Training Language Models to Follow Instructions with Human Feedback
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Making language models bigger does not inherently make them better at following a user's intent. For example, large language models can generate outputs that are untruthful, toxic, or simply not helpful to the user. In other words, these models are not aligned with their users. In this paper, we show an avenue for aligning language models with user intent on a wide range of tasks by fine-tuning with human feedback. Starting with a set of labeler-written prompts and prompts submitted through the OpenAI API, we collect a dataset of labeler demonstrations of the desired model behavior, which we use to fine-tune GPT-3 using supervised learning. We then collect a dataset of rankings of model outputs, which we use to further fine-tune this supervised model using reinforcement learning from human feedback. We call the resulting models InstructGPT. In human evaluations on our prompt distribution, outputs from the 1.3B parameter InstructGPT model are preferred to outputs from the 175B GPT-3, despite having 100x fewer parameters. Moreover, InstructGPT models show improvements in truthfulness and reductions in toxic output generation while having minimal performance regressions on public NLP datasets. Even though InstructGPT still makes simple mistakes, our results show that fine-tuning with human feedback is a promising direction for aligning language models with human intent.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Existing literature (Ouyang et al., 2022) does not fully describe the details of these models, such as the pretraining corpus, model sizes, and model biases.”
From Self-Refine: Iterative Refinement with Self-Feedback (2023) · cites this paper as Ouyang et al., 2022
Experimental — accuracy not yet measuredIn the citing paper
“Specifically, providers mitigate race and gender bias through reinforcement learning from human feedback (RLHF), adversarial stress-testing known as red teaming, and hard-coded refusals governed by the provider's own content policies [6, 43, 71].”
From All Public Voices Are Equal, But Are Some More Equal Than Others to LLMs? (2026) · cites this paper as [71]
In the citing paper
“Fine-tuning a model from human feedback at scale, using preference data from paid raters or drawn from a large and willing user base, is an especially potent technique.It has the potential not only to shape a model's responses to better reflect user norms (for better or worse), but also to filter out toxic language, improve factual accuracy, and mitigate the tendency to fabricate information.”
From Talking about Large Language Models (2024) · cites this paper as [26]
In the citing paper
“These include general competencies such as in-context learning (ICL) [13], chain-of-thought (CoT) [17] reasoning, and instruction following [25], as well as task-specialized skills like mathematical reasoning [30].”
From A Survey of Large Language Models (2026) · cites this paper as [25]
In the citing paper
“When external reward models or ground-truth answers are available, rejection sampling can also be applied to select higher-quality responses from multiple candidates [25].”
From A Survey of Large Language Models (2026) · cites this paper as [25]
41 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
Items 2,501–2,600 of 4,340
LLMs Encode Relevance as a Layer-Wise Cross-Lingual Signal
Bernardelle, P., Mohtadi, S., Civelli, S., Mackenzie, J., & Demartini, G. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3841097 · Cited by 1
Retrieval-grounded multilingual LLM assistance for island smallholder farmers
Tantaroudas, N. D., Karachalios, I., & McCracken, A. J. (2026) · Open Research Europe · doi:10.12688/openreseurope.24512.1 · Cited by 1
