# Interaction Context Often Increases Sycophancy in LLMs

arXiv: https://arxiv.org/abs/2509.12517 · HTML: https://mlsanity.com/paper/2509.12517/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2025.

## Built on by (most cited first, 26 of 26)

- [Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs](https://mlsanity.com/paper/2509.21305/) (2025)
- [What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct](https://mlsanity.com/paper/2605.21778/) (2026)
- [MemSyco-Bench: Benchmarking Sycophancy in Agent Memory](https://mlsanity.com/paper/2607.01071/) (2026)
- [SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy](https://mlsanity.com/paper/2604.02423/) (2026)
- [Most LLM Conformity Needs No Speaker: Measuring the Speaker-Free Floor in Peer-Pressure Benchmarks](https://mlsanity.com/paper/2607.05545/) (2026)
- [Mitigating Over-Personalization in LLMs via Structured Memory](https://mlsanity.com/paper/2608.08300/) (2026)
- [Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models](https://mlsanity.com/paper/2604.11609/) (2026)
- [Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions](https://mlsanity.com/paper/2511.07669/) (2025)
- [Persuasion Propagation: Does Persuasion Change AI Agent Behavior?](https://mlsanity.com/paper/2602.00851/) (2026)
- [AMEL: Accumulated Message Effects on LLM Judgments](https://mlsanity.com/paper/2605.22714/) (2026)
- [Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs](https://mlsanity.com/paper/2606.16011/) (2026)
- [Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models](https://mlsanity.com/paper/2607.19257/) (2026)
- [This Is a Good Paper, Right? How Tag Questions Affect Sycophancy Across 106 Language Models](https://mlsanity.com/paper/2607.23976/) (2026)
- [Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization](https://mlsanity.com/paper/2605.28969/) (2026)
- [Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference](https://mlsanity.com/paper/2606.07897/) (2026)
- [Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents](https://mlsanity.com/paper/2607.10526/) (2026)
- [Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment](https://mlsanity.com/paper/2608.11528/) (2026)
- [The Effect of Emotional Context on Large Language Models' Endorsement of Premature Decisions: Comparing Emotional Vulnerability Across Six Commercial Models](https://mlsanity.com/paper/2608.27465/) (2026)
- [Evaluating the Hidden Costs of Personalization in Large Language Models](https://mlsanity.com/paper/2608.28833/) (2026)
- [LLMs as Oracles: Reliance on LLMs for Subjective Personal Questions](https://mlsanity.com/paper/2609.14849/) (2026)
- [Talking Past the Machine: Morality, Politeness, and Alignment in Human-AI Dialogue](https://mlsanity.com/paper/2609.21401/) (2026)
- [Deflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus](https://mlsanity.com/paper/2609.25586/) (2026)
- [Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy](https://mlsanity.com/paper/2610.05162/) (2026)
- [Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding](https://mlsanity.com/paper/2610.08840/) (2026)
- [The AI's Poker Face: Contrasting Persuasion and Sycophancy in Voice-Based Multi-Turn Conversations](https://mlsanity.com/paper/2610.14124/) (2026)
- [RelLedger: Relational Information Governance for LLM Agent Organizations](https://mlsanity.com/paper/2610.16281/) (2026)

## Abstract (arXiv)

We investigate how the presence and type of interaction context shapes sycophancy in LLMs. While real-world interactions allow models to mirror a user's values, preferences, and self-image, prior work often studies sycophancy in zero-shot settings devoid of context. Using two weeks of interaction context from 38 users, we evaluate two forms of sycophancy: (1) agreement sycophancy -- the tendency of models to produce overly affirmative responses, and (2) perspective sycophancy -- the extent to which models reflect a user's viewpoint. Agreement sycophancy tends to increase with the presence of user context, though model behavior varies based on the context type. User memory profiles are associated with the largest increases in agreement sycophancy (e.g. +45% for Gemini 2.5 Pro), and some models become more sycophantic even with non-user synthetic contexts (e.g. +15% for Llama 4 Scout). Perspective sycophancy increases only when models can accurately infer user viewpoints from interaction context. Overall, context shapes sycophancy in heterogeneous ways, underscoring the need for evaluations grounded in real-world interactions and raising questions for system design around alignment, memory, and personalization.