Paper Citation Record · LEDGER

MOSLIM:Align with diverse preferences in prompts through reward classification

As of 18 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 2 inbound Pith citation observations for arXiv:2505.20336.

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

pith.paper-citation-record.v1
2505.20336 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:31:05.857015Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:52:06.717285Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

15 of 15 outbound references displayed

verified exact0
verified fuzzy1
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 06d0a058-c3cb-4990-abfd-c649518d201e · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

MOSLIM:Align with diverse preferences in prompts through reward classification Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:04.575775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82af8d40-cac6-48eb-9022-41cfdd1e25c5 · outbound

This paper cites UltraFeedback: Boosting Language Models with Scaled AI Feedback.

MOSLIM:Align with diverse preferences in prompts through reward classification UltraFeedback: Boosting Language Models with Scaled AI Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:04.758999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70ae6733-b1b2-4dfb-88e2-ee7e74a226c5 · outbound

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

MOSLIM:Align with diverse preferences in prompts through reward classification Direct Language Model Alignment from Online AI Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:04.853691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10a44876-4afa-4080-af6c-b2b9eea30c26 · outbound

This paper cites Aligning to Thousands of Preferences via System Message Generalization.

MOSLIM:Align with diverse preferences in prompts through reward classification Aligning to Thousands of Preferences via System Message Generalization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:04.948809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62f35081-5fa3-4a89-8e4b-d5af209df259 · outbound

This paper cites Aligning Crowd Feedback via Distributional Preference Reward Modeling.

MOSLIM:Align with diverse preferences in prompts through reward classification Aligning Crowd Feedback via Distributional Preference Reward Modeling

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T14:31:06.429572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 44297587-a9cb-4257-854d-c403c37fff08 · outbound

This paper cites Training language models to follow instructions with human feedback.

MOSLIM:Align with diverse preferences in prompts through reward classification Training language models to follow instructions with human feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:05.137376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcc5c1fd-e4c7-47db-96c4-153fe6678fa9 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

MOSLIM:Align with diverse preferences in prompts through reward classification Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:05.324933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f5dbaf0-6f40-460e-90b1-29500f891c01 · outbound

This paper cites Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition.

MOSLIM:Align with diverse preferences in prompts through reward classification Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:05.462525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b969249-ef59-424f-acf7-a4c47ca8d4b7 · outbound

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

MOSLIM:Align with diverse preferences in prompts through reward classification Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:05.773320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b27f801b-3457-4fb5-8e2f-571b173eed9a · outbound

This paper cites In the Table 5 in Ap- pendix B, <preference n > represents a preference intensity of n (1 ≤ n < nmax), where a larger n indicates a higher intensity.

MOSLIM:Align with diverse preferences in prompts through reward classification In the Table 5 in Ap- pendix B, <preference n > represents a preference intensity of n (1 ≤ n < nmax), where a larger n indicates a higher intensity

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:31:06.696901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6ce1a30f-7a2f-4ed8-8f29-b91fe03a5eff · outbound

This paper cites Learning to summarize from human feedback.

MOSLIM:Align with diverse preferences in prompts through reward classification Learning to summarize from human feedback

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:05.558867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7323d348-b0fc-4847-9203-2a850d839a04 · outbound

This paper cites Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts.

MOSLIM:Align with diverse preferences in prompts through reward classification Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:05.677821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 310957cd-3dfd-4981-9928-d4c190692c08 · outbound

This paper cites RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation.

MOSLIM:Align with diverse preferences in prompts through reward classification RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:05.229990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ee2d541-a903-4e3b-a6b8-2481a81d7726 · outbound

This paper cites Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards.

MOSLIM:Align with diverse preferences in prompts through reward classification Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

Reference 2023

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T14:31:06.167627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 69706b5c-63c6-4108-9952-3e4aa2897442 · outbound

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

MOSLIM:Align with diverse preferences in prompts through reward classification Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:04.657355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bf9aa005-a21c-43fe-96c2-1927be2b84b1 · inbound

A Survey on Progress in LLM Alignment from the Perspective of Reward Design cites this paper.

A Survey on Progress in LLM Alignment from the Perspective of Reward Design MOSLIM:Align with diverse preferences in prompts through reward classification

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T00:52:06.717285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2de5b500-11de-4a72-8e35-5b040521bc9c · inbound

One Model for All: Multi-Objective Controllable Language Models cites this paper.

One Model for All: Multi-Objective Controllable Language Models MOSLIM:Align with diverse preferences in prompts through reward classification

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-10T20:35:45.814908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.