iBRAHIMOĞLU, N., Demirezen, M. U., & Yıldız, F. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01490-x · Cited by 2
Jangirala, S., Gupta, V., & Mandal, A. (2026) · IEEE Access · doi:10.1109/access.2026.3719163 · Cited by 1
Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation
Yeh, Y., Li, Y., Hu, X., Lei, Z., & Yang, Y. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.48550/arxiv.2608.08009 · Cited by 1
LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing
Dong, J., 丁, 童., Gupta, I., & Wang, Y. (2026) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3773078.3831929 · Cited by 1
Taniguchi, T., Hayashi, Y., Hirose, M., Oka, M., Suzuki, K., Witkowski, O., & Tang, A. (2026) · Artificial Life · doi:10.1162/artl.a.475 · Cited by 2
Who's Keeping Score? Interactive Steering of LLM-Powered Scoring with Attune
Chopra, B., Chen, M., Dang, R., Park, C., Shankar, S., Zeighami, S., Hartmann, B., & Parameswaran, A. (2026) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3830398.3830567 · Cited by 1
Mousavi, Y., Mousavi, R., Mousavi, A., Tavasoli, M., Küçükdemiral, İ. B., Fekih, A., & Cali, Ü. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134924 · Cited by 3
Beyond Uncertainty: Multi-Solver Disagreement Rewards for Self-Evolving Reasoning Curricula
Selvendran, V., & Zhang, Z. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840051 · Cited by 1
NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation
Pu, Y., & Kong, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37098-3_3 · Cited by 1
Step Back to Move Forward: Reflection-Aware Preference Optimization for Visual Generation
Wu, J., Lin, J., Sun, J., Zhang, B., Wang, H., Fan, D., Liu, H., Gan, Q., Yang, F., & Gao, T. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835988 · Cited by 1
Self-citationJoint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching
Lin, J., Wu, J., Zuo, F., Ouyang, H., Fan, D., Zhang, B., Wang, H., Sun, J., Yang, F., Liu, H., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37531-5_34 · Cited by 1
Self-citationQuality over quantity: Diversity-aware data selection for efficient verilog code generation
Shen, Y., Zheng, W., Wei, X., Shen, H., Chen, X., & Yang, G. (2026) · Information Sciences · doi:10.1016/j.ins.2026.124283 · Cited by 1
Lan, Z., & Yang, J. (2026) · IEEE Access · doi:10.1109/access.2026.3740087 · Cited by 1
Learning Machines: From the Automatic Teacher to Large Language Models
Stefano, L. D. (2026) · CyberLeninK (CyberLeninka) · doi:10.48417/technolang.2026.03.02 · Cited by 1
Organizing Unstructured Image Collections Using Natural Language
Liu, M., Zhong, Z., Li, J., Franchi, G., Roy, S., & Ricci, E. (2026) · 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF) · doi:10.1109/cvprf71909.2026.00855 · Cited by 4
Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Models
Gu, Z., Zhao, Q., Wang, Y., Huang, Z., Xinqi, L. I., Yuan, C., Shao, J., Zhang, C., & Li, X. (2026) · doi:10.1109/cvprf71909.2026.00824 · Cited by 1
Self-citationOn the Feasibility and Opportunity of Autoregressive 3D Object Detection
Huang, Z., Yoo, J., Jeon, S., Liu, Z., Campbell, M., Weinberger, K. Q., Hariharan, B., Chao, W., & Luo, K. Z. (2026) · doi:10.1109/cvprf71909.2026.00117 · Cited by 1
Lost in the comments: Social context as a single‐pass jailbreak and defense on agentic platforms
Yun, T., Jeon, S., Kim, G., Park, J., & Min, M. (2026) · ETRI Journal · doi:10.4218/etrij.2026-0190 · Cited by 1
Cheng, Y., Kang, Z., Jiang, K., Sun, C., Pan, Q., Jiang, T., & Jacobs, B. (2026) · JMIR Formative Research · doi:10.2196/96433 · Cited by 1
Gajawada, S. (2026) · International Journal of Philosophy Ethics and Humanities · doi:10.64823/ijpeh.2602003 · Cited by 1
CellSecInspector : Safeguarding Cellular Networks via Automated Security Analysis on Specifications
Xie, K., Zhao, X., Chen, M.-Y., Chen, Y.-A., Hu, Y., Saifuzzaman, M., Li, W., Yuan, S., Tu, G.-H., & Xie, T. (2026) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3795866.3844474 · Cited by 1
