Paper Citation Record · LEDGER

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization

As of 7 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 2 inbound Pith citation observations for arXiv:2506.08712.

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

pith.paper-citation-record.v1
2506.08712 v2

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:14:45.567616Z

measured 51 of 51 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T10:01:59.503415Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T14:02:39.828118Z

Reference resolution

49 of 49 outbound references displayed

verified exact1
verified fuzzy21
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1792dcec-7e4b-485d-aab6-2652c6154666 · outbound

This paper cites Explaining individual predictions when features are dependent: More accurate approximations to shapley values.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Explaining individual predictions when features are dependent: More accurate approximations to shapley values

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.444061Z

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 98329f87-3bfb-457c-ba45-3f3c6e1eacf2 · outbound

This paper cites Llama 3 model card.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Llama 3 model card

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:41.672739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 425b234e-dc88-4f52-914a-71c22079b1b3 · outbound

This paper cites Mitigating reward over-optimization in direct alignment algorithms with adaptive importance sampling, 2025.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Mitigating reward over-optimization in direct alignment algorithms with adaptive importance sampling, 2025

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.431146Z

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 1638c1d0-5da9-4405-87c8-ac49348bd144 · outbound

This paper cites G., Guo, Z.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization G., Guo, Z

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.423282Z

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 24dd7f57-28c4-4fe8-9074-5489596df715 · outbound

This paper cites an unresolved cited work.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:42.023438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fceb882e-572d-44f2-beca-7305daa69a4c · outbound

This paper cites Step-level value preference optimization for mathematical reasoning.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Step-level value preference optimization for mathematical reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:42.135215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeb05f53-2f33-4bc0-b3c9-4eb5bc98e9c0 · outbound

This paper cites F., Leike, J., Brown, T., Martic, M., Legg, S., and Amodei, D.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization F., Leike, J., Brown, T., Martic, M., Legg, S., and Amodei, D

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.415696Z

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 95b809b0-5d62-4004-b9d9-101bc6a66065 · outbound

This paper cites Ultrafeedback: Boosting language models with high-quality feedback, 2023.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Ultrafeedback: Boosting language models with high-quality feedback, 2023

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.408306Z

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 7e194a62-4662-4361-ba68-22a6d3f5ea1d · outbound

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

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Enhancing chat language models by scaling high-quality instructional conversations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:42.398724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45141898-afe8-484c-8e62-c08716403b3e · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:42.513413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da680899-0219-4152-ad23-3e93ca90f203 · outbound

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

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization KTO: Model Alignment as Prospect Theoretic Optimization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:42.597895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31236e31-6e00-4b39-85ac-7f5232678988 · outbound

This paper cites Scaling laws for reward model overoptimization.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Scaling laws for reward model overoptimization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:42.724379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cda1935b-ddae-4a4b-8f78-97fbe109079d · outbound

This paper cites Beyond imitation: Leveraging fine-grained quality signals for alignment.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Beyond imitation: Leveraging fine-grained quality signals for alignment

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.395535Z

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 a463a060-2d3c-49a0-b719-d5e49148b80e · outbound

This paper cites A probabilistic earley parser as a psycholinguistic model.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization A probabilistic earley parser as a psycholinguistic model

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.387379Z

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 4bfa7d60-0423-4c83-aebd-ddfe0126531f · outbound

This paper cites Reference-free monolithic preference optimization with odds ratio.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Reference-free monolithic preference optimization with odds ratio

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.379614Z

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 0350f2ed-d3ce-4d3c-830c-19bf1471817b · outbound

This paper cites and Levy, R.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization and Levy, R

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.371360Z

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 cc52e0c3-8bb3-4d94-a507-dffcc102d1e6 · outbound

This paper cites Mistral 7B.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Mistral 7B

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:43.201027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19fd706-3403-47a2-ad12-cb865ce56a1b · outbound

This paper cites Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:43.248348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20b7bea3-d90f-4df8-87b0-84308a90de37 · outbound

This paper cites E., and Stoica, I.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization E., and Stoica, I

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.363481Z

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 4e3df7f6-7a62-4f25-8a5d-58e625bfe14f · outbound

This paper cites an unresolved cited work.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:14:47.355563Z

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 ebe34097-d2cb-4aaa-8b22-31ada1e6919a · outbound

This paper cites Not all tokens are what you need for pretraining.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Not all tokens are what you need for pretraining

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.347856Z

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 35ed17eb-b8c4-4dc6-a9fe-754b7d2fe017 · outbound

This paper cites Provably mitigating overoptimization in RLHF : Your SFT loss is implicitly an adversarial regularizer.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Provably mitigating overoptimization in RLHF : Your SFT loss is implicitly an adversarial regularizer

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.340004Z

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 c436c405-a559-4406-a993-cd241f3d01e9 · outbound

This paper cites and Hutter, F.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization and Hutter, F

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:43.624256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1adf573f-560b-4750-9223-cce8d4ca61cf · outbound

This paper cites an unresolved cited work.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:14:47.326955Z

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 00841d81-e6b7-49be-92af-ad2c92ce077d · outbound

