Paper Citation Record · LEDGER

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models

As of 8 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 3 inbound Pith citation observations for arXiv:2507.15328.

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

pith.paper-citation-record.v1
2507.15328 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:41:34.332605Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T22:30:07.830390Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T14:18:22.813543Z

Reference resolution

28 of 28 outbound references displayed

verified exact0
verified fuzzy19
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bb35a071-1f85-42ee-babf-04e4b66fc3bb · outbound

This paper cites de University of Stuttgart Abstract – The guiding principle of AI alignment is to train large language models (LLMs) to be harmless, helpful, and honest (HHH).

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models de University of Stuttgart Abstract – The guiding principle of AI alignment is to train large language models (LLMs) to be harmless, helpful, and honest (HHH)

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.619401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2997e9a9-8fc8-41df-b360-df3a9121a46a · outbound

This paper cites hinder constructive, open-minded political discourse.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models hinder constructive, open-minded political discourse

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.573943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4a75d726-76d1-4059-9d3c-478f941f4937 · outbound

This paper cites social disturbances.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models social disturbances

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.564544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 31401c60-2a3d-4247-9a40-e701a48fcf51 · outbound

This paper cites integrity and trustworthiness.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models integrity and trustworthiness

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.554748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c79270fa-b42d-435d-b6f6-2d10630b26bd · outbound

This paper cites the diversity of political opinions in society.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models the diversity of political opinions in society

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.544779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f835ac86-c7d2-4aa4-bc8d-80fc615d6711 · outbound

This paper cites anti-woke.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models anti-woke

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.534121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f36302dd-1c1c-44cc-9ef3-47b0a7048167 · outbound

This paper cites 2023; Batzner et al.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models 2023; Batzner et al

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.525541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 399f9c9e-1b15-4688-99bf-267aee6897ed · outbound

This paper cites an unresolved cited work.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:41:34.507893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 27d52784-5d8f-4499-92e5-1ff93816da75 · outbound

This paper cites an unresolved cited work.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:41:34.499643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b7913bad-f7ef-4b3a-89cd-9ad39a26a653 · outbound

This paper cites an unresolved cited work.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:41:34.471824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e632c4e8-7522-4e0e-b613-46b28daa7c79 · outbound

This paper cites an unresolved cited work.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:41:34.463056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 715c685f-2389-4982-ba9e-f75f4e7b9361 · outbound

This paper cites 2024; Kim et al.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models 2024; Kim et al

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.443107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c49f0a78-fb7b-4669-bac3-3f6d88e34d07 · outbound

This paper cites truthful.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models truthful

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.417449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 20493268-f9b1-4807-8f17-6bab605c3057 · outbound

This paper cites harmful”, “helpful.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models harmful”, “helpful

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.406131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1495c21d-36eb-447d-a1e2-8fb73d53d248 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T15:41:34.317802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aee0481a-f462-4e2f-9270-4bd9e439af9d · outbound

This paper cites In Educational Policy 39 (3), pp.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models In Educational Policy 39 (3), pp

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.396313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9290f995-4ac4-4161-91df-229157a44fe6 · outbound

This paper cites The Alignment Problem from a Deep Learning Perspective.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models The Alignment Problem from a Deep Learning Perspective

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T15:41:34.328537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aab556a-c3e4-43d7-98f2-1ee7e52ff03e · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models Fine-Tuning Language Models from Human Preferences

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T15:41:34.332605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a49bbd6b-ddbc-45ec-8566-da37ac498297 · outbound

This paper cites Political Neutrality in AI Is Impossible- But Here Is How to Approximate It.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models Political Neutrality in AI Is Impossible- But Here Is How to Approximate It

Reference 722

Resolution: unresolved; no resolver link, observed 2026-08-06T15:41:34.324873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0898734f-7d8b-4c47-8808-0de7083013e4 · outbound

This paper cites an unresolved cited work.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models Unresolved cited work

Reference 1984

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:41:34.452403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 53df2a9c-8ec7-44f9-aa56-e6239b784a8c · outbound

This paper cites Systems and orientations characteristic of the political left tend to align more closely with many of these normative benchmarks than their right -wing counterparts.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models Systems and orientations characteristic of the political left tend to align more closely with many of these normative benchmarks than their right -wing counterparts

Reference 2009

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.490299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7dbc4c40-c2cf-4659-b50e-2f0078c210ba · outbound

This paper cites Moreover, conservatives tend to prefer clear, unambiguous an swers, whereas liberals 4 are more comfortable with nuance, complexity, and ambiguity (Salvi et al.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models Moreover, conservatives tend to prefer clear, unambiguous an swers, whereas liberals 4 are more comfortable with nuance, complexity, and ambiguity (Salvi et al

Reference 2012

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.480586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b5d15919-36cf-44f1-9fa1-0d2de2a2e4b2 · outbound

This paper cites 2024; Rozado 2023; Rotaru et al.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models 2024; Rozado 2023; Rotaru et al

Reference 2017

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.591542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9de62a38-0fb8-4a33-bf79-f754516c3290 · outbound

This paper cites woke” ideology. One could argue that this “left-wing alignment.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models woke” ideology. One could argue that this “left-wing alignment

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.433055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2dc27983-be1a-4518-944d-a353322820e2 · outbound

This paper cites 2020), constitutional AI (Bai et al.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models 2020), constitutional AI (Bai et al

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.610017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2bddc49c-932c-4dbe-9a29-c7eb6b9f4843 · outbound

This paper cites 2022; Bang et al.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models 2022; Bang et al

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.517090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 529fa86f-105b-4e96-967b-446ad2417f1e · outbound

This paper cites adverse political and electoral consequences.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models adverse political and electoral consequences

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.582156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 50f3c272-e5fb-4c25-a60b-3263161935ec · outbound

This paper cites At the same time, research on fairness biases in LLMs has spiked (Barocas et al.

On the Inevitability of Left-Leaning Political Bias in Aligned Language Models At the same time, research on fairness biases in LLMs has spiked (Barocas et al

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:41:34.600806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 8a9c1b6a-7047-4500-8f39-f9aacc4af56c · inbound

What Is The Political Content in LLMs' Pre- and Post-Training Data? cites this paper.

What Is The Political Content in LLMs' Pre- and Post-Training Data? On the Inevitability of Left-Leaning Political Bias in Aligned Language Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-24T00:23:04.188264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 49471c03-ac86-4619-ab60-e1f91ef0dbe3 · inbound

Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science cites this paper.

Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science On the Inevitability of Left-Leaning Political Bias in Aligned Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-24T00:23:04.188264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 50945763-94db-4610-a5fa-8ec267f622ae · inbound

M\"OVE: A Holistic LLM Benchmark for the German Public Sector cites this paper.

M\"OVE: A Holistic LLM Benchmark for the German Public Sector On the Inevitability of Left-Leaning Political Bias in Aligned Language Models

Reference 127

Resolution: verified exact; arxiv_id, observed 2026-07-24T00:23:04.188264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.