Agentic AI Systems in Radiology: Design, Applications, Evaluation, and Challenges
Blüthgen, C., Veen, D. V., Truhn, D., Kather, J. N., Moor, M., Polacin, M., Chaudhari, A. S., Frauenfelder, T., Langlotz, C. P., Krauthammer, M. O., et al. (2026) · Radiology · doi:10.1148/radiol.253226 · Cited by 1
Zhang, Y., Xiang, Z., & Xu, H. (2026) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc70364.2026.11740028 · Cited by 14
Inclusion-Exclusion Knowledge Filtering Approach for Conversation-Based Preliminary Diagnosis
Chen, B., & Chen, J. (2023) · IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability (ECBIOS) · doi:10.1109/ecbios57802.2023.10218646 · Cited by 1
Paint ChatGPT: A Platform for Old Shanghai Calendar Card Generation
Wang, H., Qian, S., Zhang, J., Jin, C., & Wang, J. (2023) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew59549.2023.00063 · Cited by 2
Automated evaluation of sport and leisure accident reports using natural language processing
Maschek, A., & Stöckl, A. (2023) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme57830.2023.10252673 · Cited by 1
Learning entity-oriented representation for biomedical relation extraction
Hu, Y., Chen, Y., Qin, Y., & Huang, R. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104527 · Cited by 1
Public Opinion Mining Using Large Language Models on COVID-19 Related Tweets
Tran, V., & Matsui, T. (2023) · International Conference on Knowledge and Systems Engineering/Proceedings · doi:10.1109/kse59128.2023.10299499 · Cited by 1
Disturbance rejection with compensation on features
Hu, X., Su, J., & Zhang, J. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110129 · Cited by 1
Automated Text Simplification for the Task Guidance in Augmented Reality
Wu, G., Qian, J., Castelo, S., Chen, S., Rulff, J., & Silva, C. T. (2023) · IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct) · doi:10.1109/ismar-adjunct60411.2023.00123 · Cited by 1
Explananda and explanantia in deep neural network models of neurological network functions
Moldoveanu, M. (2023) · Behavioral and Brain Sciences · doi:10.1017/s0140525x23001632 · Cited by 1
Annotate French Clinical Data Using Large Language Model Predictions
Méoni, S., Ryffel, T., & de la Clergerie, É. V. (2023) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi57859.2023.00099 · Cited by 1
Pietrosanti, G. M., Nadizar, G., Pigozzi, F., & Medvet, E. (2023) · IEEE Access · doi:10.1109/access.2023.3342912 · Cited by 1
FinKENet: A Novel Financial Knowledge Enhanced Network for Financial Question Matching
Guo, Y. F., Liang, T., Chen, Z., Yang, B., Wang, J., & Zhao, Y. (2023) · Entropy · doi:10.3390/e26010026 · Cited by 1
Energy Saving Based on Transformer Models with LeakyReLU Activation Function
Wang, J., Li, X., & Wang, J. (2023) · International Conference on Information Science and Technology · doi:10.1109/icist59754.2023.10367091 · Cited by 1
Multi-Feature Enhanced Multimodal Action Recognition
Zhu, Q., Gu, Z., He, H., Yu, Z., Li, C., Zhao, T., & Xu, Z. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10394285 · Cited by 1
Lu, J., Wang, G., Cai, Y., & Wu, X. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3360722 · Cited by 1
A Study on the Adverse Impact of Synthetic Speech on Speech Recognition
Huang, J., Bai, Y., Cai, Y., & Bian, W. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446991 · Cited by 1
Unveiling the Reliability of ChatGPT Answers in the Biomedical Realm: An Assessment in the
Elbatanouny, H., Khater, T., Ansari, S., Khan, B., Khan, W., Almajali, E. R., Al‐Jumeily, D., & Hussain, A. J. (2023) · International Conference on Developments in eSystems Engineering (DeSE) · doi:10.1109/dese60595.2023.10469457 · Cited by 1
Building end-to-end dialogue system with large language models