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

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Sim PO : Simple preference optimization with a reference-free reward

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.318519Z

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 0be6bca5-b5ca-4bc2-8d9a-e9b77595f50f · outbound

This paper cites and Frank, S.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization and Frank, S

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:43.851661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3e0bd5a-75e2-468e-b903-a10285da3a45 · outbound

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

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization F., Leike, J., and Lowe, R

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.309553Z

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 2ee4273c-88b4-4a4d-9b2c-3d9c1bf7385f · outbound

This paper cites an unresolved cited work.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:14:47.262125Z

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 51e5e0f4-f6c6-48d5-9ce1-3c8eade8b949 · outbound

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

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Disentangling Length from Quality in Direct Preference Optimization

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:44.113845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99509864-b239-4a70-b17e-fc59fcc97449 · outbound

This paper cites B., Finn, C., and Niekum, S.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization B., Finn, C., and Niekum, S

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:47.059754Z

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 97ba12ec-4d95-47d8-8976-42f0e7f567b6 · outbound

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

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization D., Ermon, S., and Finn, C

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:46.766693Z

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 84fcbaca-6bd8-4148-bf89-5d8863154608 · outbound

This paper cites an unresolved cited work.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:14:46.666687Z

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 58b40bde-26e0-4200-923a-e26b358609f2 · outbound

This paper cites S., and Martin, A.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization S., and Martin, A

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:44.448597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cbce2f8-8b15-43d9-93b5-5f33853423d1 · outbound

This paper cites an unresolved cited work.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:44.525429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db5ae8f2-5af7-4907-8de6-8a392005d2f9 · outbound

This paper cites Trl: Transformer reinforcement learning.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Trl: Transformer reinforcement learning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:44.606004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5991f4c3-c998-4191-811e-7aca3019706c · outbound

This paper cites V., Murray, K., and Kim, Y.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization V., Murray, K., and Kim, Y

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:46.544726Z

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 8ad94440-41a3-4cd0-9335-cea3803121d6 · outbound

This paper cites Selective preference optimization via token-level reward function estimation.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Selective preference optimization via token-level reward function estimation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:44.737682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34656020-91f9-4927-a40e-e1992ba9a49a · outbound

This paper cites S., Hasegawa-Johnson, M.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization S., Hasegawa-Johnson, M

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:46.416795Z

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 d628485e-9912-4853-92ab-417c060d13ae · outbound

This paper cites S., Eom, S., Han, G., Nam, D., Jo, D., On, K.-W., Hasegawa-Johnson, M., Kim, S., and Yoo, C.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization S., Eom, S., Han, G., Nam, D., Jo, D., On, K.-W., Hasegawa-Johnson, M., Kim, S., and Yoo, C

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:44.866870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 683d2268-77fb-4ccf-95d4-895c8b07727f · outbound

This paper cites ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:44.934080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a63adae7-2697-41d5-b8ca-70c8752b2ccf · outbound

This paper cites C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:45.017306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af5f835a-0a5b-41ae-ad1d-c0f68a006d57 · outbound

This paper cites S., Kim, J., and Yoo, C.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization S., Kim, J., and Yoo, C

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:45.080901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77f05230-c189-4624-9aff-b930a294cd2c · outbound

This paper cites Tpc: Test-time procrustes calibration for diffusion-based human image animation.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Tpc: Test-time procrustes calibration for diffusion-based human image animation

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:46.318669Z

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 bba0a0e7-f868-48a1-bac1-32d45411538f · outbound

This paper cites RRHF : Rank responses to align language models with human feedback.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization RRHF : Rank responses to align language models with human feedback

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:46.199167Z

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 1eeb1d21-fd0d-487f-a370-57350e86ea35 · outbound

This paper cites Token-level direct preference optimization.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Token-level direct preference optimization

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:14:46.081029Z

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 1dc57259-667c-4d60-b5b1-f7b8a9949c6b · outbound

This paper cites SLiC-HF: Sequence Likelihood Calibration with Human Feedback.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization SLiC-HF: Sequence Likelihood Calibration with Human Feedback

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:45.342641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e796a6b-07b7-440a-873a-5c8207e6972e · outbound

This paper cites P., Zhang, H., Gonzalez, J.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization P., Zhang, H., Gonzalez, J

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:45.422180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cb49ef8-9c9b-4f85-9bb5-73958cbf26a9 · outbound

This paper cites T-REG: Preference Optimization with Token-Level Reward Regularization.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization T-REG: Preference Optimization with Token-Level Reward Regularization

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:14:45.733451Z

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 a0194a21-5383-4b36-b536-83db9bb9b377 · outbound

This paper cites write newline.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization write newline

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:45.567616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 71ed9b45-e61e-4f44-81eb-d7947419bbf3 · inbound

Failure Modes of Maximum Entropy RLHF cites this paper.

Failure Modes of Maximum Entropy RLHF ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-18T14:02:39.830504Z

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 bf7f5771-d720-4a92-87dc-47e4c6c247e1 · inbound

Normalized Rewards for Preference Optimization cites this paper.

Normalized Rewards for Preference Optimization ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T10:01:59.503415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.