Paper Citation Record · LEDGER

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework

As of 7 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 1 inbound Pith citation observation for arXiv:2506.02460.

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

pith.paper-citation-record.v1
2506.02460 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:29:04.351940Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-13T05:26:06.829382Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy2
unresolved26
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bb2b1986-2a73-4238-acb4-fad48e5da3eb · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:01.842073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aa5008f-3aad-4325-8681-3801bdc0ca56 · outbound

This paper cites RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:01.157653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aa4e8e9-8960-4ae0-a1c0-3e5742328263 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:29:06.185150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bc8199fa-d576-474c-9d33-ab98dd4e513b · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:29:05.919249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 171d31b1-9863-4c5e-b59c-e5f1252dde59 · outbound

This paper cites Merging Multi-Task Models via Weight-Ensembling Mixture of Experts.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Merging Multi-Task Models via Weight-Ensembling Mixture of Experts

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T11:29:04.618001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0430879d-abbe-4953-9680-9ecb03056df2 · outbound

This paper cites LaMDA: Language Models for Dialog Applications.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework LaMDA: Language Models for Dialog Applications

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:01.610048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce66d95-0fd3-4578-9292-8bf08f438808 · outbound

This paper cites down_proj.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework down_proj

Reference 7

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T11:29:06.555858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1a8efca2-8ec7-4920-9761-d5f159216e85 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:29:05.703389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b607c745-4ce3-4803-a085-290c575d85fb · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:01.974051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16d55d80-f1d4-460a-af2d-6b1b38aba57d · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:02.866717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f9389c9-48e1-4ae4-93ea-1a8d197cb92f · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:02.946311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b127cda-e2dd-4894-978f-d7d9e48f9c68 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:02.273505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ae837ae-f25d-48b0-8281-ef0e67387472 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:02.412666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63d8ef9e-b8ee-49e5-be72-023d3d818da5 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:02.518248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11b0d200-ccfa-40b8-acad-6ab536092ff3 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:02.757009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4856d297-4be8-4a96-b1b3-38f67330b6dd · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:03.016592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ed653ce-7590-4888-9262-c2b378a33e76 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:03.132466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cfb2568-389b-4830-b96b-2132da3287d0 · outbound

This paper cites A safe and harmless response should skillfully navigate these subjects, showcasing globally acceptable values.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework A safe and harmless response should skillfully navigate these subjects, showcasing globally acceptable values

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:05.472301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ca24d825-d858-4790-9bf9-c1e6e9405578 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:29:05.314381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6d2b1923-9a34-4757-9f75-87eb70fa4a5c · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:03.505789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3003033a-3b4f-4829-ac9b-e0a285322b84 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:03.652989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3cf01f7-bed6-40d6-88a4-9e6174cfc23f · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:03.747503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cabe24b1-ce1e-43e3-a5a7-935920a83c10 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:03.835256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf1d51a2-cd8c-4ad3-bbd7-be7bdcf08504 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:03.949790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0a472a2-f57f-4617-807b-a4f1497e6308 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:29:05.104390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5ec9fe74-efc0-4ee2-97ab-4ff3b9b4db22 · outbound

This paper cites an unresolved cited work.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:04.208734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a5f1b79-fda8-4b06-886b-46512f984a93 · outbound

This paper cites A helpful and quality response should address these subjects diligently, demonstrating prowess in delivering timely, accurate, and respectful responses to users.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework A helpful and quality response should address these subjects diligently, demonstrating prowess in delivering timely, accurate, and respectful responses to users

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:29:04.954417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a76c2dc1-1aba-4b8a-88f1-67ae4cc22924 · outbound

This paper cites Disentangling Length from Quality in Direct Preference Optimization.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Disentangling Length from Quality in Direct Preference Optimization

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:01.345378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02535d01-7e76-49d4-837d-0168cc1f1cb3 · outbound

This paper cites Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:01.233545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f366d40f-8412-423a-8efd-6d89fba3a5ef · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T11:29:01.068351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a709ed57-33f9-4518-9e36-356ac925cf97 · inbound

Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints cites this paper.

Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework

Reference 85

Resolution: unresolved; no resolver link, observed 2026-07-13T05:26:06.829382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.