Paper Citation Record · LEDGER

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

As of 16 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 2 inbound Pith citation observations for arXiv:2506.14574.

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

pith.paper-citation-record.v1
2506.14574 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:59:20.206994Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T14:59:12.210012Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T10:48:02.099479Z

Reference resolution

38 of 38 outbound references displayed

verified exact0
verified fuzzy21
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3ad100d9-c45f-4638-9378-5ed9748e2569 · outbound

This paper cites Hindsight experience replay.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Hindsight experience replay

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.665968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bbd70215-91af-4951-b798-b836fcaee5dd · outbound

This paper cites an unresolved cited work.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:59:20.655381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c9fa6ee3-4026-412a-8da2-bd38ac6842fd · outbound

This paper cites On the weaknesses of reinforcement learning for neural machine translation.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization On the weaknesses of reinforcement learning for neural machine translation

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.644355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 78c8d9a9-286d-4134-ad09-942f9483a6d4 · outbound

This paper cites Ultrafeedback: Boosting language models with scaled AI feedback.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Ultrafeedback: Boosting language models with scaled AI feedback

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.633850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 44c41176-263a-4e64-8e87-36373369656c · outbound

This paper cites Model alignment as prospect theoretic optimization.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Model alignment as prospect theoretic optimization

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.615533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f0071c97-0b26-4991-92a9-674b2c2c068b · outbound

This paper cites The Llama 3 Herd of Models.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.079682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64b30941-1df2-4f31-a4a2-c9c9e7725f52 · outbound

This paper cites Direct Language Model Alignment from Online AI Feedback.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Direct Language Model Alignment from Online AI Feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.083973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a540d8e-872c-4673-887f-cbc3c8e08264 · outbound

This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.087957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d123037-c166-44dc-b0d0-637531a95bbc · outbound

This paper cites A., Choi, Y., and Hajishirzi, H.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization A., Choi, Y., and Hajishirzi, H

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.602280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fe5cdfaf-9896-4941-b5d5-01f5ff0bbc9b · outbound

This paper cites an unresolved cited work.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:59:20.591409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dd0ac76e-306c-4b3b-9352-4790887ba812 · outbound

This paper cites E., and Stoica, I.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization E., and Stoica, I

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.578932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7110caa9-8fb5-429d-8bf3-8fa3b2bd4db9 · outbound

This paper cites an unresolved cited work.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:59:20.564851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fe53e676-c947-4b41-82fd-b97fbc51d34f · outbound

This paper cites and Hutter, F.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization and Hutter, F

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.108793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde593bf-cd05-4d12-950e-4507bc753d8c · outbound

This paper cites Sim PO : Simple preference optimization with a reference-free reward.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Sim PO : Simple preference optimization with a reference-free reward

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.113317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a2bf27-688d-492d-84eb-f995dd1303ed · outbound

This paper cites Aligning CodeLLMs with Direct Preference Optimization.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Aligning CodeLLMs with Direct Preference Optimization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.116800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2ca7894-93c3-4ac1-8e17-1a2e6d2f3313 · outbound

This paper cites GPT-4 Technical Report.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization GPT-4 Technical Report

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.121968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cc2a536-2fbe-46f6-b235-e98933f2f72b · outbound

This paper cites F., Leike, J., and Lowe, R.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization F., Leike, J., and Lowe, R

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.540547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6f390981-a170-46a6-9d8c-5abff0cba0ec · outbound

This paper cites Token-level Proximal Policy Optimization for Query Generation.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Token-level Proximal Policy Optimization for Query Generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.130052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5503b1c-4266-461c-b049-1f5c68aa6279 · outbound

This paper cites Disentangling length from quality in direct preference optimization.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Disentangling length from quality in direct preference optimization

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.528127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d429dbc8-4ba8-4243-822c-5e29a3926c03 · outbound

This paper cites D., Ermon, S., and Finn, C.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization D., Ermon, S., and Finn, C

