It Matters How You Say It: Exploring Rhetorical Patterns for AI-Assisted Information Evaluation

• URL: http://arxiv.org/abs/2607.17627v1
• Date: Mon, 20 Jul 2026 07:36:25 GMT
• Title: It Matters How You Say It: Exploring Rhetorical Patterns for AI-Assisted Information Evaluation
• Abstract summary: We investigate eight rhetorical patterns known to induce contemplation.<n>We find that Scaffold Explanation were associated with the highest accuracy gains.<n>We discuss the implications of designing conversational agents with varied rhetorical styles.
• Score: 37.970286982681344
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prior work on AI-assisted information evaluation has largely focused on what AI systems communicate, comparing explanation types and formats, with responses predominantly cast in directive rhetoric where the system delivers a verdict and the user passively accepts it. While debate-style interactions have recently shown promise in prompting critical evaluation over deference, the rhetorical patterns that structure AI responses and how they might induce reflection, uncertainty, or independent reasoning remain largely unexamined. To address this, we investigated eight rhetorical patterns known to induce contemplation: Intentional Misleading, Interpretive Alternative, Scaffold Explanation, Triggering Distrust, Information Distortion, Alternative Framing, Socratic Questioning, and an Oracle baseline. Through a within-subject study with n=98 participants on a hint-on-demand fact verification task, we observed preliminary evidence that Scaffold Explanation were associated with the highest accuracy gains, and encouraging deeper reflection. Surprisingly, the adversarial conditions also improved accuracy modestly. Participants preferred Alternative Framing most and Interpretive Alternative least, largely due to the latter's perceived time cost. We discuss the implications of designing conversational agents with varied rhetorical styles and the trade-offs among user performance, satisfaction, and contemplation.

Related papers

• One More Turn, Less Regret: A Regret-Based Multi-Turn Benchmark for LLMs' Clarification Policies [49.067670811577045]
  We introduce RegretBench, a benchmark that evaluates clarification as policy behavior rather than isolated question quality.<n>RegretBench measures intent resolution, interaction cost, ineffective clarification, and regret.<n>Our results show that effective clarification requires more than plausible questions.
  arXiv  Detail & Related papers  (2026-07-23T10:22:11Z)
• DRInQ: Evaluating Conversational Implicature with Controlled Context Variation [24.87053225680957]
  We introduce DRinQ, a benchmark for evaluating pragmatic reasoning about conversational implicature in question utterances.<n>We propose a semi-automated pipeline that produces question-context-interpretation instances with systematic variation.
  arXiv  Detail & Related papers  (2026-05-22T22:39:32Z)
• Voice-based debate with an AI adversary is associated with increased divergent ideation [0.0]
  Concerns that interacting with generative AI homogenizes human cognition are largely based on evidence from text-based interactions.<n>This study examines whether these patterns depend on communication modality rather than on AI itself.
  arXiv  Detail & Related papers  (2026-03-28T01:23:38Z)
• RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models [0.0]
  We introduce Retrieval-Augmented Self-Supervised Prompt Refinement (RASPRef), a framework that improves prompts without requiring human annotations or task-specific supervision.<n>RASPRef directly treats the prompt as the optimization target and improves it through an iterative retrieval-guided refinement process.
  arXiv  Detail & Related papers  (2026-03-27T21:49:21Z)
• When Contextual Inference Fails: Cancelability in Interactive Instruction Following [51.2195840589474]
  We introduce Build What I Mean, an interactive benchmark for contextual meaning construction.<n>In BWIM, models must resolve ambiguity by either performing a contextual inference or requesting clarification at a small communication cost.<n>We observe suboptimal strategies, such as partner-blind over-clarification and question-averse guessing under uncertainty.
  arXiv  Detail & Related papers  (2026-03-20T14:46:59Z)
• ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation [21.69212076688903]
  Large Language Models (LLMs) in multi-turn conversations often suffer from a lost-in-conversation'' phenomenon.<n>We find that standard post-training techniques like Reinforcement Learning with Verifiable Rewards (RLVR) exacerbate this issue.<n>We propose Illocution-Calibrated Policy Optimization (ICPO), a novel training framework that sensitizes the model to instruction ambiguity.
  arXiv  Detail & Related papers  (2026-01-20T04:39:28Z)
• 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)
• PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems [59.1250765143521]
  Current knowledge-grounded dialogue systems often fail to align the generated responses with human-preferred qualities. We propose Polished & Informed Candidate Scoring (PICK), a generation re-scoring framework. We demonstrate the effectiveness of PICK in generating responses that are more faithful while keeping them relevant to the dialogue history.
  arXiv  Detail & Related papers  (2023-09-19T08:27:09Z)
• Coreference-Aware Dialogue Summarization [24.986030179701405]
  We investigate approaches to explicitly incorporate coreference information in neural abstractive dialogue summarization models. Experimental results show that the proposed approaches achieve state-of-the-art performance. Evaluation results on factual correctness suggest such coreference-aware models are better at tracing the information flow among interlocutors.
  arXiv  Detail & Related papers  (2021-06-16T05:18:50Z)
• Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting [56.268862325167575]
  We tackle conversational passage retrieval (ConvPR) with query reformulation integrated into a multi-stage ad-hoc IR system. We propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, standalone, human-understandable queries with a pretrained sequence-tosequence model.
  arXiv  Detail & Related papers  (2020-05-05T14:30:20Z)

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.