Paper Citation Record · LEDGER

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models

As of 8 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2505.19743.

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

pith.paper-citation-record.v1
2505.19743 v3

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:11:32.239612Z

measured 32 of 32 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy13
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6d6a5bcf-1410-499e-9bee-80e9ba2d008d · outbound

This paper cites Llama 3 model card.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Llama 3 model card

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:34.576056Z

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 6604e4c7-4876-4fbf-a6c5-4753b52ba655 · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:30.354244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 897d858c-ec8d-4902-a479-ad3454ca6d16 · outbound

This paper cites A general theo- retical paradigm to understand learning from human pref- erences.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models A general theo- retical paradigm to understand learning from human pref- erences

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:34.317720Z

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 04fc6024-8a07-4f7e-bf80-f3e477e26742 · outbound

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

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:30.529078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d45dbd4-4bca-4e1b-ba73-570d344eedba · outbound

This paper cites Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:30.658985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 855cb21f-ee1f-4a9c-a45b-59058a3e097e · outbound

This paper cites Safe rlhf: Safe reinforcement learning from human feedback.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Safe rlhf: Safe reinforcement learning from human feedback

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:34.082016Z

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 589885e6-e3ec-489e-9626-de2308e31c5a · outbound

This paper cites Raft: Reward ranked finetuning for generative foundation model alignment.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Raft: Reward ranked finetuning for generative foundation model alignment

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:33.938139Z

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 39000e2c-02cc-43e3-bb45-c39de069dde3 · outbound

This paper cites Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:30.866015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae7fcb4f-528c-4d01-ac0c-f6371d9b54c0 · outbound

This paper cites Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:30.936931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f05f867-ff0e-4065-8f01-bf7651d187a3 · outbound

This paper cites PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.054317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bdf83ab-21be-4bb7-9887-959928d07895 · outbound

This paper cites Mistral 7B.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Mistral 7B

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.096508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0ebabd2-5a2f-4c99-8920-e91a99b028b2 · outbound

This paper cites Dynamic context selection for document-level neural machine translation via rein- forcement learning.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Dynamic context selection for document-level neural machine translation via rein- forcement learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:33.797114Z

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 67459871-29de-46ae-ba2d-8d2545b9a780 · outbound

This paper cites Rain: Your language mod- els can align themselves without finetuning.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Rain: Your language mod- els can align themselves without finetuning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:33.657948Z

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 a56194f8-74ef-4bd5-94c0-b158a810ad1d · outbound

This paper cites WebGPT: Browser-assisted question-answering with human feedback.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models WebGPT: Browser-assisted question-answering with human feedback

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.354337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91c21b9c-92ec-44b9-8eef-10ea4e1495ee · outbound

This paper cites Discovering language model behaviors with model-written evaluations.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Discovering language model behaviors with model-written evaluations

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:33.356856Z

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 50bee4c0-563f-436b-b0f4-554b9e7a3a4d · outbound

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

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.507646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a52bf91-962a-46af-be21-be10800abe81 · outbound

This paper cites Self-critiquing models for assisting human evaluators.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Self-critiquing models for assisting human evaluators

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.546765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aafe33f8-6e17-4fca-a305-083e30e4be93 · outbound

This paper cites Learning to summarize with human feedback.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Learning to summarize with human feedback

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:33.180261Z

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 56fc202a-a8ae-4449-9161-221c8110495a · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.652819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe761636-83cd-4a26-a6ab-06a340bb0116 · outbound

This paper cites Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.734703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 821655a1-b7eb-4960-af6c-5269549aa457 · outbound

This paper cites Aligning Large Language Models with Human: A Survey.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Aligning Large Language Models with Human: A Survey

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.809976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77e94b15-2a06-4775-8896-7597012b38aa · outbound

This paper cites Recursively Summarizing Books with Human Feedback.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Recursively Summarizing Books with Human Feedback

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.886088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6cd4066-6ef3-448c-a30e-c0710270a619 · outbound

This paper cites RRHF: Rank Responses to Align Language Models with Human Feedback without tears.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models RRHF: Rank Responses to Align Language Models with Human Feedback without tears

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.958446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbd60d84-94dd-4028-8a95-c4afe65da5e0 · outbound

This paper cites Token- level direct preference optimization.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Token- level direct preference optimization

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:32.992025Z

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 f7819f66-1b75-41c9-ad78-34db3d3a57bc · outbound

This paper cites Llamafactory: Unified efficient fine- tuning of 100+ language models.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Llamafactory: Unified efficient fine- tuning of 100+ language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:32.808085Z

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 c4de7e60-b185-4ffc-a5e9-0029ea61649a · outbound

This paper cites DPO Meets PPO: Reinforced Token Optimization for RLHF.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models DPO Meets PPO: Reinforced Token Optimization for RLHF

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:32.199965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b4deacb-e750-4ada-bfad-fd7e36233812 · outbound

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

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Fine-Tuning Language Models from Human Preferences

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:32.239612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65db4843-36f3-4006-a46d-b49cd14deb8a · outbound

This paper cites RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:31.238165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11622fac-69f3-4709-a420-7de135f080eb · outbound

This paper cites Training language models to follow instruc- tions with human feedback.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Training language models to follow instruc- tions with human feedback

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:33.510976Z

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 7300e744-7910-476a-b0be-1e611f510e7c · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Constitutional AI: Harmlessness from AI Feedback

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:30.606796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05331e07-6d4b-44e5-a284-a84a0b92d6de · outbound

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

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models Ultrafeedback: Boosting language models with high-quality feedback

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:34.197255Z

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 b4213521-25c1-4121-b9e0-0c12ca520057 · outbound

This paper cites aligner/aligner-7b-v1.0 · Hug- ging Face — huggingface.co.

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models aligner/aligner-7b-v1.0 · Hug- ging Face — huggingface.co

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:11:34.468851Z

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.

Pith citing papers

No inbound Pith citation observations are available.