MPO: Multilingual Safety Alignment via Reward Gap Optimization | Paper Citation Record

Observation 497f8a2f-4be6-44e1-808b-3a73f6558898 · outbound

This paper cites online" 'onlinestring :=.

MPO: Multilingual Safety Alignment via Reward Gap Optimization online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:24.456676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d8ff080-d982-4309-874d-06424dada9cc · outbound

This paper cites write newline.

MPO: Multilingual Safety Alignment via Reward Gap Optimization write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:24.506655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba7ea19-07cc-4635-b2b1-c6ff5343566f · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:24.560690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 101214ea-f3e7-4c4c-8879-a7ccb09cf00a · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:24.638462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feed01be-d34d-4d8e-953f-9564d0c08325 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:24.710928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1665e839-c1eb-424d-bf25-d19453b49c01 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:24.789514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dbbf828-86a8-466a-a296-16f26c5d8f29 · outbound

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

MPO: Multilingual Safety Alignment via Reward Gap Optimization Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:24.858897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fec29b8-de1f-4aa1-b0f0-702c132c6e64 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:24.928984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f72d56-2192-4907-8718-1538c2549aa7 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.018578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4d63cd6-ccee-4efe-850f-e0f976fb48aa · outbound

This paper cites High-Dimension Human Value Representation in Large Language Models.

MPO: Multilingual Safety Alignment via Reward Gap Optimization High-Dimension Human Value Representation in Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.083248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0f07532-770e-437a-b29d-857be1e23e6a · outbound

This paper cites Towards Scalable Automated Alignment of LLMs: A Survey.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Towards Scalable Automated Alignment of LLMs: A Survey

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.146437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf229c52-f0ba-4940-9581-9a17bc746fcd · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.231163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83067b22-3ba4-4077-ac0e-50b004ede170 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.237978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5f97a93-f886-4890-919f-1b733718782f · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Training Verifiers to Solve Math Word Problems

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.242409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e64fe45c-a05b-42b3-9423-1ce6b4f9afc4 · outbound

This paper cites No Language Left Behind: Scaling Human-Centered Machine Translation.

MPO: Multilingual Safety Alignment via Reward Gap Optimization No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.247094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbf6d2b8-c686-4ffa-98e0-b047983cf746 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.351130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 082310df-b97d-440d-a0f3-52e56812b61f · outbound

This paper cites RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment.

MPO: Multilingual Safety Alignment via Reward Gap Optimization RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.425024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba87895d-fe0a-472c-8d90-a6c3d2c913ec · outbound

This paper cites The Llama 3 Herd of Models.

MPO: Multilingual Safety Alignment via Reward Gap Optimization The Llama 3 Herd of Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.545583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64a5bca5-f1c3-44f1-b169-e5b946ac97e5 · outbound

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

MPO: Multilingual Safety Alignment via Reward Gap Optimization KTO: Model Alignment as Prospect Theoretic Optimization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.700478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 194804bc-7aad-4459-96e8-2fabf0380569 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.829780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9ed2007-fb39-4570-989e-af31e701df1a · outbound

This paper cites LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Inconsistencies.

MPO: Multilingual Safety Alignment via Reward Gap Optimization LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Inconsistencies

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:25.999616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1519a9e1-e67b-41f0-9275-d2a1a4517c22 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:26.179526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99d9834b-ceb7-477c-80bf-12b9c591f53f · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

MPO: Multilingual Safety Alignment via Reward Gap Optimization DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:26.326794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37779663-14c7-4844-8c03-42accb2ae545 · outbound

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

MPO: Multilingual Safety Alignment via Reward Gap Optimization Direct Language Model Alignment from Online AI Feedback

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:26.468933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27c48240-013e-4924-a6c1-a6c84b511234 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:26.632423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc08fea9-a032-4b1b-ad7d-9390616c367e · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:26.777808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85152293-05a5-459a-a684-bd08637f235d · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:26.925931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f838adc4-e756-4e9d-b604-4ffe7b8e99cb · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:27.095791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7d3b16e-c508-4aae-a349-25bdfd37f0d1 · outbound

This paper cites Cross-lingual Transfer of Reward Models in Multilingual Alignment.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Cross-lingual Transfer of Reward Models in Multilingual Alignment

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:57:35.859818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6018cc7a-1e68-4d15-b2b2-eebc2bfd3394 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:42.643686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5473e744-cacd-48aa-9108-265a17e89494 · outbound

This paper cites Large Language Models Are Cross-Lingual Knowledge-Free Reasoners.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Large Language Models Are Cross-Lingual Knowledge-Free Reasoners

