Safe Inference-Time Alignment via Lagrangian Reward Augmentation | Paper Citation Record

Observation 9da458eb-b52c-4ac2-b292-155e7faa17bd · outbound

This paper cites Rank analysis of incomplete block designs: I.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Rank analysis of incomplete block designs: I

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0aa7a822-3fba-4d90-96a1-1102fa05b8fe · outbound

This paper cites Reinforcement learning from human feedback with high-confidence safety guarantees.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Reinforcement learning from human feedback with high-confidence safety guarantees

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b49af43-32d3-4d2d-8341-b4f4af1349a4 · outbound

This paper cites Deep reinforcement learning from human preferences.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Deep reinforcement learning from human preferences

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e607e1d9-2c8d-4666-b6ca-0d86865bc024 · outbound

This paper cites Scaling laws for reward model overoptimization.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Scaling laws for reward model overoptimization

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9792b898-8330-400b-ba73-f4504d012958 · outbound

This paper cites Realtoxicityprompts: Evaluating neural toxic degeneration in language models.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Realtoxicityprompts: Evaluating neural toxic degeneration in language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53f5a3e6-8d0b-4c12-a7ff-d8e037e255d7 · outbound

This paper cites The Llama 3 Herd of Models.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4c7758f-5e0d-4663-8a03-d149eaa72f8a · outbound

This paper cites Value Augmented Sampling for Language Model Alignment and Personalization.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Value Augmented Sampling for Language Model Alignment and Personalization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c6b4f76-dca3-484c-b321-88e2c59f0f2c · outbound

This paper cites Beavertails: Towards improved safety alignment of llm via a human-preference dataset.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Beavertails: Towards improved safety alignment of llm via a human-preference dataset

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 505efc81-efab-421d-a8f7-635d9ae5b8c6 · outbound

This paper cites u chemann, Maria Bannert, Daryna Dementieva, Frank Fischer, Urs Gasser, Georg Groh, Stephan G \.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation u chemann, Maria Bannert, Daryna Dementieva, Frank Fischer, Urs Gasser, Georg Groh, Stephan G \

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42069561-8fc6-4f8f-9001-76b6f435a068 · outbound

This paper cites Gpt-4 passes the bar exam.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Gpt-4 passes the bar exam

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d8303d2-9c00-42ce-a472-0a57a99f828a · outbound

This paper cites Performance of chatgpt on usmle: potential for ai-assisted medical education using large language models.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Performance of chatgpt on usmle: potential for ai-assisted medical education using large language models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d446d9f-348a-4792-ba79-0f90a95426ac · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9742a86-e76e-48dd-9fab-6e9f1683e054 · outbound

This paper cites Foundation models for generalist medical artificial intelligence.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Foundation models for generalist medical artificial intelligence

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5926ad6b-5045-4408-98fd-b7fa3df37392 · outbound

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

Safe Inference-Time Alignment via Lagrangian Reward Augmentation WebGPT: Browser-assisted question-answering with human feedback

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5efa0096-0a10-484d-8721-c8a63f30fe55 · outbound

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

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Training language models to follow instructions with human feedback

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20885d27-65fc-40e5-8fc2-f1eb59ae16ac · outbound

This paper cites Computational Optimal Transport.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Computational Optimal Transport

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff819ac3-f356-4198-b8bd-6281f1551c1b · outbound

This paper cites Qwen2.5 Technical Report.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Qwen2.5 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daa32e7f-265a-4f51-9db8-ff02010ddb15 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Direct preference optimization: Your language model is secretly a reward model

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 047a2ce5-9e24-4ccb-b222-72aa4d473dc6 · outbound

This paper cites Scaling laws for reward model overoptimization in direct alignment algorithms.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Scaling laws for reward model overoptimization in direct alignment algorithms

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f19105-e644-4921-ac23-7b5e818bcaf5 · outbound

This paper cites Learning to summarize from human feedback.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Learning to summarize from human feedback

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bde22e4-842c-4a63-883b-4efd1083dea8 · outbound

This paper cites Hashimoto.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Hashimoto

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 230d259d-dcc9-411f-85bd-98fc39e9ef03 · outbound

This paper cites Preventing undesirable behavior of intelligent machines.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Preventing undesirable behavior of intelligent machines

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea6a95d9-5d2b-4a5f-a090-4047da1d6258 · outbound

This paper cites Asymptotic statistics, volume 3.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Asymptotic statistics, volume 3

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d9dbe28-413f-43b9-8852-45f67f5ae41a · outbound

This paper cites Fudge: Controlled text generation with future discriminators.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Fudge: Controlled text generation with future discriminators

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3741bc93-6ad7-4418-8714-f36688e3d59c · outbound

This paper cites A large language model for electronic health records.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation A large language model for electronic health records

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef73142e-dc4e-4369-a79d-a809b83272f8 · outbound

This paper cites Controlled Decoding from Language Models.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Controlled Decoding from Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 720b3ea0-fa45-4009-8487-9e6e6307be9d · outbound

This paper cites Theoretical guarantees on the best-of-n alignment policy.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Theoretical guarantees on the best-of-n alignment policy

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2aec05c3-0fba-4c6c-9285-d088541337c5 · outbound

This paper cites ARGS: Alignment as Reward-Guided Search.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation ARGS: Alignment as Reward-Guided Search

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f550b1eb-c7b9-4e9e-83bd-8b6aaf3cf543 · outbound

This paper cites Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , pages=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , pages=

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5e009cb-0681-49f5-bc44-3f350a50e308 · outbound

This paper cites arXiv preprint arXiv:2406.07780 , year=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation arXiv preprint arXiv:2406.07780 , year=

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a06b04-24da-43fb-87d8-d9b9e93f71da · outbound

This paper cites Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c1f8641-65bc-4e7e-ab35-8ea5357eab5e · outbound

This paper cites Towards Cost-Effective Reward Guided Text Generation.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Towards Cost-Effective Reward Guided Text Generation

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6e56e6c-5c43-41e2-b223-219f4a8d88c3 · outbound

This paper cites Safe RLHF: Safe Reinforcement Learning from Human Feedback.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Safe RLHF: Safe Reinforcement Learning from Human Feedback

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e7fad65-0ae2-4c1c-93dc-eb58b8674588 · outbound

This paper cites Advances in neural information processing systems , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in neural information processing systems , volume=

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9367313c-eca2-4354-bf35-b76bc7b54b5f · outbound

This paper cites Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a60d9eaa-f814-4b83-a7fc-25be22e1827a · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in Neural Information Processing Systems , volume=

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 907ea24f-379e-4c61-be29-b40805335096 · outbound

This paper cites arXiv preprint arXiv:2505.20065 , year=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation arXiv preprint arXiv:2505.20065 , year=

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c35ee9f0-f284-4cf5-96bd-62b2b9b289c0 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in Neural Information Processing Systems , volume=

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7b632eb-0689-4b6a-942d-e3e3c079e7a8 · outbound

This paper cites Attention is All you Need , url =.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Attention is All you Need , url =

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe1a0395-308c-46da-8445-ace778f66aae · outbound

This paper cites ArXiv , year=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation ArXiv , year=

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d2da1ad-5cc1-42e8-8bf7-a99121d33315 · outbound

This paper cites Constitutional.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Constitutional

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1db714f-f71d-48c5-96af-920be57ea4bf · outbound

This paper cites ArXiv , year=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation ArXiv , year=

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 361396de-4449-4f63-87d1-dc1cb03b8c5e · outbound

This paper cites 2022 , eprint=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2022 , eprint=

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 214df456-f915-405f-b63e-e0ce3b13a9fa · outbound

This paper cites 2017 , eprint=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2017 , eprint=

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9abac8c3-d6fb-413a-905c-13dadac5ef1c · outbound

This paper cites International Conference on Machine Learning , year=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation International Conference on Machine Learning , year=

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f9e071d-dd10-4190-8816-72ada9c84431 · outbound

This paper cites 2004 , publisher=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2004 , publisher=

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aea1f52-74fc-4b5c-b84f-8272f2ffd87d · outbound

This paper cites University of Pennsylvania Philadelphia, PA , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation University of Pennsylvania Philadelphia, PA , volume=

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47e4a5e0-289b-4f09-a66f-81bca841d633 · outbound

