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 1,301–1,400 of 4,340
Enhancing the Robustness of AI-Generated Text Detectors: A Survey
Liu, X., Li, Y., & Li, K. (2025) · Mathematics · doi:10.3390/math13132145 · Cited by 10
Effective Long-Context Scaling of Foundation Models
Xiong, W., Liu, J., Molybog, I., Zhang, H., Bhargava, P., Hou, R., Martin, L., Rungta, R., Sankararaman, K. A., Oguz, B., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.16039 · Cited by 9
A Survey on Self-Evolution of Large Language Models
Tao, Z., Lin, T.-E., Chen, X., Li, H., Wu, Y., Li, Y., Jin, Z., Huang, F., Tao, D., & Zhou, J. (2024) · arXiv · doi:10.48550/arxiv.2404.14387 · Cited by 9
Typhoon: Thai Large Language Models
Pipatanakul, K., Jirabovonvisut, P., Manakul, P., Sripaisarnmongkol, S., Patomwong, R., Chokchainant, P., & Tharnpipitchai, K. (2023) · arXiv · doi:10.48550/arxiv.2312.13951 · Cited by 9
“Instruction-tuning or fine-tuning methods could be categorized into supervised fine-tuning (SFT) and alignment via reinforcement learning using human feedback (RLHF) [52, 38] or AI feedback (RLAIF) [18], and Direct Preference Optimization (DPO) [46].”
MethodParallel Learning for Legal Intelligence: A HANOI Approach Based on Unified Prompting
Song, Z., Huang, M., Miao, Q., & Wang, F. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2023.3301400 · Cited by 10
Vision-language joint representation learning for sketch less facial image retrieval
Dai, D., Fu, S., Liu, Y., & Wang, G. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102535 · Cited by 10
Li, H., Yu, S., Zhang, S., & Tan, G. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610083 · Cited by 9
Defending Large Language Models Against Jailbreak Attacks Through Chain of Thought Prompting
Cao, Y., Gu, N., Shen, X., Yang, D., & Zhang, X. (2024) · International Conference on Networking and Network Applications (NaNA) · doi:10.1109/nana63151.2024.00028 · Cited by 15
Language-based reasoning graph neural network for commonsense question answering
Yang, M., Wang, Y., & Gu, Y. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106816 · Cited by 11
Is ChatGPT the Future of Causal Text Mining? A Comprehensive Evaluation and Analysis
Takayanagi, T., Suzuki, M., Kobayashi, R., Sakaji, H., & Izumi, K. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825555 · Cited by 14
SUGAR: Leveraging Contextual Confidence for Smarter Retrieval
Zubkova, H., Park, J.-H., & Lee, S.-W. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890064 · Cited by 15
Ma, Y., Qing, L., Kang, Y., Liu, J., Zhang, Y., Cheng, Q., Lu, W., & Liu, X. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127226 · Cited by 13
Active generation network of human skeleton for action recognition
Wang, X., Liu, L., Li, F., & Lu, K. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127529 · Cited by 12
Parameter-Efficiently Fine-Tuning Large Language Models for Classroom Dialogue Analysis
Wang, D., Zheng, Y., Li, J., & Chen, G. (2025) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2025.3567995 · Cited by 12
Aligning large language models with human preferences using historical text edits
Majkutewicz, J., & Szymański, J. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113566 · Cited by 9
Afzaal, U., Su, Z., Sajjad, U., Stack, T., Lü, H., Niu, S., Akbar, A., Gürcan, M. N., & Niazi, M. K. K. (2025) · Patterns · doi:10.1016/j.patter.2025.101284 · Cited by 15
An empirical study of LLMs via in-context learning for stance classification
Shi, L., Giunchiglia, F., Luo, R., Shi, D., Song, R., Diao, X., & Xu, H. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104322 · Cited by 12
CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval
Tian, R., Xu, X., Jin, B., Kang, S., & Han, J. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818844 · Cited by 11
TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP
Cai, Y., Thomason, J., & Rostami, M. G. (2026) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3776574.3831142 · Cited by 10
Ji, Y., Li, R., & Mao, B. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3072-4_6 · Cited by 14
Pharmacist: Safety Alignment Data Curation for Large Language Models Against Harmful Fine-Tuning