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:27.400236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fc2c1ab-27eb-43a6-b243-7544099e38f0 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:42.282021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 59fbe1ef-b02a-452d-87d1-4cc44a803892 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:41.996094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 795a9b5c-9ae4-401d-9fa3-edf03b080874 · outbound

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

MPO: Multilingual Safety Alignment via Reward Gap Optimization PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:27.885966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77a6aafa-f178-4bd3-81f8-03eed46059fd · outbound

This paper cites Mistral 7B.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Mistral 7B

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:27.997377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 056051c0-a66a-4d0d-9f71-50200e298291 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:28.119956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c708738-64a1-4aa6-a72f-3d5b4a647a6c · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:41.722080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 60600cb9-d31f-4b29-a573-cad06695cfcd · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:28.395465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4fc7b8f-d925-4471-ba70-edfcde93d668 · outbound

This paper cites A Cross-Language Investigation into Jailbreak Attacks in Large Language Models.

MPO: Multilingual Safety Alignment via Reward Gap Optimization A Cross-Language Investigation into Jailbreak Attacks in Large Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:28.564672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6997dc8-bd11-4a18-84a8-8ffee63b9d80 · outbound

This paper cites XTRUST: On the Multilingual Trustworthiness of Large Language Models.

MPO: Multilingual Safety Alignment via Reward Gap Optimization XTRUST: On the Multilingual Trustworthiness of Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:28.698812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38a24934-5e02-4b88-859c-2fb5741f9951 · outbound

This paper cites Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:28.808252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6852c46f-e6fb-4d63-972d-aac640c962ee · outbound

This paper cites LiPO: Listwise Preference Optimization through Learning-to-Rank.

MPO: Multilingual Safety Alignment via Reward Gap Optimization LiPO: Listwise Preference Optimization through Learning-to-Rank

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:28.962243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6756cf52-6e94-4b84-9ade-83efaeb08cc7 · outbound

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

MPO: Multilingual Safety Alignment via Reward Gap Optimization SimPO: Simple Preference Optimization with a Reference-Free Reward

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:29.123942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b342a0da-fb0a-4358-b2ad-f005862cef9a · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:41.424966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b099331d-2fcc-4156-baf3-2a36470ed34d · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:41.127182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a2decc0f-9639-4fac-ade4-88e2134b45ba · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:29.548473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbf0c15e-e879-4f34-b07e-e854e4c04e5f · outbound

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

MPO: Multilingual Safety Alignment via Reward Gap Optimization Disentangling Length from Quality in Direct Preference Optimization

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:29.682556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef3b0565-4d01-47e9-94ed-130ff597e838 · outbound

This paper cites Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:29.830816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 384696c4-80c4-4884-bf73-dfba6942dba1 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:40.768641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4f0628ee-8b9d-4e35-8257-3542d0c58060 · outbound

This paper cites Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:30.121689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3675735-891f-41a6-ae51-9e41d4ac6c9e · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:30.298858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6d4bbd5-aa18-4d50-9cd0-67a9bf82f9e4 · outbound

This paper cites Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:30.449159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88739229-8381-4a4e-85a7-b44baa333377 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:40.466984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e58de1f1-48ac-4cc7-aad1-602ef4fb59a4 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:40.070819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c8df08d7-fa7c-40af-90c7-3558c8025d87 · outbound

This paper cites Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:30.769929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fc3bb9f-9dd6-404b-a077-7627ad067481 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:39.626610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4de1f0e2-1706-42eb-8b7b-7bc3a58cc799 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:39.329803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ca5ac8a9-eedd-41b3-9250-b13f49a36cb8 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:31.111817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b1f4f8d-a4ec-484e-8542-d04f3331f5f3 · outbound

This paper cites A Long Way to Go: Investigating Length Correlations in RLHF.

MPO: Multilingual Safety Alignment via Reward Gap Optimization A Long Way to Go: Investigating Length Correlations in RLHF

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:31.186800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 874b778a-127d-433c-a680-7b50424dacba · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:39.093873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a8d89031-663a-45ff-bf7d-17a612ed4ac4 · outbound

This paper cites Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:31.334455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53a3215f-2213-4b49-b398-321db234a88a · outbound

This paper cites A Roadmap to Pluralistic Alignment.