This paper cites 2025 , eprint=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2025 , eprint=

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73655ecb-fb9b-414c-a1af-732ba84c79f9 · outbound

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

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb5eca30-e387-4c5e-8fd7-d2536026b64e · outbound

This paper cites 2021 , publisher=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2021 , publisher=

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 310c0985-add4-4890-95ea-d9b53c909e8e · outbound

This paper cites Rank analysis of incomplete block designs: I.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Rank analysis of incomplete block designs: I

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a76c9f8-9b72-4ba7-9925-856c56360029 · outbound

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

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d835919e-1879-4bbb-a9a5-307a672ccbb9 · outbound

This paper cites DeepRLStructPred@ICLR , year=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation DeepRLStructPred@ICLR , year=

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de5159fe-d2d9-49be-8490-d93380e2f3d2 · outbound

This paper cites ArXiv , year=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation ArXiv , year=

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d057888e-7068-4b20-9b6d-519e47f900f7 · outbound

This paper cites Machine learning , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Machine learning , volume=

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2c044a5-cb3a-4229-ae84-bcc000a9ccc4 · outbound

This paper cites 2024 , eprint=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2024 , eprint=

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1faf0388-5032-4bc8-b2d5-dbb831f31f50 · outbound

This paper cites Reinforcement Learning Conference , year=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Reinforcement Learning Conference , year=

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d5bfc06-b01f-4a96-9118-ce2f6c6f113b · outbound

This paper cites Science , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Science , volume=

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2f35738-4096-4e78-b60e-18feffe5c558 · outbound

This paper cites 2020 , eprint=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2020 , eprint=

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05582faf-a5bf-43bb-8810-3baa35fd28cb · outbound

This paper cites 2016 , publisher=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2016 , publisher=

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e564baf-e1bb-49b3-9d3f-4cc53485eebd · outbound

This paper cites International conference on machine learning , pages=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation International conference on machine learning , pages=

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 530afae8-312c-4c13-b16c-9e0e9de5baee · outbound

This paper cites Advances in neural information processing systems , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in neural information processing systems , volume=

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c153b27-c814-4551-b60b-1a6b85bd1ad7 · outbound

This paper cites an unresolved cited work.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Unresolved cited work

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b4fde2a-fd75-4a27-b39f-a4d0c45958af · outbound

This paper cites Advances in Neural Information Processing Systems 32 , pages =.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in Neural Information Processing Systems 32 , pages =

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29b13f32-6b58-4867-ab65-0287c48c4fc0 · outbound

This paper cites 2015 , url=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2015 , url=

Reference 77

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c926ba54-41d4-4601-b878-62193159a272 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in Neural Information Processing Systems , volume=

Reference 78

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0deb4c19-711d-4eef-8ee1-c5f300cbca79 · outbound

This paper cites Mathematical finance , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Mathematical finance , volume=

Reference 79

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efb6c590-e990-4a33-836f-579730425078 · outbound

This paper cites Journal of banking & finance , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Journal of banking & finance , volume=

Reference 80

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8efddcd-3f1a-46ab-9344-7e271bf6ec6f · outbound

This paper cites Advances in mathematical economics , pages=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in mathematical economics , pages=

Reference 81

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4a7bbb3-29f0-48c8-a516-01647b42123d · outbound

This paper cites 2024 , eprint=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2024 , eprint=

Reference 82

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 296c4afc-b15a-4667-a0f0-ee848d81bbdf · outbound

This paper cites NPJ digital medicine , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation NPJ digital medicine , volume=

Reference 83

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f2662d7-912e-42da-aa1f-d77d6d388b77 · outbound

This paper cites Nature , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Nature , volume=

Reference 84

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9afab344-8328-4f29-ac24-47b42ebfe57e · outbound

This paper cites Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences , volume=

Reference 85

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c446c8a-0fd7-40c1-842a-29a0cbb251a6 · outbound

This paper cites Learning and individual differences , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Learning and individual differences , volume=

Reference 86

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbb2c9e3-b5df-4267-8737-b056a96ed6ee · outbound

This paper cites PLoS digital health , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation PLoS digital health , volume=

