Paper Citation Record · LEDGER

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability

As of 22 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 2 inbound Pith citation observations for arXiv:2510.12229.

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

pith.paper-citation-record.v1
2510.12229 v3

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T10:04:08.124917Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T22:20:53.464810Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-09T05:46:01.579330Z

Reference resolution

15 of 15 outbound references displayed

verified exact0
verified fuzzy0
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 19963716-f3d0-4db2-a663-672329b7f802 · outbound

This paper cites Addressing Moral Uncertainty using Large Language Models for Ethical Decision-Making.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Addressing Moral Uncertainty using Large Language Models for Ethical Decision-Making

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:07.130183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a334bba8-d244-413f-9e79-27b7ee69afae · outbound

This paper cites Mistral 7B.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Mistral 7B

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:07.482408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61b60131-a68b-46c5-9592-7dc3bb7f12f7 · outbound

This paper cites URL https://distill.pub/ 2020/circuits/zoom-in/.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability URL https://distill.pub/ 2020/circuits/zoom-in/

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:07.655520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1b90ac2-af4b-4981-91d6-2c43468eb6e7 · outbound

This paper cites Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Task.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Task

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:07.846936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4d23b16-2f90-42ed-a028-165c546272cf · outbound

This paper cites Sarfati, Y ., Hardy-Bayl´e, M.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Sarfati, Y ., Hardy-Bayl´e, M

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:07.898295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9563ab4b-bcc7-4fbd-b8be-149b0fb75df1 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Gemma 2: Improving Open Language Models at a Practical Size

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:07.979364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 425f9994-2666-456d-9267-2c710b28a798 · outbound

This paper cites Taxonomy of risks posed by lan- guage models.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Taxonomy of risks posed by lan- guage models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:08.039228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 457e262e-5331-48a7-ba88-877c2af58e10 · outbound

This paper cites acl-long.893/.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability acl-long.893/

Reference 893

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:06.984040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e57758-7181-4be4-8d6a-e94627284b89 · outbound

This paper cites Could a Large Language Model be Conscious?.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Could a Large Language Model be Conscious?

Reference 2005

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:06.629384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1741f6ed-a444-4df9-9ef3-1a013553e5a7 · outbound

This paper cites Towards Best Practices of Activation Patching in Language Models: Metrics and Methods.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Reference 2010

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:08.124917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec1a5368-4d93-46ef-9348-bc03d92d5fcf · outbound

This paper cites The Llama 3 Herd of Models.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability The Llama 3 Herd of Models

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:07.321726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a68d1b7-cf90-46d8-9ab4-3e89cbdff978 · outbound

This paper cites M., Gebru, T., McMillan-Major, A., and Shmitchell, S.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability M., Gebru, T., McMillan-Major, A., and Shmitchell, S

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:06.560346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59110f0d-e0b7-48c3-95af-bfa9a5a84f07 · outbound

This paper cites doi: 10.18653/v1/2023.acl-long.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability doi: 10.18653/v1/2023.acl-long

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:06.846244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5192ad6-599f-412c-8d58-0d48776bb6ed · outbound

This paper cites Interpreting Bias in Large Language Models: A Feature-Based Approach.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Interpreting Bias in Large Language Models: A Feature-Based Approach

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:07.765256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a2ef335-0406-48f7-87ce-ccb2a49563dd · outbound

This paper cites Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:06.753097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f702573e-df5f-4169-b928-02847faba96c · inbound

Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy cites this paper.

Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T22:20:53.464810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55550e9d-3148-46e8-95a7-d0387ade3479 · inbound

User identity conditions moral wrongness ratings in non-reasoning large language models cites this paper.

User identity conditions moral wrongness ratings in non-reasoning large language models Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-20T02:18:20.628178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.