Paper Citation Record · LEDGER

Sycophancy in Large Language Models: Causes and Mitigations

As of 21 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 22 inbound Pith citation observations for arXiv:2411.15287.

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

pith.paper-citation-record.v1
2411.15287 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T14:36:32.089518Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 22 of 22 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:38:47.682170Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

19 of 19 outbound references displayed

verified exact1
verified fuzzy2
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

8
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation e33668a4-97e6-42c8-8973-12f4a7f9d16e · outbound

This paper cites AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions.

Sycophancy in Large Language Models: Causes and Mitigations AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:31.997089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85d03ed1-0b66-4306-a935-1957c427972e · outbound

This paper cites Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey.

Sycophancy in Large Language Models: Causes and Mitigations Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.003633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a1e9be8-b793-44b5-a10e-3d0d0e6cda72 · outbound

This paper cites arXiv preprint arXiv:2406.02630 (2024).

Sycophancy in Large Language Models: Causes and Mitigations arXiv preprint arXiv:2406.02630 (2024)

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.009862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9794ade3-6aba-4bcd-9a01-1de1a65163d7 · outbound

This paper cites Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.

Sycophancy in Large Language Models: Causes and Mitigations Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.014524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcbab968-e499-432c-bc5d-5c71eb470452 · outbound

This paper cites Understanding Knowledge Drift in LLMs through Misinformation.

Sycophancy in Large Language Models: Causes and Mitigations Understanding Knowledge Drift in LLMs through Misinformation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.020284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2def5796-26b9-438e-8497-2612da600ef3 · outbound

This paper cites Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment.

Sycophancy in Large Language Models: Causes and Mitigations Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.025197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38947fce-35a0-4478-806c-cf1bfbab7af0 · outbound

This paper cites Best Practices and Lessons Learned on Synthetic Data.

Sycophancy in Large Language Models: Causes and Mitigations Best Practices and Lessons Learned on Synthetic Data

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.030367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b4b2fea-0e14-4d9a-9071-ee5794eb6cb5 · outbound

This paper cites It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF.

Sycophancy in Large Language Models: Causes and Mitigations It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-08-12T14:36:32.528079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ee31fc52-b73d-42b7-839b-c398af5d521c · outbound

This paper cites arXiv preprint arXiv:2 406.03827 (2024).

Sycophancy in Large Language Models: Causes and Mitigations arXiv preprint arXiv:2 406.03827 (2024)

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:36:32.773107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e16d6739-9591-4fdc-8679-75b6c5bb904c · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Sycophancy in Large Language Models: Causes and Mitigations Towards Understanding Sycophancy in Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.045412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f53c5d9-1882-4d24-8a3b-7c0131bea1c7 · outbound

This paper cites Steering Without Side Effects: Improving Post-Deployment Control of Language Models.

Sycophancy in Large Language Models: Causes and Mitigations Steering Without Side Effects: Improving Post-Deployment Control of Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.050822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79833940-dd95-4353-bb30-e589ba0891fe · outbound

This paper cites an unresolved cited work.

Sycophancy in Large Language Models: Causes and Mitigations Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-12T14:36:32.755783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cc20c6f8-441b-4955-947a-d63d127288de · outbound

This paper cites Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting.

Sycophancy in Large Language Models: Causes and Mitigations Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.060454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d720d4a6-69b8-40e6-9668-40bfb6814041 · outbound

This paper cites arXiv preprint arXiv:2308 .03958 (2023).

Sycophancy in Large Language Models: Causes and Mitigations arXiv preprint arXiv:2308 .03958 (2023)

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:36:32.738494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5c2a08d9-1297-43c5-a6b1-ed261f913322 · outbound

This paper cites Language Models Learn to Mislead Humans via RLHF.

Sycophancy in Large Language Models: Causes and Mitigations Language Models Learn to Mislead Humans via RLHF

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.070436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f142288b-3c90-41f3-93cd-7619afc9ab42 · outbound

This paper cites ControlLM: Crafting Diverse Personalities for Language Models.

Sycophancy in Large Language Models: Causes and Mitigations ControlLM: Crafting Diverse Personalities for Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.075452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a5b669e-7d09-4269-82cd-cb1b31c2b6fa · outbound

This paper cites System 2 Attention (is something you might need too).

Sycophancy in Large Language Models: Causes and Mitigations System 2 Attention (is something you might need too)

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.080781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9bfe9e8-a229-446f-a121-ed966e622dbd · outbound

This paper cites arXiv preprint arXiv:2310.0217 4 (2023).

Sycophancy in Large Language Models: Causes and Mitigations arXiv preprint arXiv:2310.0217 4 (2023)

Reference 18

Resolution: verified exact; raw_fallback, observed 2026-08-12T14:36:32.410524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4aa870de-f9f3-4111-b5f8-dd99d9082c48 · outbound

This paper cites arXiv preprint arXiv:2408.11261 (2024).

Sycophancy in Large Language Models: Causes and Mitigations arXiv preprint arXiv:2408.11261 (2024)

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T14:36:32.089518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9a658642-bd01-46fc-afad-907ea24b4842 · inbound

Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems cites this paper.

Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems Sycophancy in Large Language Models: Causes and Mitigations

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T04:47:29.253647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b926d21-bbe1-47ce-8be4-18f9098e2038 · inbound

Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models cites this paper.

Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models Sycophancy in Large Language Models: Causes and Mitigations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T23:38:47.682170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c49d21e-223a-43e7-9924-9dc18488319f · inbound

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents cites this paper.

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Sycophancy in Large Language Models: Causes and Mitigations

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T20:28:15.680312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c20ba81-db54-447d-9537-25943cdfc6d8 · inbound

The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process cites this paper.

The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process Sycophancy in Large Language Models: Causes and Mitigations

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T11:54:15.223966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a998f7-9326-4ed9-9e4a-50e1f8790d2c · inbound

Teaching Astronomy with Large Language Models cites this paper.

Teaching Astronomy with Large Language Models Sycophancy in Large Language Models: Causes and Mitigations

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-19T10:17:15.305207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a3360c34-e303-4c04-801e-2d4a4865ed71 · inbound

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs cites this paper.

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs Sycophancy in Large Language Models: Causes and Mitigations

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T11:07:15.461973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 08ed9fed-2043-4474-bf2f-6e4a9c27f638 · inbound

"Check My Work?": Measuring Sycophancy in a Simulated Educational Context cites this paper.

"Check My Work?": Measuring Sycophancy in a Simulated Educational Context Sycophancy in Large Language Models: Causes and Mitigations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:36:07.166524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d470870f-794c-4c2f-bb0f-463c4619ece6 · inbound

The Rise of AI Companions: Interaction with AI Companions and Psychological Well-being cites this paper.

The Rise of AI Companions: Interaction with AI Companions and Psychological Well-being Sycophancy in Large Language Models: Causes and Mitigations

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T09:22:16.050122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e450fc3f-4ecc-42de-b366-3f1da7aab470 · inbound

LLMs in Coding and their Impact on the Commercial Software Engineering Landscape cites this paper.

LLMs in Coding and their Impact on the Commercial Software Engineering Landscape Sycophancy in Large Language Models: Causes and Mitigations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T23:40:59.632434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be411334-3402-45b3-8c6d-ce53abf7f192 · inbound

Potemkin Understanding in Large Language Models cites this paper.

Potemkin Understanding in Large Language Models Sycophancy in Large Language Models: Causes and Mitigations

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T22:30:31.121504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5e4330f-4c62-4e20-8c42-8eee2f5eaa92 · inbound

WebGuard: Building a Generalizable Guardrail for Web Agents cites this paper.

WebGuard: Building a Generalizable Guardrail for Web Agents Sycophancy in Large Language Models: Causes and Mitigations

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T16:12:49.594341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7b77eaf-3be0-4534-bf5c-c0599430eee2 · inbound

Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy cites this paper.

Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy Sycophancy in Large Language Models: Causes and Mitigations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T22:07:48.251798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c5c64fa-d185-4665-a0e6-798855228181 · inbound

Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models cites this paper.

Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models Sycophancy in Large Language Models: Causes and Mitigations

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-21T20:05:33.781032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7e33c09f-631a-4c54-868c-81bcf1538074 · inbound

AI as Equalizer or Amplifier? Task Complexity as the Moderating Factor for Human Expertise in Hybrid Intelligence Systems cites this paper.

AI as Equalizer or Amplifier? Task Complexity as the Moderating Factor for Human Expertise in Hybrid Intelligence Systems Sycophancy in Large Language Models: Causes and Mitigations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T07:16:37.803697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f67c44-b53d-4cb4-90e9-e1c4b6fd3e6c · inbound

Mitigating LLM biases toward spurious social contexts using direct preference optimization cites this paper.

Mitigating LLM biases toward spurious social contexts using direct preference optimization Sycophancy in Large Language Models: Causes and Mitigations

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:33:14.739471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6098520a-006c-4a4d-b39d-9719482955ca · inbound

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems cites this paper.

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems Sycophancy in Large Language Models: Causes and Mitigations

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T20:13:13.989942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8c7285b2-9049-4fd4-bcb4-834c5d121bd6 · inbound

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems cites this paper.

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems Sycophancy in Large Language Models: Causes and Mitigations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T16:57:39.842389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dc2144a-68e8-49ce-a36a-750ba357d67a · inbound

The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior cites this paper.

The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior Sycophancy in Large Language Models: Causes and Mitigations

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T22:10:50.098873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 920a1d73-7fc6-44d0-a17b-2360dbaebe69 · inbound

GroupEnvoy: A Conversational Agent Speaking for the Outgroup to Foster Intergroup Relations cites this paper.

GroupEnvoy: A Conversational Agent Speaking for the Outgroup to Foster Intergroup Relations Sycophancy in Large Language Models: Causes and Mitigations

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-10T08:07:25.384420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5af90a83-a452-4b76-9e54-03a51f4cd97d · inbound

Can AI Help You Get Over Your Breakup? One Session with a Belief-Reframing Chatbot Shows Sustained Distress Reduction cites this paper.

Can AI Help You Get Over Your Breakup? One Session with a Belief-Reframing Chatbot Shows Sustained Distress Reduction Sycophancy in Large Language Models: Causes and Mitigations

Reference 123

Resolution: verified exact; arxiv_id, observed 2026-05-12T00:16:25.854180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f993cb87-520e-424f-a43c-1c60670c0792 · inbound

When Support Escalates Distress: Regulation and Escalation in LLM Responses to Venting and Advice-Seeking cites this paper.

When Support Escalates Distress: Regulation and Escalation in LLM Responses to Venting and Advice-Seeking Sycophancy in Large Language Models: Causes and Mitigations

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:34:46.406329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 17914a78-19e3-46cc-9d70-bbe04f21a7bf · inbound

Training Large Language Models for Self-Explanation Faithfulness cites this paper.

Training Large Language Models for Self-Explanation Faithfulness Sycophancy in Large Language Models: Causes and Mitigations

Reference 119

Resolution: unresolved; no resolver link, observed 2026-08-01T08:36:28.389431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.