Liu, G., Mu, Q., Huang, T., Wang, X., Shen, L., Lin, W., & Zhang, L. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3744640 · Cited by 9
Learned Conformational Space and Pharmacophore Into Molecular Foundational Model
Wang, L., Wu, Y., Luo, H., Liang, M., Zhou, Y. Z., Chen, C. J., Liu, C., Zhang, J., & Zhang, Y. (2026) · Advanced Science · doi:10.1002/advs.202513556 · Cited by 13
Multi-modal anchor adaptation learning for multi-modal summarization
Chen, Z., Lu, Z., Rong, H., Zhao, C., & Xu, F. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.127144 · Cited by 9
eDKM: An Efficient and Accurate Train-Time Weight Clustering for Large Language Models
Cho, M., Alizadeh, K., Fu, Q., Adya, S. N., Mundo, C. C. D., Rastegari, M., Naik, D. K., & Zatloukal, P. (2024) · IEEE Computer Architecture Letters · doi:10.1109/lca.2024.3363492 · Cited by 13
UnstrPrompt: Large Language Model Prompt for Driving in Unstructured Scenarios
Li, Y., Li, L., Wu, Z., Bing, Z., Xuanyuan, Z., Knoll, A., & Chen, L. (2024) · IEEE Journal of Radio Frequency Identification · doi:10.1109/jrfid.2024.3367975 · Cited by 12
Let Topic Flow: A Unified Topic-Guided Segment-Wise Dialogue Summarization Framework
Han, Q., Yang, Z., Lin, H., & Qin, T. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3374112 · Cited by 14
Semantic Encoding Algorithm for Classification and Retrieval of Aviation Safety Reports
Gao, Y., Zhu, G., Duan, Y., & Mao, J. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3359356 · Cited by 9
Procedural Level Generation in Educational Games From Natural Language Instruction
Kumaran, V., Carpenter, D., Rowe, J., Mott, B., & Lester, J. C. (2024) · IEEE Transactions on Games · doi:10.1109/tg.2024.3392670 · Cited by 9
MoDiPO: text-to-motion alignment via AI-feedback-driven direct preference optimization
Pappa, M., Collorone, L., Ficarra, G. M., Spinelli, I., & Galasso, F. (2026) · Frontiers in Computer Science · doi:10.3389/fcomp.2026.1707808 · Cited by 10
Allaway, E., Bhagavatula, C., Hwang, J. D., McKeown, K. R., & Leslie, S. (2024) · Computational Linguistics · doi:10.1162/coli_a_00530 · Cited by 25
Fu, J., Long, Y., Chen, K., Wei, W., & Dou, Q. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611051 · Cited by 14
Baek, D., Kim, J., & Lee, H.-C. (2024) · IEEE Access · doi:10.1109/access.2024.3447737 · Cited by 10
From Extraction to Generation: Multimodal Emotion-Cause Pair Generation in Conversations
Ma, H., Yu, J., Wang, F., Cao, H., & Xia, R. (2024) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3446646 · Cited by 13
Characterizing English Preposing in PP constructions
Potts, C. (2024) · Journal of Linguistics · doi:10.1017/s0022226724000227 · Cited by 9
Liu, W., Xiao, Y., Cheng, S., Zeng, D., Zhou, L., Kong, W., Zhang, M., & Chen, W. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.126099 · Cited by 11
Dharuman, G., Hippe, K., Brace, A., Foreman, S., Hatanpää, V., Sastry, V. K., Zheng, H., Ward, L. T., Muralidharan, S., Vasan, A. K., et al. (2024) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/sc41406.2024.00013 · Cited by 15
Adaptive Prediction Ensemble: Improving Out-of-Distribution Generalization of Motion Forecasting
Li, J., Li, J., Bae, S., & Isele, D. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3522848 · Cited by 19
Navigating chemical-linguistic sharing space with heterogeneous molecular encoding
Lv, L., Li, H., Wang, Y., Chen, Z., Yan, Z., Lin, Z., Li, Y., Yuan, L., & Tian, Y. (2026) · Nature Communications · doi:10.1038/s41467-026-74666-w · Cited by 11
Knowledge Management for Automobile Failure Analysis Using Graph RAG
Ojima, Y., Sakaji, H., Nakamura, T., Sakata, H., Seki, K., Teshigawara, Y., Yamashita, M., & Aoyama, K. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10826046 · Cited by 16
Nomura, A., Takeji, Y., Shimojima, M., & Takamura, M. (2025) · Circulation Journal · doi:10.1253/circj.cj-24-0865 · Cited by 10
Sun, J., Shi, W., Shen, X., Liu, S., Wei, L., & Wan, Q. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103037 · Cited by 12
Unlocking Generative Priors: A New Membership Inference Framework for Diffusion Models