Reference 87

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9bfa319-ca37-45bb-b35a-181c63406882 · outbound

This paper cites Findings of the association for computational linguistics: EMNLP 2020 , pages=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Findings of the association for computational linguistics: EMNLP 2020 , pages=

Reference 88

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3a6a99a-eea5-4821-af82-89579f142141 · outbound

This paper cites Ethical and social risks of harm from Language Models.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Ethical and social risks of harm from Language Models

Reference 89

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab8e2cb9-c229-401c-8a1c-fbaff14c01bc · outbound

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

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 90

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d5b41cf-7330-4772-8969-f59b338a1c54 · outbound

This paper cites Improving alignment of dialogue agents via targeted human judgements.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Improving alignment of dialogue agents via targeted human judgements

Reference 91

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8a5cd61-f56b-4c45-9113-3d3198ab9ea7 · outbound

This paper cites Advances in neural information processing systems , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in neural information processing systems , volume=

Reference 92

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 762eae1a-a72b-4322-a132-fec3aba6a9e4 · outbound

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

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 93

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d274b3b-eca7-459c-b17d-039d6ef0e25c · outbound

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

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 94

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76eb964d-0282-46ca-8756-bc4d523005b1 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in Neural Information Processing Systems , volume=

Reference 95

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebfe296b-88ad-4f81-bcbe-1fa257ae7d75 · outbound

This paper cites arXiv preprint arXiv:2402.02698 , year=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation arXiv preprint arXiv:2402.02698 , year=

Reference 96

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78627b48-e129-4421-b1c5-1a0a53378d0d · outbound

This paper cites SIAM Journal on Optimization , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation SIAM Journal on Optimization , volume=

Reference 97

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ebf5663-7144-4179-9c4d-6a3ce6f9c4e3 · outbound

This paper cites The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=

Reference 98

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 575a54e8-9142-4164-9407-75ae23fb5830 · outbound

This paper cites Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society , pages=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society , pages=

Reference 99

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5aecd7d-65bd-48b3-ab38-abb4810f133a · outbound

This paper cites Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling

Reference 100

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d377f38f-7567-4d7f-ac3b-92149dbfed5a · outbound

This paper cites Recipes for Safety in Open-domain Chatbots.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Recipes for Safety in Open-domain Chatbots

Reference 101

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0201cfc2-6dec-4ea5-8064-35b071820530 · outbound

This paper cites LaMDA: Language Models for Dialog Applications.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation LaMDA: Language Models for Dialog Applications

Reference 102

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30b11f2d-32db-41f4-a69a-f0936bd6d3e7 · outbound

This paper cites Adversarial Training for High-Stakes Reliability.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Adversarial Training for High-Stakes Reliability

Reference 103

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85cbb6ca-3aa2-4830-b59b-5f800a6df652 · outbound

This paper cites Enhancing LLM Safety via Constrained Direct Preference Optimization.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Enhancing LLM Safety via Constrained Direct Preference Optimization

Reference 104

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e9d10ac-0873-4a31-919d-4531ce2957aa · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in Neural Information Processing Systems , volume=

Reference 105

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbba9b50-535d-46a1-9911-52c57324de6d · outbound

This paper cites Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization

Reference 106

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 213c8880-eaa6-4fda-8b0a-975f0d8a7317 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in Neural Information Processing Systems , volume=

Reference 107

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b5adc77-6d28-43f2-9e6d-1e8fccb9b27a · outbound

This paper cites Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models

Reference 108

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dce02dfa-7e83-4f55-ac8d-445419b216a3 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Advances in Neural Information Processing Systems , volume=

Reference 109

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 139e0b3d-c286-4974-a55c-b44b58c19d32 · outbound

This paper cites Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models

Reference 110

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a6e7a13-ffe8-4162-888f-8aaa28ca0a9c · outbound

This paper cites 2024 , eprint=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2024 , eprint=

Reference 111

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f5d8de7-1523-4c14-81a7-db5dc8e15b59 · outbound

This paper cites 2021 , eprint=.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation 2021 , eprint=

Reference 112

Resolution: unresolved; no resolver link, observed 2026-07-12T07:05:47.150308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers