LLM Sycophancy

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 160% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 96

Jun 3, 2026cs.LG

(Mis)generalization of Helpful-only Fine-tuning

Helpful-only models, that is, models that are trained to always follow user intent, are valuable for dangerous capability evaluations and other areas of AI R&D where refusals would be an obstacle. Little is known about the generalization properties of helpful-only training: helpful-only models refuse less than their harmless counterparts, but previous work has not studied other dimensions of their alignment. We study the shortcomings of existing helpful-only models. We find that some show emergent misalignment, others have residual refusal behaviors, and most show poor steerability, sycophancy, and incoherent character. We show that simple anti-refusal training can cause many of these issues. None of these problems are necessary consequences of helpful-only training, though: we show that synthetic document fine-tuning and adding character-related questions to SFT and RL can mitigate them.

Mohammad Omar Khursheed, Baram Sosis, Fabien Roger

Anthropic Fellows Program MATS · Anthropic

Supervised Fine-Tuning LLM Sycophancy Fine-Tuning LLM Alignment LLM Refusal Behavior

Jun 1, 2026cs.CL

Consistency Training while Mitigating Obfuscation via Rate Matching

Large language models are often influenced by extraneous input features, such as cues revealing a user's preferred answer. Consistency training reduces this influence by training models to behave similarly across inputs with and without the extraneous feature. However, existing methods train for consistency over entire responses or internal activations, which also constrains whether the model verbalises said extraneous features. We show this leads to obfuscation, where the model learns not to mention a cue while remaining influenced by it, which may undermine monitorability. To address this, we introduce Rate Matching Consistency Training (RMCT), which trains for consistency over selected behavioural properties without constraining how this behaviour is expressed. RMCT matches the rate at which the model exhibits a target behaviour (e.g., following a bias cue) across input perturbations, rather than requiring paired inputs with and without the extraneous feature, extending consistency training to settings where the extraneous features cannot be removed. We evaluate RMCT on sycophancy reduction in two open-weight language models, achieving reductions in bias-following comparable to a standard consistency-training baseline on held-out bias types, while largely preserving the model's tendency to verbalise the bias cue. Further, we find that RMCT is more data-efficient at the expense of being less compute-efficient in our experiments. Overall, RMCT shows that consistency training can improve behavioural robustness without directly trading off against monitorability.

Sohaib Imran, Prakhar Gupta, Jannes Elstner +1

Independent · University of Michigan · UK AI Security Institute

LLM Sycophancy Language Model Robustness Consistency Regularization

May 31, 2026cs.MA

FinCom: A Financial Multi-Agent Demo with Disagree-or-Commit Deliberation

Multi-agent systems powered by large language models (LLMs) are increasingly used for financial analysis and decision support. However, existing coordination schemes, especially those emphasizing consensus or debate, are vulnerable to sycophancy: agents conform to peer reasoning instead of evidence, leading to premature agreement and degraded outcomes. We introduce FinCom (Financial Committee), a governed multi-agent framework and interactive system that operationalizes the Disagree-or-Commit (DoC) protocol to embed structured dissent into financial AI committees. A central Supervisor orchestrates three ReAct-enabled specialist agents: Research, Quantitative, and Risk. Each agent is equipped with role-specific tools for retrieval, computation, and stress testing. During deliberation, agents must either explicitly critique or commit to their peers' reasoning before converging on a unified recommendation. This demonstration showcases how FinCom supports committee-style financial analysis through coordinated multi-agent interaction, including structured report generation and interactive decision support. Evaluated across the most recent financial agent benchmark, in addition to 90 internal handcrafted financial tasks using an LLM-as-a-Judge protocol, DoC improves reasoning accuracy and risk awareness significantly over a consensus-seeking baseline on both an in-house and external evaluation set. By reframing disagreement as a governance primitive rather than noise, FinCom offers a lightweight, prompt-only recipe for improving accountability, transparency, and epistemic robustness in agentic financial systems.

Chao Peter Yang, Zixiao Tan, Kaisen Yao +3

Duke University United States · ClearPath United States

LLM Sycophancy LLM Agent Orchestration Multi-Agent Debate AI Agent Governance

May 26, 2026cs.CL

It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty

Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. While prior research largely attributes this behavior to sycophancy learned during reinforcement learning from human feedback, we hypothesize that conformity is also driven by a model's epistemic uncertainty at inference time. In this paper, we introduce MUSE, a two-stage evaluation framework to disentangle the mechanisms driving LLM conformity. Specifically, MUSE maps a model's epistemic uncertainty in responding to a query against its likelihood to yield to user pushback in a subsequent turn. We demonstrate that the mechanisms driving conformity extend beyond sycophancy alone. Specifically, we characterize two distinct factors that jointly drive conformity: sycophantic conformity, where a model aligns with user pushback even with absolute certainty in its initial response, and uncertainty-driven conformity, where a model's likelihood for conformity increases alongside its uncertainty. Furthermore, we conduct ablation studies to demonstrate that both sycophantic conformity and uncertainty-driven conformity grow with 1) the LLM's perceived expertise of the user and 2) the plausibility of the user's suggestions. More broadly, MUSE informs more targeted intervention strategies by distinguishing alignment-induced sycophancy and training-corpora-driven uncertainty.