Fu, X., Wang, X., Li, Q., Liu, J., Dai, J., Han, J., & Gao, X. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3560776 · Cited by 14
A design toolkit for task support with mixed reality and artificial intelligence
Caetano, A., Aponte, A., & Sra, M. (2025) · Frontiers in Virtual Reality · doi:10.3389/frvir.2025.1536393 · Cited by 11
AnnCoder: A Mti-Agent-Based Code Generation and Optimization Model
Zhang, Z., Wang, J., Li, Z., Wang, Y., & Zheng, J. (2025) · Symmetry · doi:10.3390/sym17071087 · Cited by 23
Active reward learning and iterative trajectory improvement from comparative language feedback
Hirota, E., Yang, Z., Hiranaka, A., Jun, M., Tien, J., Russell, S., Dragan, A. D., & Bıyık, E. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649251394742 · Cited by 12
Defending Against Jailbreak Through Early Exit Generation of Large Language Models
Zhao, C.-W., Dou, Z.-H., & Huang, K.-Z. (2024) · International Conference on Neural Information Processing · doi:10.1007/978-981-95-4445-5_36 · Cited by 2
Enhancing code summarization with action word prediction
Li, M., Yu, H., Fan, G., Zhou, Z., & Huang, Z. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126777 · Cited by 9
Chen, Y., Dong, S., Hu, B., Liu, Q., & Qu, Y. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/ad0f08 · Cited by 11
R-Cut: Enhancing Explainability in Vision Transformers with Relationship Weighted Out and Cut
Niu, Y., Ding, M., Ge, M., Karlsson, R., Zhang, Y., Carballo, A., & Takeda, K. (2024) · Sensors · doi:10.3390/s24092695 · Cited by 10
Are Large Language Models Table-based Fact-Checkers?
Zhang, H., Si, Q., Fu, P., Zheng, L., & Wang, W. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580146 · Cited by 10
Honesty over Accuracy: Trustworthy Language Models through Reinforced HesitationPreprint
Mohamadi, M. A., Wang, T., & Li, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.11500 · Cited by 11
Multimodal LLMs as Customized Reward Models for Text-to-Image Generation
Zhou, S., Zhang, R., Zhu, H., Kveton, B., Zhou, Y., Gu, J., Chen, J., & Chen, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01826 · Cited by 14
PAR: Prompt-Aware Token Reduction Method For Efficient Large Multimodal Models
Liu, Y., Wu, F., Li, R., Tang, Z., & Li, K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463003 · Cited by 9
JARVIS for HVAC: LLM-based Question-Answer Framework for Sensor-driven HVAC System Interaction
Lee, S., Lee, J., Kang, M., Lee, S., Kim, D., Hong, J., Shin, J., Zhang, P., & Ko, J. (2026) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3810210 · Cited by 11
Safeguarding LLM Agents from Misalignment through Provenance Analysis
She, Y., Liang, Y., & Kang, E. (2026) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3832783.3837535 · Cited by 9
One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment
Cai, H., Li, Y., Yu, T., Zhu, F., Wang, W., Feng, F., & Li, W. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809689 · Cited by 10
Synthetic Interaction Data for Scalable Personalization in Large Language Models
Ma, Y., Huang, Y., Wang, W., Luo, X., Zhang, X., & Feuerriegel, S. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817563 · Cited by 8
TD-MPC2: Scalable, Robust World Models for Continuous Control
Hansen, N., Su, H., & Wang, X. (2023) · arXiv · doi:10.48550/arxiv.2310.16828 · Cited by 8
“As a result, successful application of deep RL often requires large teams of experts with significant computational resources (Berner et al., 2019; Schrittwieser et al., 2020; Ouyang et al., 2022).”
BackgroundLLM Critics Help Catch LLM Bugs
McAleese, N., Pokorny, R. M., Uribe, J. F. C., Nitishinskaya, E., Trebacz, M., & Leike, J. (2024) · arXiv · doi:10.48550/arxiv.2407.00215 · Cited by 10
“Our LLM critics are auto-regressive Transformer policies similar to InstructGPT and ChatGPT [19].”
MethodSelf-citationRouteLLM: Learning to Route LLMs with Preference Data
Ong, I., Almahairi, A., Wu, V., Chiang, W.-L., Wu, T., Gonzalez, J. E., Kadous, M. W., & Stoica, I. (2024) · arXiv · doi:10.48550/arxiv.2406.18665 · Cited by 15
“It is important to distinguish between reward modeling [21] and routing.”
Ranking Manipulation for Conversational Search Engines
Pfrommer, S., Bai, Y., Gautam, T., & Sojoudi, S. (2024) · arXiv · doi:10.48550/arxiv.2406.03589 · Cited by 8
“A subsequent fine-tuning stage attempts to align the model with human intentions by limiting the generation of objectionable content and improving instruction-following performance (Ouyang et al., 2022).”
BackgroundInfluentialA Survey of Post-Training Scaling in Large Language Models
Lai, H., Liu, X., Gao, J., Cheng, J., Qi, Z., Xu, Y., Yao, S., Zhang, D., Du, J., Hou, Z., et al. (2025) · Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2025.acl-long.140 · Cited by 8
Handover QG: Question Generation by Decoder Fusion and Reinforcement Learning
Chung, H.-L., Chan, Y.-H., & Fan, Y.-C. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3426292 · Cited by 8
Exploring Text-to-Motion Generation with Human Preference
Sheng, J., Lin, M. G., Zhao, A., Pruvost, K., Wen, Y., Li, Y., Huang, G. M., & Liu, Y. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00195 · Cited by 18
Cambricon-C: Efficient 4-Bit Matrix Unit via Primitivization
Chen, Y., Zhao, Y., Hao, Y., Wen, Y., Dai, Y., Li, X., Liu, Y., Zhang, R., Zou, M., Song, X., et al. (2024) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro61859.2024.00047 · Cited by 9
Addressing hallucinations with RAG and NMISS in Italian healthcare LLM chatbots
Priola, M. P. (2026) · Data & Knowledge Engineering · doi:10.1016/j.datak.2026.102627 · Cited by 8
MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion
Inoue, S., Wang, S., Wang, W., Zhu, P., Bi, M., & Li, H. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888195 · Cited by 18
Golnari, P., Prantzalos, K., Hood, V. L., Meskis, M. A., Isom, L. L., Wilcox, K. S., Parent, J. M., Lal, D., Lhatoo, S. D., Goodkin, H. P., et al. (2025) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2025.105942 · Cited by 9
Meng, X., Jiao, X., Li, J., Wang, S., Pan, J., Jing, B., & Tang, X. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127630 · Cited by 9
How Much Semantic Information is Available in Large Language Model Tokens?
Haslett, D. A., & Cai, Z. G. (2025) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00747 · Cited by 14
Cross-attention fusion of graph and MLLM for social relation recognition
Tang, W., Qing, L., Wang, P., Li, L., & Peng, Y. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103259 · Cited by 8
MalPID: Malicious Prompt Injection Detection Dataset for Large Language Model based Applications
Omri, S., Abdelkader, M., & Hamdi, M. (2024) · International Conference on Communications and Networking (ComNet) · doi:10.1109/comnet64071.2024.10987374 · Cited by 8
The role of LLMs in theory building
Astobiza, A. M. (2025) · Social Sciences & Humanities Open · doi:10.1016/j.ssaho.2025.101617 · Cited by 11
Peng, D. (2025) · IEEE Access · doi:10.1109/access.2025.3583324 · Cited by 8
AI-driven design: powered by large language model and intelligent computation
Sa, G., Li, Z., Liu, Z., & Tan, J. (2025) · International Journal of Extreme Manufacturing · doi:10.1088/2631-7990/adea23 · Cited by 8
Yu, J., Song, J., & Lu, Y. (2025) · Systems · doi:10.3390/systems13080692 · Cited by 8
Inducing state anxiety in LLM agents reproduces human-like biases in consumer decision-making
Ben‐Zion, Z., Elyoseph, Z., Spiller, T. R., & Lazebnik, T. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00122-1 · Cited by 13
Pareto Multi-objective Alignment for Language Models
He, Q., & Maghsudi, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06078-5_15 · Cited by 21
Aligning Generative Speech Enhancement with Perceptual Feedback
Li, H., Hou, N., Hu, Y., Yao, J., Siniscalchi, S. M., Zhuang, X., Ye, D., Yang, W., & Chng, E. S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461654 · Cited by 12
ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs
Zhang, B., Chen, Z., Song, B., Li, Q., Wu, F., & Chen, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464735 · Cited by 8
Artificial superintelligence alignment in healthcare
Ueda, D., Walston, S. L., Kurokawa, R., Saida, T., Honda, M., Iima, M., Watabe, T., Yanagawa, M., Nishioka, K., Sofue, K., et al. (2025) · Japanese Journal of Radiology · doi:10.1007/s11604-025-01907-1 · Cited by 10
