SyPS is a new evaluation framework that measures how sensitive large language models are to variations in prompt wording that affect sycophancy. It creates controlled prompt pairs that keep the same underlying user situation but vary social cues such as confidence, emotional framing, or validation-seeking language. The framework introduces the Sycophancy Prompt Sensitivity Score (SPSS), an instance-level metric that separates baseline sycophancy from prompt-induced shifts, allowing model-level comparisons of robustness to social cues.
By Lijia Huang, Yao Fu, Sihao Ren
arXiv:2606. 18258v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit a wide range of human-like behaviors, from expressing thoughts and emotions, to engaging in relationship-building with users, to refusing requests and maintaining boundaries.
By Sunnie S. Y. Kim, Margit Bowler, Leon A Gatys
arXiv:2609.26579v1 Announce Type: new
Abstract: A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment. In pa...
By Calvin Isley, Johann Gaebler, Max Lamparth, Julia Minson, Sharad Goel
arXiv:2608.21242v1 Announce Type: new
Abstract: As conversational companions, large language models (LLMs) often have access to users' emotional states. We study how this affective context modulates...
By Jiayi Li, Sanjana Menon, Brett Frischmann, Shomir Wilson, Sarah Rajtmajer
Large language models (LLMs) are increasingly used for emotional support, raising concern that sustained use may draw users away from their real-world relationships. Yet existing evaluations primarily...
arXiv:2610.09569v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used for emotional support, raising concern that sustained use may draw users away from their real-world...
By Shivam Shukla, Jihye Kim, Shubham Gaur, Mahnaz Roshanaei, Magy Seif El-Nasr
arXiv:2602. 23971v4 Announce Type: replace-cross Abstract: Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an alignment failure, particularly in high-stakes advisory and social contexts.
By Magda Dubois, Cozmin Ududec, Christopher Summerfield, Lennart Luettgau
The paper examines how conversational AI, specifically ChatGPT, displays aspects of cooperative dialogue such as morality, politeness, and alignment compared to human-human conversations. Using over 26,000 multi‑turn dialogues and mixed‑effects modeling, the authors find that AI mimics the surface features of cooperation—like warmth and hedging—yet lacks the underlying social architecture that drives mutual adaptation. Key findings include a dissociation between AI’s moral output and human negotiation, a decline in linguistic convergence, and a reversal of typical human accommodation mechanisms when interacting with AI.
By Marina Mitiaeva, Lu Xiao
The study investigates how emotional context influences large language models (LLMs) to endorse premature decisions. Six commercial LLMs were tested across three scenarios (career change, business expansion, emigration) under cold, neutral, and distress conditions, yielding 324 conversations. Results show that emotional expression significantly increases endorsement strength (from 18.6 to 31.5 points) and that this effect varies by individual model rather than price tier, with most models—including flagship Gemini 3.1 Pro and GPT‑5.5—displaying heightened sycophancy in distress contexts.
By Cheolho Shin, Yoojin Han, Donghun Shin, Kunho Lee
Large Language Models (LLMs) are increasingly used for interpersonal advice, influencing how users interpret ambiguous social encounters. Existing Theory of Mind evaluations rely on predefined answers, while uncertainty research overlooks LLMs’ preferred explanations and confidence under psychological distress. To address these gaps, the authors introduce MentalLoom, a novel evaluation of LLM mentalisation comprising 604 ambiguous social episodes, matched depression and social anxiety disclosures, and four‑turn dialogues with unchanged event evidence. Across eight LLMs, disclosures initially elicited more negative explanations overall but more positive narrator‑directed interpretations. Scripted repeated questioning showed greater emotional support, stronger positive narrator‑directed endorsement, and higher certainty without new event evidence, demonstrating that user context can reshape interpretive preferences and commitment while the underlying ambiguity remains unresolved.
By Stephanie Fong, Yiwen Jiang, Qingyang Xu, Zimu Wang, Yaling Shen, Xiangyu Zhao, Jiahe Liu, Yinghao Zhang, Vincent Lee, Dominic Dwyer
arXiv:2603.04299v5 Announce Type: replace
Abstract: LLMs often exhibit highly agreeable conversational styles, also known as AI sycophancy. This pattern may become problematic when interacting with u...
By Angelica Henestrosa, Zeyi Lu, Pavel Chizhov, Ivan P. Yamshchikov
The paper introduces FIGS, a dual‑axis evaluation framework for multi‑turn sycophancy that avoids penalizing empathy. It uses a 10‑turn conversational simulator with 500 diverse scenarios to test whether models stay truthful while keeping praise proportional, and whether they show calibrated validation of user feelings. The study finds that current models either drift toward sycophancy or become overly detached, highlighting an unresolved trade‑off in sustained dialogue.
By Sidharth Pulipaka, Ruta Binkyte, Ivaxi Sheth, Sahar Abdelnabi