MPO: Multilingual Safety Alignment via Reward Gap Optimization A Roadmap to Pluralistic Alignment

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:31.395223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9087105a-3423-49a5-bdc5-2a49c9149be9 · outbound

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

MPO: Multilingual Safety Alignment via Reward Gap Optimization Gemma 2: Improving Open Language Models at a Practical Size

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:31.492367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4fcae0e-8798-4418-a31d-f7ec5f352c37 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

MPO: Multilingual Safety Alignment via Reward Gap Optimization LLaMA: Open and Efficient Foundation Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:31.599783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3bb1a22-1236-41ba-8813-f422d8b6ad35 · outbound

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

MPO: Multilingual Safety Alignment via Reward Gap Optimization Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:31.698375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 193c4fe7-28da-4ff6-8839-9e5ff3ab131a · outbound

This paper cites Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:31.771057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f0334cc-3ba2-4641-91e9-6318de668604 · outbound

This paper cites The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context.

MPO: Multilingual Safety Alignment via Reward Gap Optimization The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:31.833322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 987cc69d-84de-4dab-9a7e-544ac5e73b2c · outbound

This paper cites Secrets of RLHF in Large Language Models Part II: Reward Modeling.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Secrets of RLHF in Large Language Models Part II: Reward Modeling

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:31.942943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a359a9-4859-48a0-a56e-c182e408bc33 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:32.142229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebc27f3d-3bfd-4ef4-8a68-cc192a5a3bd2 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:38.802200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aa0da394-8c4e-45e9-b174-c1d39e70a3b9 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:32.346784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f53a85-0537-4637-9bee-cbda48e618e1 · outbound

This paper cites AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization.

MPO: Multilingual Safety Alignment via Reward Gap Optimization AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:32.415979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3c0d95a-bbe3-4757-a3eb-a969bc83ffcc · outbound

This paper cites Self-Play Preference Optimization for Language Model Alignment.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Self-Play Preference Optimization for Language Model Alignment

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:32.545303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04a79900-4a94-4c93-a31e-935cc8f187b0 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:38.556358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation da0f5f37-1f7c-4240-8dd9-790546c4e401 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:38.263191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bb475938-3de4-4752-894b-27492d3a2540 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:38.022571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 007606b7-0f54-4940-9364-ad318506c3f5 · outbound

This paper cites Qwen2.5 Technical Report.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Qwen2.5 Technical Report

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:32.944119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd3fe851-ca50-4459-86c0-eb3284e68f77 · outbound

This paper cites Language Imbalance Driven Rewarding for Multilingual Self-improving.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Language Imbalance Driven Rewarding for Multilingual Self-improving

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:33.067658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c602530-3321-4d28-9ae1-49550853a256 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:37.745551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 459f7de1-50a4-4bb5-9cef-4d70061f5343 · outbound

This paper cites LIMO: Less is More for Reasoning.

MPO: Multilingual Safety Alignment via Reward Gap Optimization LIMO: Less is More for Reasoning

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:33.230366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0e9820d-b1af-4b14-b87b-4f900dcabd39 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 81

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:37.446554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bf04a478-53f7-4b9a-a795-3d434d2f7093 · outbound

This paper cites Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:33.437094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ded7f472-70ec-4d01-873b-b688b89c4823 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 83

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:37.243436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 762e112c-6610-4c75-b25f-36d6adf96db2 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:33.625408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 242a42a7-3c4e-4fa1-8577-1062d1e4b100 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 85

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:37.073604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aa8c5c34-ff28-4625-a657-1dcddd708dd8 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 86

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:36.909689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 43b95a2c-098d-411b-bbbd-227a6a8f75c3 · outbound

This paper cites Lens: Rethinking Multilingual Enhancement for Large Language Models.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Lens: Rethinking Multilingual Enhancement for Large Language Models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:33.978484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0996711a-353a-46f7-8ebf-30c5f8f3ac44 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 88

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:36.751044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 18767a1e-5f4c-48c5-a02f-551c7436fa5a · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 89

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:36.593780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dda1918c-bb5b-4f74-bd1a-c2ca0568c75f · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:34.362206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e49b728a-c5be-4450-b589-1482d296fa00 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 91

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:36.434984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ce17b9a4-ba83-4304-98ee-e311c9930fe7 · outbound

This paper cites an unresolved cited work.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Unresolved cited work

Reference 92

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:57:36.264145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 71142e03-05df-428c-8bc1-c5e1e97b0b1f · outbound

This paper cites DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization.

MPO: Multilingual Safety Alignment via Reward Gap Optimization DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:34.760038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d101f4e2-d9d3-45d7-85ec-90e4347e6dea · outbound

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

MPO: Multilingual Safety Alignment via Reward Gap Optimization Fine-Tuning Language Models from Human Preferences

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:34.857649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 956e5001-0899-4a2b-8aed-3b38f92ab001 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

MPO: Multilingual Safety Alignment via Reward Gap Optimization Representation Engineering: A Top-Down Approach to AI Transparency

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T14:57:35.041116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers