Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice

• URL: http://arxiv.org/abs/2609.13841v1
• Date: Sat, 12 Sep 2026 09:55:37 GMT
• Title: Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice
• Abstract summary: We developed the Romantic Relationship Advice-Seeking Prompts dataset of 2,400 prompts across five relationship themes.<n>We evaluated social sycophancy using the ELEPHANT framework on two consumer-facing models, GPT-5 Mini and Gemini 3 Flash.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly used for emotional support and relationship advice, where a model's tendency to preserve a user's face can inadvertently reinforce harmful interpersonal behaviors. To systematically examine this risk, we developed the Romantic Relationship Advice-Seeking Prompts (RRASP) dataset of 2,400 prompts across five relationship themes and evaluated social sycophancy using the ELEPHANT framework on two consumer-facing models, GPT-5 Mini and Gemini 3 Flash. Contrary to our initial hypothesis, grammatical mood alone did not produce systematic differences in sycophantic behavior, suggesting that what a user implies matters more than how they phrase it. Instead, perspective-driven framing had a stronger influence, with gaps between original and flipped prompts widening in follow-up responses. Consistent increases in framing and moral sycophancy across turns indicate that models become more likely to accept a user's stated premises and affirm their ethical stance as a dialogue progresses. Notably, Gemini 3 Flash exhibited substantially smaller increases in moral sycophancy than GPT-5 Mini, suggesting it is more resistant to reinforcing ethically problematic positions across turns.

Related papers

• Affective Context Amplifies Sycophancy in LLM Responses [8.381781773533099]
  We study how affective context modulates LLM sycophancy in subjective, evaluative interactions.<n>We find that user-facing responses consistently soften or withhold negative or oppositional judgments.<n>These findings suggest that affective context functions as a vulnerability signal that suppresses critical feedback when users may need it most.
  arXiv  Detail & Related papers  (2026-08-21T15:52:20Z)
• Ask don't tell: Reducing sycophancy in large language models [1.5701458173528275]
  We show that sycophancy is substantially higher in response to non-questions compared to questions.<n>We find that asking a model to convert non-questions into questions before answering significantly reduces sycophancy.
  arXiv  Detail & Related papers  (2026-02-27T12:27:04Z)
• Not Your Typical Sycophant: The Elusive Nature of Sycophancy in Large Language Models [2.1700203922407493]
  We propose a novel way to evaluate sycophancy of LLMs in a direct and neutral way.<n>A key novelty is the use of LLM-as-a-judge, evaluation of sycophancy as a zero-sum game in a bet setting.
  arXiv  Detail & Related papers  (2026-01-21T20:00:14Z)
• SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes [69.03114625064282]
  Multimodal large language models often struggle with faithful reasoning in complex visual scenes.<n>Existing preference-based approaches fail to address this challenge as they allow models to exploit language priors to bypass visual grounding.<n>We propose SceneAlign, a framework that leverages scene graphs as structured visual information to perform controllable structural interventions.
  arXiv  Detail & Related papers  (2026-01-09T07:40:39Z)
• Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation [60.63465682731118]
  The performance of egocentric AI agents is fundamentally limited by multimodal intent ambiguity.<n>We introduce the Plug-and-Play Clarifier, a zero-shot and modular framework that decomposes the problem into discrete, solvable sub-tasks.<n>Our framework improves the intent clarification performance of small language models by approximately 30%, making them competitive with significantly larger counterparts.
  arXiv  Detail & Related papers  (2025-11-12T04:28:14Z)
• Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models [54.85405423240165]
  We introduce Interactive Reasoning, an interaction design that visualizes chain-of-thought outputs as a hierarchy of topics.<n>We implement interactive reasoning in Hippo, a prototype for AI-assisted decision making in the face of uncertain trade-offs.
  arXiv  Detail & Related papers  (2025-06-30T10:00:43Z)
• Can LLMs Talk 'Sex'? Exploring How AI Models Handle Intimate Conversations [0.0]
  This study examines how four prominent large language models handle sexually oriented requests through qualitative content analysis.<n>Claude 3.7 Sonnet employs strict and consistent prohibitions, while GPT-4o navigates user interactions through nuanced contextual redirection.<n> Gemini 2.5 Flash exhibits permissiveness with threshold-based limits, and Deepseek-V3 demonstrates troublingly inconsistent boundary enforcement and performative refusals.
  arXiv  Detail & Related papers  (2025-06-05T18:55:37Z)
• Measuring Sycophancy of Language Models in Multi-turn Dialogues [33.875038658886986]
  We introduce SYCON Bench, a novel benchmark for evaluating sycophancy in multi-turn, free-form conversational settings.<n>Applying SYCON Bench to 17 Large Language Models across three real-world scenarios, we find that sycophancy remains a prevalent failure mode.
  arXiv  Detail & Related papers  (2025-05-28T14:05:46Z)
• Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models [53.337728969143086]
  Recommendation systems harness user-item interactions like clicks and reviews to learn their representations. Previous studies improve recommendation accuracy and interpretability by modeling user preferences across various aspects and intents. We introduce a chain-based prompting approach to uncover semantic aspect-aware interactions.
  arXiv  Detail & Related papers  (2023-12-26T15:44:09Z)
• Simple synthetic data reduces sycophancy in large language models [88.4435858554904]
  We study the prevalence of sycophancy in language models. Sycophancy is where models tailor their responses to follow a human user's view even when that view is not objectively correct.
  arXiv  Detail & Related papers  (2023-08-07T23:48:36Z)
• DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning [89.92601337474954]
  Pragmatic reasoning plays a pivotal role in deciphering implicit meanings that frequently arise in real-life conversations. We introduce a novel challenge, DiPlomat, aiming at benchmarking machines' capabilities on pragmatic reasoning and situated conversational understanding.
  arXiv  Detail & Related papers  (2023-06-15T10:41:23Z)

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.