Fan, J., & Ma, G. (2024) · International Conference on Signal Processing Systems (ICSPS) · doi:10.1117/12.3022781 · Cited by 1
Complex Motion Planning for Quadruped Robots Using Large Language Models
Zhang, X., He, R., Tong, K., Man, S., Tong, J., Li, H., & Zhuang, H. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10558349 · Cited by 1
Named Entity Recognition via Unified Information Extraction Framework
Chen, X., Zhang, Z., & Lu, X. (2024) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai61966.2024.10603324 · Cited by 1
Unlocking Chain of Thought in Base Language Models by Heuristic Instruction
Ren, Z., Wang, B., Sun, S., Wang, Y., Ding, Z., & Liu, W. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650937 · Cited by 1
Word and Character Semantic Fusion by Pretrained Language Models for Text Classification
Wu, Y., & Wan, J. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651461 · Cited by 1
OSAgent: Copiloting Operating System with LLM-based Agent
Xu, J., Guo, K., Gong, W., & Shi, R. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650304 · Cited by 11
Grounded Language Acquisition from Object and Action Imagery
Kubricht, J., Yang, Z., Qiu, J., & Tu, P. (2024) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss61716.2024.10672572 · Cited by 1
CLFR-M: Continual Learning Framework for Robots via Human Feedback and Dynamic Memory
Wang, L., Fei, Y., Tang, H., & Yan, R. (2024) · IEEE Conference on Cybernetics and Intelligent Systems · doi:10.1109/cis-ram61939.2024.10672832 · Cited by 2
Automatic Prompt Generation Based on Combinatorial Relationships in Reasoning Problems
Wu, T., & He, H. (2024) · doi:10.1109/icnlp60986.2024.10692467 · Cited by 1
Small modular reactor reinforcement learning framework: Automating reactor core startup
Bae, S. J., Son, H. H., Lee, Y., & Yang, J. (2024) · Nuclear Engineering and Technology · doi:10.1016/j.net.2024.10.009 · Cited by 1
Consistency and Controversy Analysis in the Hype of Room-Temperature Superconductivity
Chen, T., Zhang, B., Zhang, W., Wang, T., Wang, X., Li, Q., & Wang, F. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3479727 · Cited by 2
Physics Representation Learning for Dexterous Manipulation Planning
Wu, Y., Hu, M., Jin, R., & Liu, R. (2024) · IEEE RO-MAN · doi:10.1109/ro-man60168.2024.10731363 · Cited by 1
Toward a Multi-dimensional Humor Dataset for Social Robots
Zhang, H., Hei, X., Cárdenas, J. J. G., Miao, X., & Tapus, A. (2024) · IEEE RO-MAN · doi:10.1109/ro-man60168.2024.10731268 · Cited by 2
Rahman, A. T. A. S., & Kaur, A. (2024) · IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET) · doi:10.1109/acroset62108.2024.10743336 · Cited by 1
A Scene-Aware Prompt Template of Chinese Text Data Augmentation Method Based on Large Language Model
Kong, L., Wang, G., He, J., Wang, Y., & Gao, Y. (2024) · IEEE International Conference on Pattern Recognition and Machine Learning (PRML) · doi:10.1109/prml62565.2024.10779819 · Cited by 1
Abzianidze, L., Bylinina, L., & Paperno, D. (2024) · Cambridge University Press eBooks · doi:10.1017/9781009542340 · Cited by 1
Laki, L. J., & Yang, Z. G. (2024) · IEEE Conference on Information Technology and Data Science (CITDS) · doi:10.1109/citds62610.2024.10791375 · Cited by 1
Research on Knowledge Graph Extraction Methods for Chinese STEM Curriculum
Wang, C., Sang, X., Wang, X., Gao, Y., & Liu, Y. (2024) · International Conference on Machine Learning and Natural Language Processing (MLNLP) · doi:10.1109/mlnlp63328.2024.10800180 · Cited by 1
Class-Aware Visual Prompt Learning for Vision Language Models
Zhang, S., & Li, Z. (2024) · Journal of Imaging Science and Technology · doi:10.2352/j.imagingsci.technol.2025.69.3.030415 · Cited by 1
Tezcan, A., Skidanova, A., & Moerman, T. (2024) · Prague Bulletin of Mathematical Linguistics · doi:10.14712/00326585.030 · Cited by 4
MAT: Medical AI-generated Text Detection Dataset from Multi-models and Multi-Methods
