RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2604.17301v1
• Date: Sun, 19 Apr 2026 07:35:36 GMT
• Title: RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation
• Abstract summary: RoTRAG is a retrieval augmented framework that incorporates concise human written moral norms, called Rules of Thumb (RoTs)<n>For each turn, RoTRAG retrieves relevant RoTs from an external corpus and uses them as explicit normative evidence for turn level reasoning and final severity classification.<n>Experiments on ProsocialDialog and Safety Reasoning Multi Turn Dialogue show that RoTRAG consistently improves both harm classification and severity estimation over competitive baselines.
• Score: 5.988201449696967
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances. However, most existing methods rely mainly on models internal parametric knowledge, without explicit grounding in external normative principles. This often leads to inconsistent judgments in socially nuanced contexts, limited interpretability, and redundant reasoning across turns. To address this, we propose RoTRAG, a retrieval augmented framework that incorporates concise human written moral norms, called Rules of Thumb (RoTs), into LLM based harm assessment. For each turn, RoTRAG retrieves relevant RoTs from an external corpus and uses them as explicit normative evidence for turn level reasoning and final severity classification. To improve efficiency, we further introduce a lightweight binary routing classifier that decides whether a new turn requires retrieval grounded reasoning or can reuse existing context. Experiments on ProsocialDialog and Safety Reasoning Multi Turn Dialogue show that RoTRAG consistently improves both harm classification and severity estimation over competitive baselines, with an average relative gain of around 40% in F1 across benchmark datasets and an average relative reduction of 8.4% in distributional error, while reducing redundant computation without sacrificing performance.

Related papers

• When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation [7.171282546185869]
  Intent-Guided Decoding arbitrates between retrieved context and parametric memory according to user intent.<n>IGD substantially improves factual recovery, achieving gains of up to 65.4 percentage points on factual-conflict benchmarks over Direct RAG.
  arXiv  Detail & Related papers  (2026-08-17T12:56:43Z)
• PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception [75.70273182182397]
  PerceptionRubrics is a rubric-based evaluation framework.<n>It addresses the gap between saturated benchmark scores and real-world brittleness.<n>It pairs 1,038 information-dense images with over 10,000 instance-specific rubrics.
  arXiv  Detail & Related papers  (2026-06-26T17:59:15Z)
• Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning [20.897370477958734]
  Retrieval-augmented generation (RAG) has become a standard mechanism for grounding language models in external knowledge.<n>We propose Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT), a framework that teaches language models to reason by analogy.
  arXiv  Detail & Related papers  (2026-06-11T17:59:52Z)
• Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation [19.888565537472363]
  CoRM-RAG (Counterfactual Risk Minimization for RAG) is a framework that aligns retrieval with decision safety rather than mere similarity.<n>We introduce a Cognitive Perturbation Protocol to simulate user biases during training, which is then distilled into a lightweight Evidence Critic.<n>This scoring module learns to identify documents that possess sufficient evidential strength to steer the model toward correctness despite adversarial query perturbations.
  arXiv  Detail & Related papers  (2026-05-02T07:22:24Z)
• Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment [97.55382322103986]
  Hit-RAG is a multi-stage preference alignment framework designed to resolve cognitive bottlenecks.<n>Our approach systematically refines the utilization of external evidence via three distinct stages.
  arXiv  Detail & Related papers  (2026-03-07T04:05:27Z)
• Reasoning-Augmented Representations for Multimodal Retrieval [27.4146940988752]
  Universal Multimodal Retrieval (UMR) seeks any-to-any search across text and vision.<n>We argue this brittleness is often data-specified: when images carry "silent" evidence and queries leave key semantics implicit, a single embedding pass must both reason and compress.<n>We propose a data-centric framework that decouples these roles by externalizing reasoning before retrieval.
  arXiv  Detail & Related papers  (2026-02-06T19:01:54Z)
• From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG [65.0203623486525]
  Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering.<n>Their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields.<n>Existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning.
  arXiv  Detail & Related papers  (2026-02-06T08:25:30Z)
• Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers [41.58256327940237]
  Proactive Interactive Reasoning transforms Large Language Models into proactive inquirers.<n>PIR targets premise- and intent-level uncertainty through direct interaction with the user.<n>Experiments on mathematical reasoning, code generation, and document editing demonstrate that PIR consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-01-29T18:56:12Z)
• Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning [137.33138614095435]
  Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models.<n>Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval.<n>We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions.
  arXiv  Detail & Related papers  (2025-11-12T08:29:39Z)
• Decomposed Reasoning with Reinforcement Learning for Relevance Assessment in UGC Platforms [30.51899823655511]
  Retrieval-augmented generation (RAG) plays a critical role in user-generated content platforms.<n> platforms present unique challenges: 1) ambiguous user intent due to sparse user feedback in RAG scenarios, and 2) substantial noise introduced by informal and unstructured language.
  arXiv  Detail & Related papers  (2025-08-04T15:14:09Z)
• Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcement [9.66890519317288]
  Retrieval-augmented generation (RAG) improves performance on knowledge-intensive tasks but can be derailed by wrong, irrelevant, or conflicting retrieved text.<n>We propose Knowledgeable-R1, a reinforcement-learning framework that explicitly trains large language models to use parametric knowledge.
  arXiv  Detail & Related papers  (2025-06-05T15:34:15Z)
• T2I-Eval-R1: Reinforcement Learning-Driven Reasoning for Interpretable Text-to-Image Evaluation [60.620408007636016]
  We propose T2I-Eval-R1, a novel reinforcement learning framework that trains open-source MLLMs using only coarse-grained quality scores.<n>Our approach integrates Group Relative Policy Optimization into the instruction-tuning process, enabling models to generate both scalar scores and interpretable reasoning chains.
  arXiv  Detail & Related papers  (2025-05-23T13:44:59Z)
• Negotiated Reasoning: On Provably Addressing Relative Over-Generalization [49.5896371203566]
  Over-generalization is a thorny issue in cognitive science, where people may become overly cautious due to past experiences. Agents in multi-agent reinforcement learning (MARL) also have been found to suffer relative over-generalization (RO) as people do and stuck to sub-optimal cooperation. Recent methods have shown that assigning reasoning ability to agents can mitigate RO algorithmically and empirically, but there has been a lack of theoretical understanding of RO.
  arXiv  Detail & Related papers  (2023-06-08T16:57:12Z)

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.