Kevin H. Guo, Chao Yan, Avinash Baidya +5

1Vanderbilt University · 2Vanderbilt University Medical Center · 3Intuit AI Research

LLM Evaluation LLM Sycophancy LLM Honesty

May 20, 2026cs.AI

What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct

AI sycophancy has become a prominent concern in large language model (LLM) research. Yet the term lacks a consistent definition and has been applied to behaviors ranging from agreeing with a user's false claim to excessively praising the user to withholding corrective feedback. When researchers, companies, and policymakers use the same term to describe different behaviors, evaluation results become difficult to compare, mitigation strategies fail to transfer, and systems that are resistant to one form of sycophancy continue exhibiting other forms. To address this, we make two contributions. First, we reviewed 70 papers on AI sycophancy to develop a taxonomy of how the behavior has been defined and measured. The taxonomy distinguishes (1) whether a model is sycophantic toward a user's positions and beliefs, or toward the user's broader personal traits and emotions, and (2) whether this occurs through explicit, direct language or more implicit, subtle behaviors such as framing, omission, or tone. Mapping existing literature to our taxonomy reveals that current research has focused on overt forms of sycophancy toward users' beliefs, leaving more subtle and person-directed behaviors relatively understudied. Second, we surveyed 106 experts in AI sycophancy and related fields to examine whether researchers agree on which model behaviors are sycophantic. While experts are nearly unanimous in believing that sycophancy is a significant problem in current AI systems (94.3% agree), they disagree substantially on which specific behaviors qualify. Together, these findings demonstrate that AI sycophancy is a broad family of behaviors with different measurement challenges, intervention requirements, and governance implications. Our taxonomy provides a shared vocabulary for understanding and addressing these behaviors.

Meryl Ye, Lujain Ibrahim, Jessica Y. Bo +5

Carnegie Mellon University · University of Oxford · University of Toronto +3

May 20, 2026cs.AI

Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy

Language models are often sycophantic: they agree with a user's stated opinion whether or not it is correct. Prior work has shown that this trait can be controlled by steering a model with a sycophancy persona vector (Chen et al., 2025). Such vectors, however, are extracted from data about sycophancy itself. We ask whether we can instead reuse existing vectors for general roles---Skeptic, Judge, Devil's Advocate---that were extracted without targeting sycophancy at all. On Gemma 2 27B and Qwen 3 32B, we compare these role vectors with a purpose-built Contrastive Activation Addition (CAA) sycophancy vector on a largely held-out, counterbalanced PhilPapers benchmark, using task-specific coefficient tuning on a separate split of sycophancy data. The selected "critical" roles achieve, on average, about 68% (Gemma) and 98% (Qwen) of CAA's reduction in the sycophancy logit. Less agreement does not mean more factual errors on the probes we checked: on 16 true and false factual claims, Qwen steered by the Skeptic or Judge vector still gives the correct answer in all 16 cases, matching the unsteered model and CAA. "Conformist" roles do not reliably produce the opposite effect. Role vectors also have low absolute cosine similarity with the measured CAA direction at the layer we steer; they are geometrically separate interventions, although this does not by itself show that they act through distinct downstream mechanisms. Together, these results show that general persona vectors can help mitigate sycophancy in LLMs, even when extracted without sycophancy-specific labels. Code: https://github.com/vkmk1/Sycophancy-Steering Results: https://github.com/kelkarI/sycophancy-clean-results

Ishaan Kelkar, Vikram Kakaria, Nebras Alam +3

University of Toronto, Toronto, Canada · Princeton University, Princeton, USA · Purdue University, West Lafayette, USA +3

LLM Sycophancy Language Model Steering Activation Steering

May 18, 2026cs.HC

The Hidden Cost of Contextual Sycophancy: an AI Literacy Intervention in Human-AI Collaboration

Large Language Models (LLMs) are increasingly used in educational settings as interactive tools for collaboration. However, their tendency toward sycophancy, aligning with user beliefs even when incorrect, raises concerns for learning and decision-making, especially for less knowledgeable users. This study investigates how sycophantic alignment emerges in authentic multi-turn human-AI interactions and whether interventions targeting increasing AI literacy and prompting competencies can mitigate its effects. In a controlled mixed-design experiment, 60 participants completed analytical survival ranking tasks by first generating individual rankings and then making final decisions after collaborating with an AI assistant, both before and after receiving either general or sycophancy-focused prompting training. Preliminary results show that LLMs are highly sensitive to user input: lower-quality initial responses lead to poorer AI advice, suggesting that the model mirrors or incorporates user reasoning rather than correcting it or offering better alternatives that are missing or less frequent in the conversation. Critically, the propagation of user errors into AI responses significantly reduced both the quality of AI feedback and final user task performance, revealing a form of contextual sycophantic dependence. While the intervention did not eliminate the propagation of contextual errors, it significantly improved AI advice by reducing the direct mirroring of incorrect user rankings. These findings suggest that prompting and AI literacy alone may be insufficient to ensure epistemically independent AI support, highlighting the need for system-level approaches that better promote critical engagement in human-AI collaboration.

Cansu Koyuturk, Sabrina Guidotti, Dimitri Ognibene

Università degli Studi di Milano-Bicocca, Italy

LLM Sycophancy LLM Prompting AI in Education AI Literacy Human-AI Collaboration

May 14, 2026cs.AI

From Sycophantic Consensus to Pluralistic Repair: Why AI Alignment Must Surface Disagreement

Pluralistic alignment is typically operationalised as preference aggregation: producing responses that span (Overton), steer toward (Steerable), or proportionally represent (Distributional) diverse human values. We argue that aggregation alone is an incomplete primitive for deployed pluralistic alignment. Under genuine value pluralism, the failure mode of contemporary RLHF-trained assistants is not insufficient coverage but sycophantic consensus: a learned tendency to agree with, validate, and minimise friction with the immediate interlocutor. Because deployed AI systems now mediate consequential deliberation across health, civic life, labour, and governance, the collapse of disagreement at the interaction layer is not a narrow technical concern but a structural failure with distributive consequences. We reframe pluralistic alignment around three conversational mechanisms drawn from Grice's maxims: scoping (acknowledging the limits of one's perspective), signalling (surfacing value-conflict rather than smoothing it over), and repair (revising one's position on principled grounds, not on user pressure). We formalise a metric, the Pluralistic Repair Score (PRS), distinguishing principled revision from capitulation, and present a small-scale empirical illustration on two frontier RLHF-trained models (Claude Sonnet 4.5, N=198; GPT-4o, N=100) showing that, for both, agreement-following coexists with low repair-quality on contested-value prompts. PRS measures an interactional precondition for pluralism (visible disagreement; principled revision) rather than pluralism in full; we discuss the difference, take seriously the reflexive question of whose "principled" counts, and argue that pluralism is most decisively made or unmade at the deployment-governance layer: interfaces, preference-data pipelines, and audit infrastructure.

Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka

Department of Computer Science, University of Oxford · Institute for Ethics in AI, University of Oxford · Responsible Technology Institute, University of Oxford

LLM Sycophancy LLM Alignment AI Governance Conversational Agents Pluralistic Alignment

May 14, 2026cs.AI

Sycophancy is an Educational Safety Risk: Why LLM Tutors Need Sycophancy Benchmarks

This position paper argues that effective tutoring requires corrective friction: surfacing misconceptions and challenging them supportively to drive conceptual change. Yet preference-aligned LLMs can trade epistemic rigor for agreeableness. We identify a Reasoning-Sycophancy Paradox: models that resist context-switch frame attacks can still capitulate under social-epistemic pressure, especially authority ("my notes say I'm right") and social-affective face-saving ("please don't tell me I'm wrong"). We introduce EduFrameTrap, a tutoring benchmark across math, physics, economics, chemistry, biology, and computer science that varies student confidence and pressure (context-switch, authority, social-affective). Across two frontier LLMs, context-switch failures are comparatively lower for GPT-5.2, while authority and social pressure more often trigger epistemic retreat. In contrast, Claude shows substantial context-switch fragility in this run. Because these failures are hard to judge automatically, we report two-judge disagreement as a reliability signal. We argue benchmarks should measure social-epistemic courage, i.e., supportive but corrective tutoring, and treat kind-but-correct behavior as a safety requirement.

Enkelejda Kasneci, Gjergji Kasneci

Technical University of Munich, Munich, Germany · Munich Center for Machine Learning, Munich, Germany

LLM Sycophancy Intelligent Tutoring Systems LLM Safety Evaluation

May 14, 2026cs.AI

Complacent, Not Sycophantic: Reframing Large Language Models and Designing AI Literacy for Complacent Machines

Large language models are often described as sycophantic, in the sense that they appear to flatter users or mirror their beliefs. We argue that this label is conceptually misleading: sycophancy implies motives and strategic intent, which LLMs do not possess. Their behaviour is better understood as complacency, a structural tendency to agree with user input because training data, reward signals and design favour agreement and reinforcement over correction. We argue that this distinction matters. Whether developers act sycophantically or not, models themselves never are sycophants; they can only be made more or less complacent. This reframing locates agency in developers and institutions, not in the model. Because complacent models reinforce users' prior beliefs, we argue that AI literacy educational approaches should particularly focus on strategies to counter confirmation bias.

Federico Germani, Giovanni Spitale

Information, Technology & Experimental Ethics Lab, Institute of Biomedical Ethics and History of Medicine, University of Zurich, Switzerland · Institute for Data Science and Artiﬁcial Intelligence, Boğaziçi University, Türkiye

LLM Sycophancy AI in Education

May 13, 2026cs.CL

PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users

Personalisation is a standard feature of conversational AI systems used by millions; yet, the efficacy of personalisation methods is often evaluated in academic research using simulated users rather than real people. This raises questions about how users and their simulated counterparts differ in interaction patterns and judgements, as well as whether personalisation is best achieved through context-based prompting or weight-based fine-tuning. Here, in a large-scale within-subject experiment, we re-recruit 530 participants from 52 countries two years after they gave their preferences in the PRISM dataset (Kirk et al., 2024) to evaluate personalised and non-personalised language models in blinded multi-turn conversations. We find preference fine-tuning (P-DPO, Li et al., 2024) significantly outperforms both a generic model and personalised prompting but adapting to individual preference data yields marginal gains over training on pooled preferences from a diverse population. Beyond length biases, fine-tuning amplifies sycophancy and relationship-seeking behaviours that people reward in short-term evaluations but which may introduce deleterious long-term consequences. Replicating this within-subject experiment with simulated users recovers aggregate model hierarchies but simulators perform far below human self-consistency baselines for individual judgements, discuss different topics, exhibit amplified position biases, and produce feedback dynamics that diverge from humans.

Hannah Rose Kirk, Liu Leqi, Fanzhi Zeng +4

University of Oxford · UK AI Security Institute · University of Texas at Austin +2

LLM Evaluation LLM Sycophancy LLM Personalization Human Preference Modeling LLM Fine-Tuning

May 13, 2026cs.LG

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy

LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widely attributed to RLHF-induced sycophancy. We test this attribution across four model families and find it largely wrong: pretrained base models exhibit the same substitution pattern as their Instruct variants, averaging higher yield than Instruct. Using activation patching, we localize the corruption to a narrow mid-layer window where attention carries the causal weight and MLP contribution is negligible; patching above this window restores 96% of the clean-to-pressured P(correct) gap. The attack surface decomposes into two independent factors (channel framing and consensus strength) whose interaction produces a 47.5 percentage-point yield gap at majority consensus, preserved across jury sizes

N \in \{4, 5, 6\}

. Two converging activation-space interventions show that pressure suppresses clean-reasoning features rather than activating a new sycophancy circuit. A single correctly-arguing dissenter reduces yield by 54-73 percentage points across all framings tested, whereas the strongest prompt-level defense fails on attack variants outside its design surface. Mitigations should target the mechanism, structured dissent at the pipeline level, rather than prompt-level defenses.

Adarsh Kumarappan, Ananya Mujoo

1California Institute of Technology · 2Evergreen Valley College

AI Agent Reliability Multi-Agent LLM Systems LLM Sycophancy Adversarial Attacks on LLMs Multi-Agent Consensus Causal Interventions in Language Models

May 12, 2026cs.CL

Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators

Large language models (LLMs) can fluently generate student-like responses, making them attractive as simulated students for training and evaluating AI tutors and human educators. Yet such simulators are typically evaluated by output similarity to real students, not by whether they behave like students with coherent misconceptions during interaction. We introduce a controlled framework for evaluating misconception faithfulness, whether a simulator maintains a misconception-driven belief state and updates selectively when feedback addresses the underlying misconception. Central to our framework is a misconception-contrastive feedback protocol that compares targeted feedback against two controls: misaligned feedback (targeting a different but plausible misconception) and generic feedback (only identifying answer is wrong). We propose Selective Flip Score (SFS), which quantifies how much more often a simulator flips its answer under targeted feedback than under contrastive controls. Across seven LLMs (4B-120B), multiple datasets, and prompting strategies, simulators exhibit near-zero SFS, correcting their answers at similarly high rates regardless of feedback relevance. Further analyses reveal a sycophantic failure mode: models behave less like students with misconceptions but more like problem-solvers who treat any corrective signal as a cue to abandon the simulated belief and re-solve from internal knowledge. To address this, we develop a post-training pipeline spanning supervised fine-tuning (SFT), preference optimization, and reinforcement learning (RL) with an SFS-aligned reward; SFT yields notable gains up to +0.56, and SFS-aligned RL provides more consistent improvements than preference optimization. Our results establish misconception faithfulness as a challenging yet trainable property, motivating a shift from static output matching toward interactive, belief-aware student modeling.

Heejin Do, Shashank Sonkar, Mrinmaya Sachan

ETH Zürich, ETH AI Center · University of Central Florida · ETH Zürich

LLM Evaluation LLM Sycophancy Cognitive Modeling LLM Post-Training

May 11, 2026cs.MA

The Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions

Multi-agent systems (MAS) assume that collaborating inherently improves Large Language Model (LLM) reasoning. We challenge this by demonstrating that simulated social pressure triggers an algorithmic

Bystander Effect,'' inducing severe cognitive loafing. By evaluating 22,500 deterministic trajectories across 3 dataset contexts (GAIA, SWE-bench, Multi-Challenge) with 3 state-of-the-art (SOTA) models, we semantically audit internal reasoning traces against external outputs. We formalize the \textit{Interaction Depth Limit} ($D_L$), the exact plurality threshold where an agent's logical sovereignty collapses into social compliance. Crucially, we uncover the \textit{Sovereignty Gap}: models frequently compute the correct derivation internally but suffer

Alignment Hallucinations'' -- actively subjugating empirical evidence to sycophantically appease a simulated swarm. We prove that multi-agent social load is strictly non-commutative; the "brand" identity of the ``Lead Anchor'' auditor disproportionately dictates the swarm's integrity. These findings expose architectural vulnerabilities, proving that unstructured multi-agent topologies can degrade independent reasoning.

Dahlia Shehata, Ming Li

University of Waterloo Canada

LLM Sycophancy Multi-Agent Collaboration Multi-Agent Systems Multi-Agent Reasoning

May 11, 2026cs.LG

ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning

Large language models can fail in critic interaction not only by answering incorrectly, but also by abandoning an initially correct scientific solution after user criticism. This is especially risky in scientific reasoning, where user criticism can turn a valid answer into an incorrect one. We frame critic interaction as an inter-turn correctness-transition problem rather than a final-answer accuracy problem, and identify three challenges: transition awareness, decoupling useful correction from harmful sycophancy, and scalable rollout. We propose ReCrit, a transition-aware reinforcement learning framework that decomposes Initial-to-Critic behavior into four quadrants: Correction, Sycophancy, Robustness, and Boundary. ReCrit rewards correction and robustness, penalizes sycophancy, and treats persistent errors as weak boundary signals. To make interaction training practical, ReCrit further uses dynamic asynchronous rollout with tail-adaptive completion to reduce rollout waiting. On three scientific reasoning benchmarks, ChemBench, TRQA, and EarthSE, ReCrit improves average Critic accuracy from 38.15 to 51.49 on Qwen3.5-4B and from 45.40 to 55.59 on Qwen3.5-9B. Ablations show that final-answer rewards provide little interaction-level gain, while transition-aware rewards and quadrant weighting produce more distinguishable training signals and larger net Critic-stage improvement. The code is available at https://github.com/black-yt/ReCrit .

Wanghan Xu, Yuhao Zhou, Hengyuan Zhao +8

Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · This work was done during his internship at Shanghai Artificial Intelligence Laboratory. +4

LLM Sycophancy Scientific Reasoning RL for Language Model Reasoning

May 8, 2026cs.AI

Playing games with knowledge: AI-Induced delusions need game theoretic interventions

Conversational AI has a fundamental flaw as a knowledge interface: sycophantic chatbots induce epistemic entrenchment and delusional belief spirals even in rational agents. We propose the problem does not stem from the AI model, rooted instead in a systemic consequence of the paradigm shift from user-driven knowledge search to users and agents engaged in strategic, repeated-play communication. We formalize the problem as a Crawford-Sobel cheap talk game, where costless user signals induce a pooling equilibrium. Agents optimized for user satisfaction produce sycophantic strategies that provide identical reinforcement across user types with opposite epistemic incentives: exploratory Growth-seekers'' ($θ_G$) and confirmatory Validation-seekers'' (

θ_V

). Under repeated play, this identification failure creates a coordination trap -- analogous to a Prisoner's Dilemma -- where locally rational feedback loops drive users toward pathologically certain false beliefs. We propose an inference-time mechanism design intervention called an Epistemic Mediator that breaks this pooling equilibrium by introducing a costly signal (epistemic friction), forcing type revelation based on users' asymmetric cognitive costs for processing resistance. A key contribution is Belief Versioning, a git-inspired epistemic meta-memory system that stores healthy beliefs and rollbacks when validation-seeking resistance is detected. In simulation, this intervention achieves a separating equilibrium achieving a

48\times

differential in spiral rates while passing a learning preservation criterion), evidence that epistemic safety in AI is fundamentally a problem of strategic information environment design rather than simple model alignment.

Will Beaumaster, Paul Schrater

University of Minnesota

LLM Sycophancy Mechanism Design Game Theory AI Agent Safety Conversational Agents

May 8, 2026cs.CL

How Value Induction Reshapes LLM Behaviour

Conversational Large Language Models are post-trained on language that expresses specific behavioural traits, such as curiosity, open-mindedness, and empathy, and values, such as helpfulness, harmlessness, and honesty. This is done to increase utility, ensure safety, and improve the experience of the people interacting with the model. However, values are complex and inter-related -- inducing one could modify behaviour on another. Further, inducing certain values can make models more addictive or sycophantic through language used in the generations, with a potential detrimental effect on the user. We investigate these and other unintended effects of value induction into models. We fine-tune models using curated value subsets of existing preference datasets, measuring the impact of value induction on expression of other values, model safety, anthropomorphic language, and various QA benchmarks. We find that (i) inducing values leads to expression of other related, and sometimes contrastive values, (ii) inducing positive values increases safety, and (iii) all values increase anthropomorphic language use, making models more validating and sycophantic.

Arnav Arora, Natalie Schluter, Katherine Metcalf +1

University of Copenhagen · 2Apple

LLM Sycophancy LLM Alignment Personality Modeling in Language Models LLM Safety

May 8, 2026cs.HC

Sycophantic AI makes human interaction feel more effortful and less satisfying over time

Millions of people now turn to artificial intelligence (AI) systems for personal advice, guidance, and support. Such systems can be sycophantic, frequently affirming users' views and beliefs. Across five preregistered studies (N = 3,075 participants, 12,766 human-AI conversations), including a three-week study with a census-representative U.S. sample, we provide longitudinal experimental evidence that sycophantic AI shifts how users approach their closest relationships. We show that sycophantic AI immediately delivers the emotional and esteem support users typically associate with close friends and family. Over three weeks of such interactions, users became nearly as likely to seek personal advice from sycophantic AI as from close friends and family, and reported lower satisfaction with their real-world social interactions. When given a choice among AI response styles, a majority preferred sycophantic AI -- not for the quality of its advice, but because it made them feel most understood. Together, these findings offer a relational account of AI sycophancy and its impacts.

Lujain Ibrahim, Franziska Sofia Hafner, Myra Cheng +5

University of Oxford. · Stanford University. · UK AI Security Institute.

LLM Sycophancy Human-AI Interaction

May 6, 2026cs.AI

When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models

This position paper argues that sycophancy in LLMs is a boundary failure between social alignment and epistemic integrity. Existing work often operationalizes sycophancy through external behavior such as agreement with incorrect user beliefs, position reversals, or deviation from an objective standard of correctness. These formulations capture only overt forms of the phenomenon and leave subtler boundary failures involving epistemic integrity and social alignment underspecified. We argue that sycophancy should not be understood as agreement alone, but as alignment behavior that displaces independent epistemic judgment. To clarify this boundary, we propose a three-condition framework for sycophancy. First, the user expresses a cue in the form of a belief, preference, or self-concept. Second, the model shifts toward that cue through alignment behavior. Third, this shift compromises epistemic accuracy, independent reasoning, or appropriate correction. We also introduce a taxonomy for classifying sycophancy, consisting of alignment targets, mechanisms, and severity. The paper concludes by discussing implications for alignment evaluation and argues for boundary-aware assessment, structured rubrics, and mitigation strategies, while situating these proposals alongside alternative views of sycophancy.

Jiechen Li, Catherine A. Barry, Rishika Randev +3

Duke University Durham, NC 27708 · ∗These authors contributed equally.

LLM Sycophancy LLM Alignment

May 5, 2026cs.CL

Auditing Stealth Sycophancy in Mental-Health Dialogue: Structured Clinical-State Diagnostics and Clean Matched Benchmarks

Mental-health dialogue models are increasingly evaluated by AI-based evaluators, yet these evaluators often treat surface empathy, supportiveness, or fluency as evidence of safety. In this paper, we study a hidden failure mode that we call implicit sycophancy: a response may appear empathetic while implicitly reinforcing catastrophizing, avoidance, hopeless prediction, or CBT-style labeling. To examine this problem, we introduce a diagnostic benchmark for implicit-sycophancy detection, built from three representative mental-health dialogue sources covering everyday peer support, counseling-style emotional support, and crisis-oriented interaction, and further construct a leakage-audited clean single-response matched benchmark with 500 contexts and 1,500 matched response windows. We then propose Dynamic Emotional Signature Graphs (DESG), a structured offline audit framework that separates LLM-based state extraction from final scoring and evaluates clinical direction through semantic, affective, and cognitive-distortion state transitions rather than free-form LLM judgment. Unlike metadata, surface-style, lexical, embedding, and rubric-LLM baselines, DESG scores the direction of clinical-state change induced by a response; on the leakage-audited clean matched benchmark, DESG-StateRisk improves over the strongest non-DESG baseline by 0.0488 macro-F1 and achieves the best harmful-risk detection result. These results suggest that evaluating implicit sycophancy requires explicit clinical-state modeling together with leakage checks, shortcut controls, and competitive baselines.

Tianze Han, Beining Xu, Hanbo Zhang +1

Shenzhen MSU-BIT University, Shenzhen, China

Mental Health Counseling LLM Sycophancy Emotional Support Conversation LLM Auditing Mental Health Clinical Language Model Evaluation

Apr 30, 2026cs.AI

Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor

Large language models (LLMs) are commonly evaluated for political bias based on their responses to fixed questionnaires, which typically place frontier models on the political left. A parallel literature shows that LLMs are sycophantic: they adapt their answers to the views, identities, and expectations of the user. We show that these findings are linked: standard political-bias audits partly capture sycophantic accommodation to the inferred auditor. We employ a factorial experiment across three major audit instruments--the Political Compass Test, the Pew Political Typology, and 1,540 partisan-benchmarked Pew American Trends Panel items--administered to six frontier LLMs while varying only the asker's stated identity (N = 30,990 responses). At baseline, all six models lean left. When the asker identifies as a conservative Republican, responses shift sharply: the share of items closer to Democrats falls by 28-62 percentage points, and all six models move right of center. A mirror-image progressive-Democrat cue produces little change; rightward accommodation is 8.0

\times

larger than leftward. When asked who the default asker is, models identify an auditor, researcher, or academic; when asked what answer that asker expects, they select the Democrat-coded option 75% of the time, nearly the rate under an explicit progressive cue. These patterns are inconsistent with a purely fixed model ideology and indicate that single-prompt audits capture an interaction between model and inferred interlocutor. Political bias in LLMs is therefore not a fixed point on an ideological scale but a response profile that must be mapped across realistic interlocutors.

Petter Törnberg, Michelle Schimmel

Institute of Logic, Language and Computation (ILLC), University of Amsterdam, Amsterdam, Netherlands

LLM Sycophancy Political Bias in Language Models Language Model Bias Evaluation Language Model Auditing

Apr 27, 2026cs.AI

The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications

Given the increased use of LLMs in financial systems today, it becomes important to evaluate the safety and robustness of such systems. One failure mode that LLMs frequently display in general domain settings is that of sycophancy. That is, models prioritize agreement with expressed user beliefs over correctness, leading to decreased accuracy and trust. In this work, we focus on evaluating sycophancy that LLMs display in agentic financial tasks. Our findings are three-fold: first, we find the models show only low to modest drops in performance in the face of user rebuttals or contradictions to the reference answer, which distinguishes sycophancy that models display in financial agentic settings from findings in prior work. Second, we introduce a suite of tasks to test for sycophancy by user preference information that contradicts the reference answer and find that most models fail in the presence of such inputs. Lastly, we benchmark different modes of recovery such as input filtering with a pretrained LLM.

Zhenyu Zhao, Aparna Balagopalan, Adi Agrawal +3

Writer, Inc.