Xu, B., Wang, R., Ping, L., Zhu, C., Liu, X., Lin, H., Tian, L., & Xia, F. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822580 · Cited by 1
Assessing GPT's Legal Knowledge in Japanese Real Estate Transactions Exam
Inoshita, K. (2024) · International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT) · doi:10.1109/3ict64318.2024.10824669 · Cited by 1
SHR: Enhancing Event Argument Extraction Ability of Large language Models with Simple-Hard Refining
Wu, J., Zhang, C., Zheng, H., & Yu, J. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825685 · Cited by 1
Self-citationLaldin, S., Shum-Tim, C., Prakash, S., & Shum‐Tim, D. (2025) · Journal of Thoracic and Cardiovascular Surgery · doi:10.1016/j.jtcvs.2025.01.008 · Cited by 1
A Framework for Vietnamese Question-Answering in Law Domain
Le, T. V. Q., Vu, D.-H., Pham, V.-H., Le, A.-C., & Nguyen, N. (2024) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc63484.2024.00108 · Cited by 1
Loss-Aware Curriculum Learning for Chinese Grammatical Error Correction
Zhang, D., Li, Y., Bai, L., Zhang, H., Li, Y., Lin, H., Zheng, H.-T., Su, X., & Shan, Z. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889130 · Cited by 1
MAEM: A Multi-Aspect Extraction Model for Enhanced Embedding in RAG
Yi, N., Liu, C., Wang, Y., & Yu, J. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889603 · Cited by 1
CRALA: A Chinese-centric Risk Simulation and Assessment Framework for LLM Agents
Ye, W., Zhang, Z., Li, W., Qin, Y., & Zhang, P. (2024) · International Symposium on Artificial Intelligence and Intelligent Manufacturing (AIIM) · doi:10.1109/aiim64537.2024.10934441 · Cited by 1
Enriching Emotional Expressiveness in Embodied Conversational Agents Using Anime Effects
Tainaka, K., Horiuchi, T., Putra, H. F., & Kobayashi, T. (2025) · IEEE Access · doi:10.1109/access.2025.3559082 · Cited by 2
Performance Analysis of Chinese Large Language Models in Solving Math Word Problems
Pan, S., Liu, K., Chen, W., & He, B. (2024) · International Conference on Intelligent Education and Intelligent Research (IEIR) · doi:10.1109/ieir62538.2024.10960109 · Cited by 2
Zero-Shot Warning Generation for Misinformative Multimodal Content
Delvecchio, G. P., Nguyen, H. H., & Echizen, I. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw65960.2025.00088 · Cited by 1
Moral Judgment with a Large Language Model-Based Agent
Xiong, S., Gu, H., Liang, W., & Yin, L. (2025) · Electronics · doi:10.3390/electronics14132580 · Cited by 3
Nicolay, R. (2025) · Ars digitalis · doi:10.1007/978-3-658-45839-3_5 · Cited by 1
Fodor, J., Murawski, C., & Suzuki, S. (2026) · eLife · doi:10.1101/2025.07.19.665701 · Cited by 1
Improving Large Vision and Language Models by Learning from a Panel of Peers
Hernandez, J., Shi, J., Jenni, S., Ordóñez, V., & Kafle, K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00138 · Cited by 1
Learning Guarantee of Reward Modeling Using Deep Neural Networks
Luo, Y., Ge, Y., Han, R., & Shen, G. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3780316 · Cited by 1
Simonetto, S., Oostveen, R., van Ede, T., Bosch, P., & Jonker, W. (2026) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3779208.3785376 · Cited by 2
Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation
Xu, Z., Ding, B., Zhang, Y., Qi, J., Song, Q., Huang, J., Wang, L., Santelli, J., Weng, Y., Que, Q., et al. (2026) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3773078.3831877 · Cited by 2
Tahri, C. (2023) · theses.fr (ABES) · doi:10.70675/de7f6f4cz266dz4745zab2fz833e8155f8b3 · Cited by 2
Fisher, A., & Fisher, G. (2024) · Regional Anesthesia & Pain Medicine · doi:10.1136/rapm-2024-105405 · Cited by 1
Large Language Models for Pathway Curation: A Preliminary Investigation
Karkera, N., Karkera, N., Kumar, M., Srinivasulu, V. P., Ghosh, S., & Palaniappan, S. K. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95502-7.00254-2 · Cited by 1