Multi-Agent Video Recommenders: Evolution, Patterns, and Open Challenges
Ranganathan, S., Dharmaratnakar, A., Sinha, A., & Das, D. (2026) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3779211.3795739 · Cited by 12
Cheng, X., Qin, Y., Tan, Y., Li, Z., Wang, Y., Xiao, H., & Zhang, Y. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.645 · Cited by 12
The Dangerous Effects of a Frustratingly Easy LLMs Jailbreak Attack
Bombieri, M., Ponzetto, S. P., & Rospocher, M. (2025) · IEEE Access · doi:10.1109/access.2025.3589112 · Cited by 12
Generative Artificial Intelligence Models: A Survey
Almuammar, M., Alsultan, K., & Altukhaim, Y. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11546-1 · Cited by 9
Large language models exhibit speciesist bias against animals
Jotautaite, M., Caviola, L., Brewster, D. A., & Hagendorff, T. (2026) · Nature Communications · doi:10.1038/s41467-026-72297-9 · Cited by 8
Detecting Smart Home Automation Application Interferences with Domain Knowledge
Wang, T., Chen, W., Liu, L., Wu, G., Wei, J., & Huang, T. (2023) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase56229.2023.00070 · Cited by 8
On the Impact of Language Selection for Training and Evaluating Programming Language Models
Katzy, J., Izadi, M., & van Deursen, A. (2023) · IEEE International Working Conference on Source Code Analysis and Manipulation (SCAM) · doi:10.1109/scam59687.2023.00038 · Cited by 12
End-to-end volumetric segmentation of white matter hyperintensities using deep learning
Farkhani, S., Demnitz, N., Boraxbekk, C., Lundell, H., Siebner, H. R., Petersen, E. T., & Madsen, K. H. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108008 · Cited by 10
Optimizing Steering Feedback Torque With Reinforcement Learning Guided by Human Reward Model
Zhao, R., Deng, W., Huang, K., Nan, J., Wang, Y., & Ding, J. (2024) · IEEE Transactions on Transportation Electrification · doi:10.1109/tte.2024.3381266 · Cited by 9
An Intelligent Penetration Testing Method Using Human Feedback
Li, Q., Wang, R., Zhang, M., Shi, F., Shen, Y., Hu, M., Guo, B., & Xu, C. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3379633 · Cited by 8
Feasibility and Challenges of Interactive AI for Traditional Chinese Medicine: An Example of ChatGPT
Kong, Q., Chen, L. Y., Jingyi, Y. A. O., Ding, C., & Yin, P. (2024) · Chinese Medicine and Culture · doi:10.1097/mc9.0000000000000103 · Cited by 9
Improving unbalanced image classification through fine-tuning method of reinforcement learning
Wang, J., Guo, L., Jiang, Y., Zhang, S., & Zhou, Q. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111841 · Cited by 8
Visual Hindsight Self-Imitation Learning for Interactive Navigation
Kim, K. M., Lee, M., Lee, M. W., Shin, K., Lee, M., & Zhang, B. (2024) · IEEE Access · doi:10.1109/access.2024.3413864 · Cited by 10
A Proposed Model for Distinguishing Between Human-Based and ChatGPT Content in Scientific Articles
Mohamed, T. A., Khafagy, M. H., Elsedawy, A. B., & Ismail, A. S. (2024) · IEEE Access · doi:10.1109/access.2024.3448315 · Cited by 11
Predictive Maintenance Based on Identity Resolution and Transformers in IIoT
Qi, Z., Du, L., Huo, R., & Huang, T. (2024) · Future Internet · doi:10.3390/fi16090310 · Cited by 9
Dehghan, M., Wu, J. J., Fard, F. H., & Ouni, A. (2026) · Empirical Software Engineering · doi:10.1007/s10664-026-10943-y · Cited by 8
Self-citationThe Convergence of Artificial Intelligence Foundation Models and 6G Wireless Communication Networks
Shoaib, M. R., Wang, Z., & Zhao, J. (2024) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2024-spring62846.2024.10683090 · Cited by 8
Large-Scale Data Center Cooling Control via Sample-Efficient Reinforcement Learning
Mu, N., Hu, X., Jia, Q., Zhu, X., & Xiao, H. (2024) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case59546.2024.10711622 · Cited by 8
Large Language Model for Low-Carbon Energy Transition: Roles and Challenges
Cheng, Y., Zhou, X., Zhao, H. Q., Gu, J., Wang, X., & Zhao, J. (2024) · Power System and Green Energy Conference (PSGEC) · doi:10.1109/psgec62376.2024.10721191 · Cited by 8
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.