Paper Citation Record · LEDGER

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints

As of 7 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 3 inbound Pith citation observations for arXiv:2506.08266.

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

pith.paper-citation-record.v1
2506.08266 v1

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:21:58.815824Z

measured 61 of 61 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:52:19.102106Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T08:31:16.863245Z

Reference resolution

58 of 58 outbound references displayed

verified exact4
verified fuzzy17
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 56377b31-6649-45fe-88dc-a8000252c936 · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.599591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d856b60-19ac-4048-827b-1bafa03f8893 · outbound

This paper cites Constrained Markov decision processes.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Constrained Markov decision processes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.604175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6aa3d0b-ca63-4b80-8d0d-c16bd0df323a · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Constitutional AI: Harmlessness from AI Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.608048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbe55287-cb2e-4b07-84f9-2299ce6ab95d · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.612077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c12c71ee-0016-4ee0-9047-9f03ee6fe616 · outbound

This paper cites Convex optimization.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Convex optimization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.615943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d59d16e5-e0a7-46dc-a0cb-a7bed72ca393 · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Rank analysis of incomplete block designs: I

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.520895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f2e01823-14fb-4cb4-b533-7bcffd74649e · outbound

This paper cites Deep reinforcement learning from human preferences.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Deep reinforcement learning from human preferences

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.624040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43af2ee8-fb62-4003-a3d9-36fbd6627858 · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Safe RLHF: Safe Reinforcement Learning from Human Feedback

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.628042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0462d37-6aa5-49ff-b43f-4347a7448210 · outbound

This paper cites Policy Gradients with Variance Related Risk Criteria.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Policy Gradients with Variance Related Risk Criteria

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:21:59.225698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e182abdc-9e22-47b8-9852-ac3d6f0eb28d · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.636063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8c042f1-7573-493f-aac2-c9a443c337f4 · outbound

This paper cites AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.639987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f07684d-8a34-45e2-9aaa-acf16bc1838d · outbound

This paper cites Fundamentals of optimization theory with applications to machine learning.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Fundamentals of optimization theory with applications to machine learning

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.509176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 16df702a-b512-4412-854f-3cd7bae3fe74 · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.647177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3268aad4-55be-4c92-9fa7-318e0e010cf5 · outbound

This paper cites Scaling laws for reward model overoptimization.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Scaling laws for reward model overoptimization

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.497961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 94183662-19cc-44e8-b867-3065a1951642 · outbound

This paper cites an unresolved cited work.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:21:59.485906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation adafa1f0-2f03-4377-afbc-cc0c6935a6eb · outbound

This paper cites Fairness guarantees under demographic shift.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Fairness guarantees under demographic shift

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.475161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fb60a32b-e206-4001-9b95-87797be7d16a · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Improving alignment of dialogue agents via targeted human judgements

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.668478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4fca4c5-6a67-46c0-8bf4-05c628320eea · outbound

This paper cites The Llama 3 Herd of Models.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints The Llama 3 Herd of Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.671965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df3cfe86-df38-4464-b643-b1f6920c81ed · outbound

This paper cites Ethical Challenges in Data-Driven Dialogue Systems.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Ethical Challenges in Data-Driven Dialogue Systems

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.675367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3b9665f-e183-41e6-9990-aaf7b1ae7336 · outbound

This paper cites Probability inequalities for sums of bounded random variables.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Probability inequalities for sums of bounded random variables

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.679396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bf73396-d333-484c-8515-8a597fe4ae00 · outbound

This paper cites One-shot safety alignment for large language models via optimal dualization.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints One-shot safety alignment for large language models via optimal dualization

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.456542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 085d504c-bea5-441e-8287-5688ca3b64fa · outbound

This paper cites Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.685785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b85f2f4-dc88-4f8d-a4d0-1933183454bd · outbound

This paper cites Beavertails: Towards improved safety alignment of LLM via a human-preference dataset, 2023.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Beavertails: Towards improved safety alignment of LLM via a human-preference dataset, 2023

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.689205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a4a982a-e92c-4f25-8552-7c6e80c6392b · outbound

This paper cites ChatGPT for good? O n opportunities and challenges of large language models for education.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints ChatGPT for good? O n opportunities and challenges of large language models for education

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.444817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 78efc2c2-f73b-463f-bdd9-560b19c3c745 · outbound

This paper cites GPT -4 passes the bar exam.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints GPT -4 passes the bar exam

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.432588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a9a7b0f8-a552-4b74-bd8c-f14dc96d2620 · outbound

This paper cites Buy 4 reinforce samples, get a baseline for free! In DeepRLStructPred@ICLR, 2019.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Buy 4 reinforce samples, get a baseline for free! In DeepRLStructPred@ICLR, 2019

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.699651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31cb7100-2d54-4f7c-bc55-069b11578069 · outbound

This paper cites Kung, Morgan Cheatham, Arielle Medenilla, Czarina Sillos, Lorie De Leon, Camille Elepa \ n o, Maria Madriaga, Rimel Aggabao, Giezel Diaz-Candido, James Maningo, and Victor Tseng.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Kung, Morgan Cheatham, Arielle Medenilla, Czarina Sillos, Lorie De Leon, Camille Elepa \ n o, Maria Madriaga, Rimel Aggabao, Giezel Diaz-Candido, James Maningo, and Victor Tseng

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.413594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 094a5a8d-af98-4b91-83a0-bad6ed9f6a95 · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Enhancing LLM Safety via Constrained Direct Preference Optimization

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.706600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00e2e0a5-26c9-4697-956f-4b4fb406a4e0 · outbound

This paper cites Offline contextual bandits with high probability fairness guarantees.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Offline contextual bandits with high probability fairness guarantees

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.401561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fc679d97-1a53-4ad8-b491-8692792fbc38 · outbound

This paper cites Krumholz, Jure Leskovec, Eric J.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Krumholz, Jure Leskovec, Eric J

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.389891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bce4a920-bc4e-44b7-b7fd-fb5af4712eee · outbound

This paper cites Rule based rewards for language model safety.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Rule based rewards for language model safety

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.379311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ce0cb1d9-f734-47cb-b6ed-741e6ad2addd · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Training language models to follow instructions with human feedback

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.720364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08ef3aa0-5ad6-4b8b-a146-bd0f8c20961f · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:21:59.026775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f5776140-9477-4cb4-93ed-fd1f3ff2abba · outbound

This paper cites Qwen2.5 Technical Report.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Qwen2.5 Technical Report

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.727951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dba9141-8a58-4692-a9b2-e1d3b097c395 · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.731769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14082912-204e-42f1-be50-db845eab2700 · outbound

This paper cites Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.735489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 681def66-995e-4f7e-b389-928d39c912c2 · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.367354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation feb3e995-1e75-40f7-870f-c1a9fbca64fb · outbound

This paper cites Simultaneous statistical inference.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Simultaneous statistical inference

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.356121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5fcea960-3005-4e63-bfb7-1b218532842a · outbound

This paper cites Proximal Policy Optimization Algorithms.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Proximal Policy Optimization Algorithms

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.746310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0425a0d8-0177-4019-85af-d75be4267884 · outbound

This paper cites Learning to summarize from human feedback.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Learning to summarize from human feedback

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.749826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 449cef09-448b-4918-8f7b-1c2c972aa1c0 · outbound

This paper cites The probable error of a mean.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints The probable error of a mean

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.345555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7de895b4-008b-4581-abd2-f98f8bea42bc · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.756875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fc9254e-270a-4133-9587-da6866bd2b74 · outbound

This paper cites Hashimoto.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Hashimoto

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.760319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d515259b-92f9-4ecb-b751-de47abce81f2 · outbound

This paper cites Preventing undesirable behavior of intelligent machines.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Preventing undesirable behavior of intelligent machines

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.327648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 64dc4375-c341-49e2-8d1f-aa55230916cd · outbound

This paper cites LaMDA: Language Models for Dialog Applications.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints LaMDA: Language Models for Dialog Applications

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.767276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6401466-52e9-49e9-8e0b-1907d3b73769 · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.770901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce9dc7c0-7761-480a-a53a-8b110137fd31 · outbound

This paper cites Tran, Rei Sato, Takumi Tanabe, and Youhei Akimoto.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Tran, Rei Sato, Takumi Tanabe, and Youhei Akimoto

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.316321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 46904a93-d126-448b-ac6c-959027d47ce8 · outbound

This paper cites Enforcing Delayed-Impact Fairness Guarantees.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Enforcing Delayed-Impact Fairness Guarantees

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:21:58.932492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b6357af-c971-41de-9d6a-10a85f23d23e · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Ethical and social risks of harm from Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.781959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 367a0044-733d-4030-86de-d0ac856dc876 · outbound

This paper cites Simple statistical gradient-following algorithms for connectionist reinforcement learning.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Simple statistical gradient-following algorithms for connectionist reinforcement learning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.785508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17688df0-e3b8-42e0-91ee-ffcc0610464f · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Recipes for Safety in Open-domain Chatbots

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.788856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 215d5810-a9fe-434f-b1cf-63c3a55c3b00 · outbound

This paper cites Qwen2 Technical Report.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Qwen2 Technical Report

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.792512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e7ecda3-d383-418a-9fd8-e16ffa389a83 · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints A large language model for electronic health records

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:21:59.298310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f8037334-eadc-4a1f-8d46-ec3f0acf2601 · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:21:58.886951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 373be2dd-3351-4c21-85a9-93d010d415bf · outbound

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

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.803923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e532ecc-f56f-4b18-b185-9ca210e2b8c5 · outbound

This paper cites Secrets of RLHF in Large Language Models Part I: PPO.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Secrets of RLHF in Large Language Models Part I: PPO

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.808116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba6c1c8-f416-430f-a4e4-1450569e1f9a · outbound

This paper cites Adversarial Training for High-Stakes Reliability.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints Adversarial Training for High-Stakes Reliability

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.812008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f98a0e96-415d-4e86-9bf3-5e8cacb70470 · outbound

This paper cites write newline.

Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints write newline

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:58.815824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 32637181-00ce-4796-a516-eaa778829233 · inbound

Adaptive Margin RLHF via Preference over Preferences cites this paper.

Adaptive Margin RLHF via Preference over Preferences Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T14:52:19.102106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1437125e-c3ed-4c8c-85f0-a701b5c4ff4e · inbound

Reinforcement Learning from Human Feedback: A Statistical Perspective cites this paper.

Reinforcement Learning from Human Feedback: A Statistical Perspective Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:13:13.609624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8345e638-7f56-407a-8140-7d5adc8af28e · inbound

Implicit Safety Alignment from Crowd Preferences cites this paper.

Implicit Safety Alignment from Crowd Preferences Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-22T08:31:16.865653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.