Paper Citation Record · LEDGER

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness

As of 9 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2606.06306.

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

pith.paper-citation-record.v1
2606.06306 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T01:38:09.762751Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

23 of 23 outbound references displayed

verified exact3
verified fuzzy0
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch6

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b0d5b67d-10f3-44e5-904b-04617f2083bd · outbound

This paper cites 2021 , eprint =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness 2021 , eprint =

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb27f8f9-45c6-4f95-8e1f-463955c23c43 · outbound

This paper cites Bowman, Amanda Askell, Roger Grosse, Danny Hernandez, Deep Ganguli, Evan Hubinger, Nicholas Schiefer, and Jared Kaplan.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness Bowman, Amanda Askell, Roger Grosse, Danny Hernandez, Deep Ganguli, Evan Hubinger, Nicholas Schiefer, and Jared Kaplan

Reference 2

Resolution: verified exact; doi, observed 2026-06-28T01:41:29.367347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 55ffc81a-ed9b-4545-9fbc-fa61aa45057f · outbound

This paper cites AI Alignment Forum , year =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness AI Alignment Forum , year =

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f01077f-8ac5-4d37-94f1-e668fa955f61 · outbound

This paper cites Artificial intelligence risk management Framework ( AI RMF 1.0).

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness Artificial intelligence risk management Framework ( AI RMF 1.0)

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2336726-60f5-4556-98a7-097b24c3e6b6 · outbound

This paper cites The EU Artificial Intelligence (AI) Act: A Commentary , year =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness The EU Artificial Intelligence (AI) Act: A Commentary , year =

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24d1c980-b64f-489d-a318-5b08d19a55fd · outbound

This paper cites 2025 , eprint =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness 2025 , eprint =

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34050958-ba74-43e9-9cec-043c9ae9c6b1 · outbound

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

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness Simple synthetic data reduces sycophancy in large language models

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T13:06:58.895716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6ddcef69-b2fd-44fa-b575-cc3ec88bf35d · outbound

This paper cites Measuring sycophancy of language models in multi-turn dialogues.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness Measuring sycophancy of language models in multi-turn dialogues

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:06:58.893226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9798942a-5a43-4998-b600-5d41985206cd · outbound

This paper cites Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society , volume =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society , volume =

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89c9fd0c-059a-4d6c-bbd8-c4d472217f33 · outbound

This paper cites Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:06:58.890336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2cbe4604-e6d2-4587-8bf7-31eb0fc586d0 · outbound

This paper cites 2026 , eprint =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness 2026 , eprint =

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 280e9fbc-8d65-46d5-88a9-16eae717be98 · outbound

This paper cites Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval , pages =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval , pages =

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec18a396-0c9c-4b40-aab2-116f881acaa6 · outbound

This paper cites State Politics & Policy Quarterly , volume =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness State Politics & Policy Quarterly , volume =

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82b02aa8-860e-4de8-bc94-d4d48656c6ae · outbound

This paper cites 2022 , eprint =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness 2022 , eprint =

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a95f61fe-5b33-4012-8c90-05162c8b4be0 · outbound

This paper cites How Susceptible are.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness How Susceptible are

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc034183-ad67-4898-8f91-47f18999ddaa · outbound

This paper cites When truth is overridden: Uncovering the internal origins of sycophancy in large language models.arXiv preprint:2508.02087.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness When truth is overridden: Uncovering the internal origins of sycophancy in large language models.arXiv preprint:2508.02087

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:06:58.899093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ff144d59-061a-484c-a868-de03a741b287 · outbound

This paper cites Sycophantic AI decreases prosocial intentions and promotes dependence , volume =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness Sycophantic AI decreases prosocial intentions and promotes dependence , volume =

Reference 17

Resolution: verified exact; doi, observed 2026-06-28T01:41:29.369338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 38aaa39b-ddec-40b4-a28c-409a362b4d39 · outbound

This paper cites Intelligent Computing-Proceedings of the Computing Conference , pages =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness Intelligent Computing-Proceedings of the Computing Conference , pages =

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f183e93-0fbb-412e-bf2f-c04d2fc5529c · outbound

This paper cites When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:06:58.887637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 96436d9b-f555-484e-9f3d-1753bdea9f82 · outbound

This paper cites Parrot: Persuasion and agreement ro- bustness rating of output truth–a sycophancy robustness benchmark for llms.arXiv preprint arXiv:2511.17220.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness Parrot: Persuasion and agreement ro- bustness rating of output truth–a sycophancy robustness benchmark for llms.arXiv preprint arXiv:2511.17220

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:06:58.877159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c08a5a8c-fc06-47a2-a0c8-7ef3c4015555 · outbound

This paper cites 1980 , publisher =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness 1980 , publisher =

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bcc93ae-1fd3-41aa-a00f-47580818d0de · outbound

This paper cites International Conference on Learning Representations , volume =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness International Conference on Learning Representations , volume =

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-28T01:38:09.762751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09814197-7b05-4fe7-8bcf-f58c794d5035 · outbound

This paper cites arXiv preprint arXiv:2601.23096 , year =.

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness arXiv preprint arXiv:2601.23096 , year =

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-02T13:06:58.881277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.