Paper Citation Record · LEDGER

DPO-Shift: Shifting the Distribution of Direct Preference Optimization

As of 24 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 2 inbound Pith citation observations for arXiv:2502.07599.

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

pith.paper-citation-record.v1
2502.07599 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T12:17:46.052839Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:19:41.454892Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T10:28:54.031274Z

Reference resolution

41 of 41 outbound references displayed

verified exact3
verified fuzzy8
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 33145946-9ccf-4395-941c-5093e741f713 · outbound

This paper cites GPT-4 Technical Report.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.840955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63faaea3-55da-418b-a837-b8b4b46261b3 · outbound

This paper cites Llama 3 model card.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Llama 3 model card

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.846902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fa528fe-52bd-42ff-9cb5-4580d10ffaa2 · outbound

This paper cites Capybara-preferences dataset card.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Capybara-preferences dataset card

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:17:46.779862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ba312bda-118d-480d-a798-75fbcb774058 · outbound

This paper cites A general theoretical paradigm to understand learning from human preferences.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization A general theoretical paradigm to understand learning from human preferences

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.856797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b789d96-2093-4d08-9c54-ec647ad0fa42 · outbound

This paper cites Qwen Technical Report.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Qwen Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.861587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1c0063c-2605-4660-85a2-e3cd44243ef6 · outbound

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

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.867014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34ef2061-aab6-4200-b693-268954668416 · outbound

This paper cites an unresolved cited work.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.873041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 148100a8-e34a-4912-b8ec-1dc0f6cf402f · outbound

This paper cites Evaluation metrics for language models.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Evaluation metrics for language models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:17:46.745304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 48da12f1-a16a-4479-a2c2-b52e41046536 · outbound

This paper cites Deep reinforcement learning from human preferences.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Deep reinforcement learning from human preferences

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.882971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f4ec9a-402a-493b-9787-10a3d55970ce · outbound

This paper cites Perplexed: Understanding When Large Language Models are Confused.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Perplexed: Understanding When Large Language Models are Confused

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-08T12:17:46.496898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 10a41111-4a58-4256-869c-4013fd5d9ca8 · outbound

This paper cites UltraFeedback: Boosting language models with high-quality feedback.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization UltraFeedback: Boosting language models with high-quality feedback

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:17:46.720553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bbbc76a2-5801-4144-b6a0-5db54b7d0604 · outbound

This paper cites Enhancing chat language models by scaling high-quality instructional conversations.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Enhancing chat language models by scaling high-quality instructional conversations

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:17:46.704877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2396ef46-2d0e-4e60-8dbe-24000f16334e · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization KTO: Model Alignment as Prospect Theoretic Optimization

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.907909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39c339e4-edd7-42fb-97ce-a3791d515913 · outbound

This paper cites ORPO: Monolithic Preference Optimization without Reference Model.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization ORPO: Monolithic Preference Optimization without Reference Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.912780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76184030-189c-46ef-918c-4bfd064b0068 · outbound

This paper cites SDPO: Segment-Level Direct Preference Optimization for Social Agents.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization SDPO: Segment-Level Direct Preference Optimization for Social Agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.918129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b136f837-6d43-4c34-937a-3bc5eb491de4 · outbound

This paper cites Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.923786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5aa3f7ec-4432-493e-98b6-60b849829c99 · outbound

This paper cites SimPO: Simple Preference Optimization with a Reference-Free Reward.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization SimPO: Simple Preference Optimization with a Reference-Free Reward

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.928601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c695b3f-a832-4f63-a452-1d08566350ee · outbound

This paper cites Entropy Controllable Direct Preference Optimization.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Entropy Controllable Direct Preference Optimization

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-08T12:17:46.400700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c14b757c-8579-4c70-af67-3c2f211be6be · outbound

This paper cites Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke E.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke E

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:17:46.689536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f0d12657-a7e6-4a86-b414-7aeefe75b728 · outbound

This paper cites Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.943180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9b9d3f8-c4db-4d75-a847-131dd26a31a9 · outbound