Burgess, P., & Shareghi, E. (2025) · Oxford University Press eBooks · doi:10.1093/9780198945215.003.0093 · Cited by 1
Auditing Algorithmic Medical Systems to Uncover AI Harms and Remedy Racial Injustice
Broussard, M. (2025) · Oxford University Press eBooks · doi:10.1093/9780198945246.003.0020 · Cited by 1
Wang, L., Ye, Z., & Zhao, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5763184 · Cited by 5
Artificially Biased Intelligence: Does AI Think Like a Human Investor?Preprint
Keshavarz, J., Seagraves, C., & Sirmans, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.5998954 · Cited by 4
Watzlawick in the Infosphere: Meaning, Paradox, and the Algorithmic Construction of RealityPreprint
Scala, A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6136791 · Cited by 1
Assessing the Benefits of Optimized Agentic AI Systems for Asset PricingPreprint
Koijen, R. S. J., & Levy, B. (. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6474601 · Cited by 1
Shortcut Learning in Visual Question Answering
Dancette, C. (2023) · theses.fr (ABES) · doi:10.70675/2d63990azacc8z421bzb575zdca5f4b9c022 · Cited by 2
Autenrieth, D. (2026) · Oxford University Press eBooks · doi:10.1093/9780198945215.003.0246 · Cited by 1
Ritchie, L., Mehta, S., Panavas, L., & Chen, E. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.01604 · Cited by 1
SR-OPSD: Self-Referenced On-Policy Self-DistillationPreprint
Sun, Z., Li, E., Zhao, Y., Cheng, X., Yuan, W., Li, K., Liu, C., Liu, H., He, B., Zhang, X., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.09745 · Cited by 2
Grynets, O., Pochernina, O., Seletska, A., Tukalo, D., Kostetskyi, D., Fedorchuk, I. V., & Lyashkevych, V. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.13577 · Cited by 1
Understanding LLM Parameter Update Sparsity through the Lens of FisherPreprint
Zhang, Y., Mukherjee, S., & Peng, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.36262 · Cited by 1
T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement LearningPreprint
Zhang, B.-W., He, J., Liu, M., Li, F., Lv, S., Ma, W., Lin, R., Zhong, S., & Guo, L.-Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.00388 · Cited by 1
HealthFound: a health world model for quantitative reasoning on longitudinal health profilesPreprint
Guo, H., Song, L., Ren, P., Han, J., Wang, Y., Li, H., Deng, J., Wang, J., Gong, W., Feng, J., et al. (2026) · medRxiv · doi:10.64898/2026.10.03.26364142 · Cited by 1
Nakagawa, S., & Yamamoto, A. (2026) · medRxiv · doi:10.64898/2026.10.09.26365134 · Cited by 1
Social Bias in Chinese Large Language Models under Social Media ExpressionsPreprint
Zhou, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.14879 · Cited by 1
BOND: Aligning LLMs with Best-of-N Distillation
Sessa, P. G., Dadashi, R., Hussenot, L., Ferret, J., Vieillard, N., Ramé, A., Shariari, B., Perrin, S., Friesen, A., Cideron, G., et al. (2024) · arXiv · doi:10.48550/arxiv.2407.14622 · Cited by 1
AvalonBench: Evaluating LLMs Playing the Game of Avalon
Light, J., Cai, M., Shen, S., & Hu, Z. (2023) · arXiv · doi:10.48550/arxiv.2310.05036 · Cited by 1
Metadata
- Authors
- Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., & Lowe, R.
- Venue
- Advances in Neural Information Processing Systems 35
- Published
- 2022
- Pages
- 27730-27744
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133211372
- Cited by
- 3,117
- References
- 0
- Citations by year
- 2026: 1421 · 2025: 544 · 2024: 852 · 2023: 297 · 2022: 3
- FWCI
- 234.27
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- neural information processing systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- instruction following, language models, human feedback, reinforcement learning from human feedback, large language models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.