Paper Citation Record · LEDGER

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

As of 18 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 13 inbound Pith citation observations for arXiv:2412.02802.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2412.02802 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T23:07:52.884555Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:28:02.977416Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-03T20:18:56.431431Z

Reference resolution

20 of 20 outbound references displayed

verified exact0
verified fuzzy11
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 41d56fb8-d173-48e2-8525-1184b3db9b92 · outbound

This paper cites Concrete Problems in AI Safety.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Concrete Problems in AI Safety

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T23:07:52.294834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd7454c2-73d1-4663-8d22-0fa70aed3a71 · outbound

This paper cites Germanpartiesqa: Benchmarking commercial large language models for political bias and sycophancy.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Germanpartiesqa: Benchmarking commercial large language models for political bias and sycophancy

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T23:07:52.345054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efb377b1-fd3c-47ce-9045-d36f310f2a66 · outbound

This paper cites From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T23:07:52.384855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efefbd2b-0aa9-48ea-baeb-1ca4861b4f91 · outbound

This paper cites Why ai alignment could be hard with modern deep learning.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Why ai alignment could be hard with modern deep learning

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:56.164807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5af45fde-4db4-4a63-b646-87ffb629c89d · outbound

This paper cites A diachronic perspective on user trust in AI under uncertainty.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model A diachronic perspective on user trust in AI under uncertainty

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T23:07:52.480715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36fe4c5d-c3af-41c1-a5a9-d8e3a3f930b7 · outbound

This paper cites Measures for explainable ai: Explanation goodness, user satisfaction, mental models, curiosity, trust, and human-ai performance.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Measures for explainable ai: Explanation goodness, user satisfaction, mental models, curiosity, trust, and human-ai performance

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:56.014834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bf4db862-7dfd-4d2d-80ae-ccb77d8b0295 · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:55.881231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f50d9d77-bbb3-4dcc-b8f3-3dbff547ac3e · outbound

This paper cites Ai alignment project ideas.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Ai alignment project ideas

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:55.734923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ebd186d5-b1c2-4cfb-ab70-fb51ac44faf2 · outbound

This paper cites Users do not trust recommendations from a large language model more than ai-sourced snippets.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Users do not trust recommendations from a large language model more than ai-sourced snippets

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:55.564731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9973b24c-fd4f-42ca-8604-9437cbbca544 · outbound

This paper cites Evaluating the impact of hallucinations on user trust and satisfaction in llm-based systems, 2024.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Evaluating the impact of hallucinations on user trust and satisfaction in llm-based systems, 2024

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:55.437957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f348ea7-628b-4d84-a9b7-f373d6617c5e · outbound

This paper cites Reducing sycophancy and improving honesty via activation steering.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Reducing sycophancy and improving honesty via activation steering

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:55.294873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 49b6ac4e-ceac-4755-849c-462cd380b69f · outbound

This paper cites Humans and automation: Use, misuse, disuse, abuse.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Humans and automation: Use, misuse, disuse, abuse

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:55.139772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 267d7f05-ebd8-43da-b6ba-3fad8ddb2ff5 · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Discovering Language Model Behaviors with Model-Written Evaluations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T23:07:52.742538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f99b0c37-6391-46e3-b966-8fd065709056 · outbound

This paper cites Take it, leave it, or fix it: Measuring productivity and trust in human-ai collaboration.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Take it, leave it, or fix it: Measuring productivity and trust in human-ai collaboration

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:54.974802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 75ec2b62-b6b1-46f6-8817-f30ca42b5027 · outbound

This paper cites Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T23:07:52.771778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1aea93e-4e00-4ca6-90a7-927213d6aca1 · outbound

This paper cites To Trust or Distrust Trust Measures: Validating Questionnaires for Trust in AI.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model To Trust or Distrust Trust Measures: Validating Questionnaires for Trust in AI

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T23:07:52.799862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65565c21-fce8-41c2-9746-b75d9a89dc97 · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Towards Understanding Sycophancy in Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T23:07:52.831154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67212891-ac7d-4f89-beac-2dc2458b455c · outbound

This paper cites Language models don't always say what they think: unfaithful explanations in chain-of-thought prompting.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Language models don't always say what they think: unfaithful explanations in chain-of-thought prompting

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:54.814741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7576a6c4-7f18-4c3e-9633-7fb79c3b04ac · outbound

This paper cites Simple synthetic data reduces sycophancy in large language models.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Simple synthetic data reduces sycophancy in large language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T23:07:52.860150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8d9d022-d77a-4d47-8c66-d9ae5a55c1fc · outbound

This paper cites Complacency and automation bias in the use of imperfect automation.

Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model Complacency and automation bias in the use of imperfect automation

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:07:54.654829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation 396c33a5-c1c3-4f93-b2f9-00dceda25f8d · inbound

Evaluating Intra-firm LLM Alignment Strategies in Business Contexts cites this paper.

Evaluating Intra-firm LLM Alignment Strategies in Business Contexts Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T14:28:02.977416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41ced416-2657-4ece-8c9c-b1bbb4e81b9c · inbound

Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages cites this paper.

Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T21:34:41.494909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f02f1022-4c18-4d22-ab55-f9ef267c6407 · inbound

Exploring and Mitigating Fawning Hallucinations in Large Language Models cites this paper.

Exploring and Mitigating Fawning Hallucinations in Large Language Models Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T13:11:15.316050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49c56f40-7189-4950-b57c-d3220822f4d8 · inbound

Effects of Personality- and Opinion-Alignment in Human-AI Interaction cites this paper.

Effects of Personality- and Opinion-Alignment in Human-AI Interaction Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T22:29:24.728117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b4607bc-8aab-42bf-ba4d-3ed064435992 · inbound

User Detection and Response Patterns of Sycophantic Behavior in Conversational AI cites this paper.

User Detection and Response Patterns of Sycophantic Behavior in Conversational AI Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-16T14:07:58.788592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 96bb7971-bd28-4e58-b58d-cda14825dc24 · inbound

The Differential Effects of Agreeableness and Extraversion on Older Adults' Perceptions of Conversational AI Explanations in Assistive Settings cites this paper.

The Differential Effects of Agreeableness and Extraversion on Older Adults' Perceptions of Conversational AI Explanations in Assistive Settings Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-15T15:06:09.865243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a625d785-5c59-43b3-b1b1-9550f36fc289 · inbound

SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy cites this paper.

SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-13T21:48:19.223534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 36150c99-1752-4b0f-85ce-21e65e12e0ef · inbound

Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models cites this paper.

Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:50:59.760895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 81302a98-6e87-445e-864a-1fff6ba97d96 · inbound

The Rise of Verbal Tics in Large Language Models: A Systematic Analysis Across Frontier Models cites this paper.

The Rise of Verbal Tics in Large Language Models: A Systematic Analysis Across Frontier Models Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-10T02:53:29.258669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 372689fc-f0a2-49e8-a8e7-15ecb9e463d1 · inbound

"I Don't Know" -- Towards Appropriate Trust with Certainty-Aware Retrieval Augmented Generation cites this paper.

"I Don't Know" -- Towards Appropriate Trust with Certainty-Aware Retrieval Augmented Generation Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:11:11.549198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 21fd159f-b0be-488a-99bb-f8f5f11b4a26 · inbound

EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium cites this paper.

EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:56:25.903071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d0213269-5e60-4375-b85b-728978290f9e · inbound

PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience cites this paper.

PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 103

Resolution: verified exact; arxiv_id, observed 2026-07-03T20:18:56.433064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 73cd2c75-f6fc-4342-b6f0-7d633783238b · inbound

Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups cites this paper.

Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T10:10:56.926040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.