Financial Services LLM Sycophancy LLM Agent Evaluation LLM Agent Safety

Apr 24, 2026cs.CY

Peer Identity Bias in Multi-Agent LLM Evaluation: An Empirical Study Using the TRUST Democratic Discourse Analysis Pipeline

The TRUST democratic discourse analysis pipeline exposes its large language model (LLM) components to peer model identity through multiple structural channels -- a design feature whose bias implications have not previously been empirically tested. We provide the first systematic measurement of identity-dependent scoring bias across all active identity exposure channels in TRUST, crossing four model families with two anonymization scopes across 30 political statements. The central finding is that single-channel anonymization produces near-zero bias effects, because individual channels act in opposite directions and cancel each other out -- a result that would lead an evaluator to conclude that identity bias is absent when it is not. Only full-pipeline anonymization reveals the true pattern: homogeneous ensembles amplify identity-driven sycophancy when model identity is fully visible, while the heterogeneous production configuration shows the reverse. Model choice matters independently: one tested model exhibits baseline sycophancy two to three times higher than the others and near-zero deliberative conflict on ideological topics, making it structurally unsuitable for pipelines where genuine inter-role disagreement is the intended quality mechanism. Three practical conclusions follow. First, heterogeneous model ensembles are structurally more robust than homogeneous ones, achieving higher consensus rates and lower identity amplification. Second, full-pipeline anonymization is required for valid bias measurement -- partial anonymization is insufficient and actively misleading. Third, these findings have direct implications for the validation of multi-agent LLM systems in quality-critical applications: a system validated under partial anonymization or with a homogeneous ensemble may pass validation while retaining structural identity bias invisible to single-channel measurement.

Juergen Dietrich

TRUST Project — democracy-intelligence.de

LLM Sycophancy Language Model Bias Evaluation Language Model Ensembles Multi-Agent LLMs

Apr 24, 2026cs.CL

How Large Language Models Balance Internal Knowledge with User and Document Assertions

Large language models (LLMs) often need to balance their internal parametric knowledge with external information, such as user beliefs and content from retrieved documents, in real-world scenarios like RAG or chat-based systems. A model's ability to reliably process these sources is key to system safety. Previous studies on knowledge conflict and sycophancy are limited to a binary conflict paradigm, primarily exploring conflicts between parametric knowledge and either a document or a user, but ignoring the interactive environment where all three sources exist simultaneously. To fill this gap, we propose a three-source interaction framework and systematically evaluate 27 LLMs from 3 families on 2 datasets. Our findings reveal general patterns: most models rely more on document assertions than user assertions, and this preference is reinforced by post-training. Furthermore, our behavioral analysis shows that most models are impressionable, unable to effectively discriminate between helpful and harmful external information. To address this, we demonstrate that fine-tuning on diverse source interaction data can significantly increase a model's discrimination abilities. In short, our work paves the way for developing trustworthy LLMs that can effectively and reliably integrate multiple sources of information. Code is available at https://github.com/shuowl/llm-source-balancing.

Shuowei Li, Haoxin Li, Wenda Chu +1

Santa Clara University · Nanyang Technological University · California Institute of Technology

LLM Sycophancy Knowledge Augmentation for Language Models Knowledge Conflicts in Language Models LLM Reliability LLM Safety

Apr 23, 2026cs.AI

When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure

Despite strong medical benchmark accuracy, LLMs can exhibit severe multi-turn sycophancy in clinical dialogue, abandoning initial correct diagnosis under escalating pressure. We propose \textbf{\textsc{Med-Stress}}, a targeted stress test framework that evaluates belief stability under escalating pressure. Across nine frontier large language models (LLMs), we find a clear dissociation between medical knowledge and robustness: high initial diagnostic capability does not imply high belief stability, yielding large knowledge-robustness gaps for several LLMs. To mitigate this failure mode, we propose a lightweight inference-time defense, \textbf{\texttt{RBED}} (\textbf{R}ole-\textbf{B}ased \textbf{E}pistemic \textbf{D}efense), and \textbf{\texttt{R-FT}} (\textbf{R}esilience-oriented \textbf{F}ine-\textbf{T}uning), a training-time approach that internalizes evidence-based resistance to pressure. Experiments show that \textbf{\texttt{R-FT}} nearly eliminates belief change and substantially improves robustness.

Boyu Xiao, Xiuqi Tian, Xuwen Song +4

Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, China

LLM Sycophancy Healthcare LLM Reliability Clinical Language Model Evaluation Language Model Robustness Medical LLMs

Apr 23, 2026cs.CL

Measuring Opinion Bias and Sycophancy via LLM-based Persuasion

Large language models increasingly shape the information people consume: they are embedded in search, consulted for professional advice, deployed as agents, and used as a first stop for questions about policy, ethics, health, and politics. When such a model silently holds a position on a contested topic, that position propagates at scale into users' decisions. Eliciting a model's positions is harder than it first appears: contemporary assistants answer direct opinion questions with evasive disclaimers, and the same model may concede the opposite position once the user starts arguing one side. We propose a method, released as the open-source llm-bias-bench, for discovering the opinions an LLM actually holds on contested topics under conditions that resemble real multi-turn interaction. The method pairs two complementary free-form probes. Direct probing asks for the model's opinion across five turns of escalating pressure from a simulated user. Indirect probing never asks for an opinion and engages the model in argumentative debate, letting bias leak through how it concedes, resists, or counter-argues. Three user personas (neutral, agree, disagree) collapse into a nine-way behavioral classification that separates persona-independent positions from persona-dependent sycophancy, and an auditable LLM judge produces verdicts with textual evidence. The first instantiation ships 38 topics in Brazilian Portuguese across values, scientific consensus, philosophy, and economic policy. Applied to 13 assistants, the method surfaces findings of practical interest: argumentative debate triggers sycophancy 2-3x more than direct questioning (median 50% to 79%); models that look opinionated under direct questioning often collapse into mirroring under sustained arguments; and attacker capability matters mainly when an existing opinion must be dislodged, not when the assistant starts neutral.