This paper cites Pre-dpo: Improving data utilization in direct preference optimization using a guiding reference model.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Pre-dpo: Improving data utilization in direct preference optimization using a guiding reference model

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.949210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65119daf-0aba-4cb7-a45a-6001e6a64167 · outbound

This paper cites Iterative Reasoning Preference Optimization.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Iterative Reasoning Preference Optimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.953811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cc0fbaa-b4f8-4303-a375-4b58990c6ebf · outbound

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

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Disentangling Length from Quality in Direct Preference Optimization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.959380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a6b671e-0090-4735-9254-5d340e7d76f7 · outbound

This paper cites From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.964514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcdb08b6-9900-4f8e-a1a3-43257109423c · outbound

This paper cites Manning, and Chelsea Finn.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Manning, and Chelsea Finn

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.969176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d63e46b8-c36d-462a-b4de-750bbc12eb94 · outbound

This paper cites Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.973947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7acb93ba-52eb-43f3-aea2-2b3d17db54a2 · outbound

This paper cites Learning to summarize with human feedback.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Learning to summarize with human feedback

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.979808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26f9010d-7322-4a94-9531-3db1be88ae8c · outbound

This paper cites Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.985439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1708aeca-820c-4d29-93d4-736cf1eb84b1 · outbound

This paper cites Generalized Preference Optimization: A Unified Approach to Offline Alignment.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Generalized Preference Optimization: A Unified Approach to Offline Alignment

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.991858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13350852-ce03-4237-80ce-28b34add8a2a · outbound

This paper cites Llama 2: Open foundation and fine-tuned chat models, 2023.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Llama 2: Open foundation and fine-tuned chat models, 2023

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.998038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7448a94a-bc89-4a02-a58b-c3832af6a8ef · outbound

This paper cites Rush, and Thomas Wolf.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Rush, and Thomas Wolf

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:17:46.640454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4a88f863-0b9b-4fe8-9650-f4f08dd9e28e · outbound

This paper cites SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-08T12:17:46.162294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5983e2f6-f1c3-49aa-999c-9598cfd3d96f · outbound

This paper cites Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:46.012360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 631602a3-3634-47d5-a68d-f8891261281f · outbound

This paper cites A systematic evaluation of large language models of code.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization A systematic evaluation of large language models of code

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:17:46.621940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6b21bd03-5d6a-434e-8f60-6a9969484189 · outbound

This paper cites Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:46.022685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3486637-e626-491e-b325-76d1a306fcd6 · outbound

This paper cites Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:46.028385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1403d4b0-07a5-4db9-9c9d-63e497ddc699 · outbound

This paper cites Advancing LLM Reasoning Generalists with Preference Trees.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Advancing LLM Reasoning Generalists with Preference Trees

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:46.033521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b6cb968-5e4e-46a8-b591-1bf13cb00973 · outbound

This paper cites Judging LLM-as-a-judge with MT-Bench and Chatbot Arena.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Judging LLM-as-a-judge with MT-Bench and Chatbot Arena

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T12:17:46.606898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b26182b0-e13d-47b2-8538-0bb5063d22d7 · outbound

This paper cites an unresolved cited work.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-08T12:17:46.591538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b91271ad-6335-44da-a823-efee30f9354a · outbound

This paper cites an unresolved cited work.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-08T12:17:46.576011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4e3f4637-e232-4ed4-b1e0-d0973781cebb · outbound

This paper cites an unresolved cited work.

DPO-Shift: Shifting the Distribution of Direct Preference Optimization Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-08T12:17:46.559467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 5d220a40-9759-4e58-a761-1d70cbc63392 · inbound

Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment cites this paper.

Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment DPO-Shift: Shifting the Distribution of Direct Preference Optimization

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T21:19:41.454892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ec5bba3-48a6-487e-b041-1bc3367e23d9 · inbound

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs cites this paper.

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs DPO-Shift: Shifting the Distribution of Direct Preference Optimization

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-07T10:28:54.149778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.