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.515215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cda84a96-082f-4e47-9b10-43126acd6890 · outbound

This paper cites From r to q^* : Your language model is secretly a q-function.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization From r to q^* : Your language model is secretly a q-function

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.504867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ec904eb3-fa10-4f52-bd62-24135df9f95e · outbound

This paper cites Proximal Policy Optimization Algorithms.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Proximal Policy Optimization Algorithms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.146238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7ef3a5c-3826-4a0a-b3ad-cb6aa5906d36 · outbound

This paper cites Earlier tokens contribute more: Learning direct preference optimization from temporal decay perspective.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Earlier tokens contribute more: Learning direct preference optimization from temporal decay perspective

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.491433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ed1b7731-cd1e-4065-8a89-1e86b47def95 · outbound

This paper cites V., Kostrikov, I., Su, Y., Yang, S., and Levine, S.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization V., Kostrikov, I., Su, Y., Yang, S., and Levine, S

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.477722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 61174b07-3329-4789-bbaf-2071270ecefb · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Gemini: A Family of Highly Capable Multimodal Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.157866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17b3cf86-684d-4a55-b122-5f7dfc24864e · outbound

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

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Gemma 2: Improving Open Language Models at a Practical Size

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.161900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2bf55f2-6097-4376-ae9c-2fba496a0a3d · outbound

This paper cites D., and Finn, C.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization D., and Finn, C

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.466316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bb49bab6-7658-4085-94fe-bbcd71b8728c · outbound

This paper cites Interpretable preferences via multi-objective reward modeling and mixture-of-experts.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Interpretable preferences via multi-objective reward modeling and mixture-of-experts

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.455391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 51e64da4-8ebd-4d91-91a5-c7829650e1d4 · outbound

This paper cites A., Ostendorf, M., and Hajishirzi, H.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization A., Ostendorf, M., and Hajishirzi, H

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.443704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5102d338-e563-4f37-a5b3-c0f4b54cfe73 · outbound

This paper cites Inverse- Q *: Token level reinforcement learning for aligning large language models without preference data.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Inverse- Q *: Token level reinforcement learning for aligning large language models without preference data

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.431957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ce39aa76-ffb9-4e6f-98a2-3b7aea2c304b · outbound

This paper cites Preference-grounded token-level guidance for language model fine-tuning.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Preference-grounded token-level guidance for language model fine-tuning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.418301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 48ac8dcc-c5fb-46f1-afa3-646180f2d26b · outbound

This paper cites A dense reward view on aligning text-to-image diffusion with preference.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization A dense reward view on aligning text-to-image diffusion with preference

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.407009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 87939929-964a-4e5a-88ea-1058304cd6c7 · outbound

This paper cites Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.189439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73fd95e3-9db9-4fb9-96f6-ef65d94566d2 · outbound

This paper cites Token-level direct preference optimization.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Token-level direct preference optimization

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.396281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 30e4808d-3d42-4cd7-9e0e-17f50d4987e8 · outbound

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

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Judging LLM -as-a-judge with MT-Bench and Chatbot Arena

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.385309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f48c2fb8-b56e-43e0-8128-5d015c50ee54 · outbound

This paper cites DPO meets PPO : Reinforced token optimization for RLHF.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization DPO meets PPO : Reinforced token optimization for RLHF

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:59:20.374564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5d5d3081-9b40-43e8-8315-b047e71bbd0e · outbound

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

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization Fine-Tuning Language Models from Human Preferences

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.203188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4428b8cf-84ce-460f-9649-6b7264d56101 · outbound

This paper cites write newline.

TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization write newline

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T19:59:20.206994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 84ec1dfe-f34e-4d75-8df3-c366e6e177a6 · inbound

Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs cites this paper.

Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:48:02.101463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 053fcd64-447e-461e-b378-fd25c27137ca · inbound

Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization cites this paper.

Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T14:59:12.210012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.