A Dual-Hypothesis Reasoning Framework for LLM Guardrails

• URL: http://arxiv.org/abs/2607.17575v1
• Date: Mon, 20 Jul 2026 05:42:25 GMT
• Title: A Dual-Hypothesis Reasoning Framework for LLM Guardrails
• Abstract summary: ARBITER is a reasoning method for LLM guardrails that explicitly considers both safe and unsafe interpretations of a prompt.<n>ARBITER uses a cost-effective self-generation strategy for reasoning traces and LoRA-based parameter-efficient fine-tuning.<n>ARBITER provides faithful evidence-phrase explanations for unsafe decisions, enabling a more transparent and interpretable guardrail method.
• Score: 20.383868120117565
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardrails that explicitly considers both safe and unsafe interpretations of a prompt before making a safety decision, and (ii) multi-component supervised fine-tuning (MC-SFT), a structured training loss for reasoning-based guardrails that decomposes LLM outputs into logical components and weights them according to their importance. Existing reasoning-based guardrails often rely on expensive procedures, such as generating reasoning traces using larger or closed-source teacher models and applying full-parameter fine-tuning. In contrast, ARBITER uses a cost-effective self-generation strategy for reasoning traces and LoRA-based parameter-efficient fine-tuning while still achieving better performance than these expensive approaches. Additionally, ARBITER provides faithful evidence-phrase explanations for unsafe decisions, enabling a more transparent and interpretable guardrail method. Experiments on three safety moderation benchmarks show that ARBITER outperforms existing reasoning-based and non-reasoning guardrail baselines, with clear gains in out-of-domain evaluations.

Related papers

• Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence [70.8951332710039]
  Multimodal large language models (MLLMs) have demonstrated significant potential in complex spatial scene understanding and reasoning tasks.<n>However, their open-ended reasoning process is prone to decision errors and error accumulation, leading to instability in answer quality.<n>We propose an advantage-guided gating framework that dynamically intervenes in and corrects deviations during the reasoning process.
  arXiv  Detail & Related papers  (2026-08-08T07:46:04Z)
• LaRec: Unleashing LLM-based Latent Reasoning for Generative Recommendation [27.643675369277858]
  latent reasoning aims to balance efficiency by thinking within a continuous latent space.<n>$LaRec$ is an efficient generative recommendation framework designed to unleash the potential of latent reasoning.<n> Experiments on multiple datasets show that $LaRec$ significantly outperforms existing baselines with comparable efficiency.
  arXiv  Detail & Related papers  (2026-07-27T16:14:57Z)
• DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail [19.59614205209542]
  We present DT-Guard, a content safety guardrail model based on a Reasoning-Active Training, Reasoning-Free Inference paradigm.<n>The key idea is to use reasoning supervision during training while emitting only structured safety labels at inference time.
  arXiv  Detail & Related papers  (2026-07-07T14:25:05Z)
• LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval [74.72139580745511]
  LaSER is a novel self-distillation framework that internalizes explicit reasoning into the latent space of retrievers.<n>Our method successfully combines the reasoning depth of explicit CoT pipelines with the inference efficiency of standard dense retrievers.
  arXiv  Detail & Related papers  (2026-03-02T04:11:18Z)
• Reinforced Efficient Reasoning via Semantically Diverse Exploration [73.41112984160992]
  Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs)<n>We propose reinforced efficient reasoning via semantically diverse explorations, i.e., ROSE, for LLMs.<n>Our method incorporates a semantic-entropy-based branching strategy and an $varepsilon$-exploration mechanism.
  arXiv  Detail & Related papers  (2026-01-08T15:56:44Z)
• RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts [39.58550043591753]
  External LLM-based guardrail models have emerged as a popular solution to screen unsafe inputs and outputs.<n>We investigated how robust LLM-based guardrails are against additional information embedded in the context.
  arXiv  Detail & Related papers  (2025-10-06T19:20:43Z)
• Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention [53.25106308403173]
  We show that existing methods overlook the unique significance of safe reasoning, undermining their trustworthiness and posing potential risks in applications if unsafe reasoning is accessible for and exploited by malicious users.<n>We propose Intervened Preference Optimization (IPO), an alignment method that enforces safe reasoning by substituting compliance steps with safety triggers and constructing pairs for preference learning with strong signals.
  arXiv  Detail & Related papers  (2025-09-29T07:41:09Z)
• Revisiting LLM Reasoning via Information Bottleneck [57.519119962528166]
  Large language models (LLMs) have recently demonstrated remarkable progress in reasoning capabilities through reinforcement learning with verifiable rewards (RLVR)<n>We present a theoretical characterization of LLM reasoning grounded in information bottleneck (IB) principle.<n>We propose IB-aware reasoning optimization (IBRO), a framework that encourages reasoning trajectories to be both informative about the final correct answer and generalizable.
  arXiv  Detail & Related papers  (2025-07-24T13:14:25Z)
• ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning [64.32925552574115]
  ARMOR is a large language model that analyzes jailbreak strategies and extracts the core intent.<n> ARMOR achieves state-of-the-art safety performance, with an average harmful rate of 0.002 and an attack success rate of 0.06 against advanced optimization-based jailbreaks.
  arXiv  Detail & Related papers  (2025-07-14T09:05:54Z)
• Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation [9.282278040339138]
  $textbfR2Rec$ is a reasoning-enhanced recommendation framework.<n>It samples interaction chains from the user-item graph and converts them into structured interaction-of-thoughts.
  arXiv  Detail & Related papers  (2025-06-05T14:16:44Z)
• Reinforced Latent Reasoning for LLM-based Recommendation [92.56166822197919]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks.<n>Existing methods typically rely on fine-tuning with explicit chain-of-thought (CoT) data.<n>In this work, we explore an alternative approach that shifts from explicit CoT reasoning to compact, information-dense latent reasoning.
  arXiv  Detail & Related papers  (2025-05-25T11:03:45Z)
• $R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning [8.408258504178718]
  Existing guardrail models treat various safety categories independently and fail to explicitly capture the intercorrelations among them. We propose $R2$-Guard, a robust reasoning enabled LLM guardrail via knowledge-enhanced logical reasoning. $R2$-Guard significantly surpasses SOTA method LlamaGuard by 30.2% on ToxicChat and by 59.5% against jailbreaking attacks.
  arXiv  Detail & Related papers  (2024-07-08T02:15:29Z)

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.