduce CC-Gen, an agentic benchmark generator with Controllable Complexity across four levels.
  arXiv  Detail & Related papers  (2025-10-13T16:30:07Z)
• Mind the Goal: Data-Efficient Goal-Oriented Evaluation of Conversational Agents and Chatbots using Teacher Models [0.0]
  We propose a comprehensive framework for goal-oriented evaluation of multi-agent systems.<n>Our method segments conversations by user goals and evaluates success using all relevant turns.<n>In an enterprise setting, we apply our framework to evaluate AIDA, a zero-to-one employee conversational agent system.
  arXiv  Detail & Related papers  (2025-10-04T06:22:47Z)
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol [83.83217247686402]
  Large Language Models (LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions.<n>Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance.<n>This paper decomposes LLM applications into a three-layer architecture: textbftextitSystem Shell Layer, textbftextitPrompt Orchestration Layer, and textbftextitLLM Inference Core.
  arXiv  Detail & Related papers  (2025-08-28T13:00:28Z)
• A Framework for Auditing Chatbots for Dialect-Based Quality-of-Service Harms [0.6144680854063939]
  We present a framework for auditing large language models (LLM)-based chatbots for dialect bias.<n>We measure the extent to which they produce quality-of-service harms, which occur when systems do not work equally well for different people.<n>Our framework has three key characteristics that make it useful in practice.
  arXiv  Detail & Related papers  (2025-06-04T19:58:51Z)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)
• 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.<n>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.<n>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)
• ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents [52.7201882529976]
  We propose SOP-guided Monte Carlo Tree Search (MCTS) planning framework to enhance controllability of dialogue agents.<n>To enable this, we curate a dataset comprising SOP-annotated multi-scenario dialogues, generated using a semi-automated role-playing system with GPT-4o.<n>We also propose a novel method that integrates Chain of Thought reasoning with supervised fine-tuning for SOP prediction.
  arXiv  Detail & Related papers  (2024-07-04T12:23:02Z)
• SPML: A DSL for Defending Language Models Against Prompt Attacks [4.511923587827302]
  System Prompt Meta Language (SPML) is a domain-specific language for refining prompts and monitoring inputs to large language models (LLMs) SPML actively checks attack prompts, ensuring user inputs align with definitions to prevent malicious execution on the LLM backbone, optimizing costs. We introduce a groundbreaking benchmark with 1.8k system prompts and 20k user inputs, offering the inaugural language and benchmark for chatbots definition evaluation.
  arXiv  Detail & Related papers  (2024-02-19T00:53:48Z)
• PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models [72.57329554067195]
  ProxyQA is an innovative framework dedicated to assessing longtext generation. It comprises in-depth human-curated meta-questions spanning various domains, each accompanied by specific proxy-questions with pre-annotated answers. It assesses the generated content's quality through the evaluator's accuracy in addressing the proxy-questions.
  arXiv  Detail & Related papers  (2024-01-26T18:12:25Z)
• In Generative AI we Trust: Can Chatbots Effectively Verify Political Information? [39.58317527488534]
  This article presents a comparative analysis of the ability of two large language model (LLM)-based chatbots, ChatGPT and Bing Chat, to detect veracity of political information. We use AI auditing methodology to investigate how chatbots evaluate true, false, and borderline statements on five topics: COVID-19, Russian aggression against Ukraine, the Holocaust, climate change, and LGBTQ+ related debates. The results show high performance of ChatGPT for the baseline veracity evaluation task, with 72 percent of the cases evaluated correctly on average across languages without pre-training.
  arXiv  Detail & Related papers  (2023-12-20T15:17:03Z)

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.