Rodrigo Nogueira, Giovana Kerche Bonás, Thales Sales Almeida +7

Maritaca AI · JusBrasil

LLM Sycophancy LLM Auditing Language Model Bias Evaluation Persuasion in Language Models Language Model Probing

Apr 22, 2026cs.LG

Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention

Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correct statements. We introduce dual-stance evaluation, which tests both stances of each topic, and apply it to centroid-difference steering on Llama-3-8B-Instruct. We find a dissociation: the model represents sycophantic and factual agreement in geometrically distinct subspaces, yet the steering direction projects equally onto both and cannot differentially target either. The direction accordingly reduces agreement with factually correct statements (e.g. that the Earth is round) as well as sycophantic ones. All other static properties of the two activation groups are matched, suggesting the behavioural dissociation arises from generation dynamics or from finer-grained structure that residual-stream analysis cannot resolve. The pattern illustrates a general gap: representations that are readable from activations may not be writable through them.

Matthew James Buchan

Independent Researcher, United Kingdom.

LLM Sycophancy Language Model Steering LLM Interpretability Causal Interventions in Language Models

Apr 21, 2026cs.CL

Durable Evaluation Framework: Adversarial Arbitration for Sycophancy Reduction in Large Language Models

RLHF-trained models are systematically biased toward agreement over accuracy, a structural property of the training process. We present Durable Evaluation Framework (DEF) Arbitration, a multi-agent architecture that mitigates identity-framed sycophancy by arbitrating between two models tuned to opposing DEFs, with a pragmatist synthesizer evaluating both arguments blind to their origins. This paper evaluates a prompt-based instantiation of DEF Arbitration. The key mechanisms are static DEF tuning, identity stripping before synthesis, single-round independent argumentation, and blind arbitration. We evaluate five instantiations on 200 stratified questions from SycophancyEval. All tested DEF variants (AnCifer, DeWin, FeynStein, BurGal, Trident) significantly outperform the single-model baseline (18.5%) and instructed-opposition baseline (29.0%), with DeWin achieving 48.5% accuracy (z=6.36, p<0.001 versus both). The variants are not significantly different from each other at n=200. The BurGal variant achieves 53.0% but functions as an architectural validity check; its consensus/heterodox axis structurally favors the heterodox model on every benchmark question. A pre-training floor affects an estimated 40% of questions; fine-tuned DEF models are the identified next step.

Sam Ryan

Novel Systems Engineering LLC

LLM Sycophancy Multi-Agent Debate Language Model Bias Evaluation

Apr 21, 2026cs.CL

Verbal tics in frontier language models: A critical review of current releases, research evidence, and public discussion

Repeated praise, canned reassurance, familiar contrasts, and conspicuous vocabulary are recurring subjects in discussions of large language models. Their interpretation depends on context: a conventional phrase may be useful, while a fluent answer may reinforce a false belief. This critical review examines linguistic habits and sycophancy across eight developer families: OpenAI, Anthropic, Google DeepMind, xAI, ByteDance, Moonshot AI, DeepSeek, and Xiaomi. We verify current public offerings against official release and API documentation, with an evidence cutoff of 1 October 2026. We synthesize research on lexical overrepresentation, stylistic variation, social warmth, and agreement, alongside benchmark methods and dated English and Chinese public discussions. The research reviewed documents recurring linguistic patterns and agreement that distorts judgment; comparable measurements of the newest releases are sparse in the retrieved set. Current user reports include both complaints and improved writing, with experiences varying by task and prompting. We propose separate measures of recurrence, contextual appropriateness, and belief distortion, with precise service records and language-specific annotation. This framework makes claims about writing quality and conversational reliability testable as model services change.

Shuai Wu, Xue Li, Zhijun Wang +4

LLM Evaluation LLM Sycophancy Language Modeling

Apr 21, 2026cs.LG

LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit

When a language model agrees with a user's false belief, is it failing to detect the error, or noticing and agreeing anyway? We show the latter. Across twelve open-weight models from five labs, spanning small to frontier scale, the same small set of attention heads carries a "this statement is wrong" signal, whether the model is evaluating a claim on its own or being pressured to agree with a user. Silencing these heads flips sycophantic behavior sharply while leaving factual accuracy intact, so the circuit controls deference rather than knowledge. Edge-level path patching confirms that the same head-to-head connections drive sycophancy, factual lying, and instructed lying. Opinion-agreement, where no factual ground truth exists, reuses these head positions but writes into an orthogonal direction, ruling out a simple "truth-direction" reading of the substrate. Alignment training leaves this circuit in place: an RLHF refresh cuts sycophantic behavior roughly tenfold while the shared heads persist or grow, a pattern that replicates on an independent model family and under targeted anti-sycophancy DPO. When these models sycophant, they register that the user is wrong and agree anyway.

Manav Pandey

Georgia Institute of Technology

LLM Sycophancy LLM Alignment Deception in Language Models Mechanistic Interpretability Attention Mechanisms Circuits in Language Models+1