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 2,101–2,200 of 4,340
Wang, Z., Guan, Y., Lin, L., & Wang, G. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131587 · Cited by 2
Kumta, S. S., Panakaje, N., Parvin, S. M. R., & Nikzad, A. M. (2026) · Acta Psychologica · doi:10.1016/j.actpsy.2026.106530 · Cited by 4
Can Thinking Models Think to Detect Hateful Memes?
Kmainasi, M. B., Kutlu, M., Shahroor, A. E., Hasnat, A., & Alam, M. F. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774905.3795465 · Cited by 5
Zhou, Y. P., Qiu, J., Zhang, W., & Ni, F. (2026) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2026.3678742 · Cited by 4
MASSOUD, A., Meziane, F., & AlZoubi, A. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.110370 · Cited by 2
Peters, U., Bertazzoli, A., DeJesus, J. M., van der Velden, G. J., & Chin-Yee, B. H. (2026) · Public Understanding of Science · doi:10.1177/09636625261425891 · Cited by 4
Conversational recommender systems with large language models: A review of current developments
Kim, Y.-H., & Cho, Y.-S. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132508 · Cited by 6
From enclosure to foreclosure and beyond: opening AI’s totalizing logic
Schwerzmann, K. (2026) · AI & Society · doi:10.1007/s00146-026-03024-7 · Cited by 2
Cheap Expertise: Mapping and Challenging Industry Perspectives in the Expert Data Gig Economy
Wolfe, R., & Dangol, A. (2026) · Annual Symposium on Human-Computer Interaction for Work (CHIWORK) · doi:10.1145/3808045.3808063 · Cited by 2
Bastos, B. R., & Dias, M. D. O. (2026) · Advances in Social Sciences Research Journal · doi:10.14738/assrj.1305.2402 · Cited by 2
Zakershahrak, M. (2026) · Springer eBooks · doi:10.1007/978-981-95-3658-0_72 · Cited by 2
Qi, H., Xu, Y., Wang, H., Gani, A., & Por, L. Y. (2026) · Quantum Information Processing · doi:10.1007/s11128-026-05186-1 · Cited by 2
Causal Methods for LLM Development and Evaluation
Frauen, D., Brockschmidt, M., Heß, K., Ma, H., Ma, Y., Maarouf, A., Schröder, M., Schweisthal, J., Wang, Y., Deviyani, A., et al. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818647 · Cited by 2
Chen, S. T., & LIU, Y. F. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104957 · Cited by 2
Agents, Alignment, and the Many Faces of Autonomy
Fischli, R., Franklin, M., Manzini, A., & Gabriel, I. (2026) · Minds and Machines · doi:10.1007/s11023-026-09786-9 · Cited by 4
Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?
Zheng, K., Fu, J., Deng, W., Han, H., Jose, J. M., & Ge, X. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835072 · Cited by 2
Visual Token Compression Enhances Robustness of MLLMs
Gu, S., Cui, J., Hu, W., Shi, Z., Hu, Z., & Hong, R. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835289 · Cited by 2
Simulating Diverse User Behavioral Stereotypes for Evaluating Agentic Conversational Recommenders
Petruzzelli, A., Martina, A. F. M., Musto, C., de Gemmis, M., Lops, P., & Semeraro, G. M. (2026) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3773078.3831840 · Cited by 2
Large Language Models and Agentic AI for Vulnerability Management: A Systematic Review
Akrami, Y., Malkawi, M., & Alhajj, R. (2026) · Expert Systems · doi:10.1111/exsy.70437 · Cited by 2
Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment
Wulff, T., Tavella, F., Maharjan, R. S., Adikari, M., & Cangelosi, A. (2026) · doi:10.1109/cvprf71909.2026.00889 · Cited by 2
Jia, H., Jiang, C., Zhang, S., & Ye, W. (2026) · doi:10.1109/cvprf71909.2026.00917 · Cited by 2
Arifin, G. Y. (2024) · American Journal of Scholarly Research and Innovation · doi:10.63125/4m5fjb12 · Cited by 13
What Is Left for Us? Second Scholarship Against the Degradation of Research by AI
Novelli, C., & Floridi, L. (2026) · European Law Journal · doi:10.1111/eulj.70031 · Cited by 3
Object Oriented Programming Requires Object Oriented Thinking
Silberman, D., Das, S. K. V. B., & Cabrera, D. (2026) · Journal of Systems Thinking · doi:10.54120/jost.v26i1.4p7aait · Cited by 2
Turing-like tests for language and vision demonstrate a narrowing gap between humans and AI
Zhang, M., Pavarino, E., Liu, X., Dellaferrera, G., Sikarwar, A., Chen, C., Armendáriz, M., Mudrik, N., Agrawal, P., Madan, S., et al. (2026) · Nature Human Behaviour · doi:10.48550/arxiv.2211.13087 · Cited by 3
UFO: Unified Fact Obtaining for Commonsense Question Answering
Li, Z., Zou, B., Fan, Y., & Yu, H. Z. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191699 · Cited by 4
Dialogue Generation Conditional on Predefined Stories: Preliminary Results
Miyazaki, C. (2023) · IEEE Access · doi:10.1109/access.2023.3303440 · Cited by 4
Deterministic Automatic Refactoring at Scale
Gehring, J. (2023) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme58846.2023.00069 · Cited by 3
Work in Progress: ChatGPT as an Assistant in Paper Writing
Baizán, P., Gil, R., García-Loro, F., Pérez, C., Sancristobal, E., & Castro, M. A. (2023) · IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie58773.2023.10343230 · Cited by 2
An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation
Yang, C. H., Huang, G., Yu, M., Zhang, Z., Li, S., Yang, M., Shi, S., Yang, Y., & Liu, L. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00637 · Cited by 6
A transformer-based approach to automate disease prediction from patient descriptions
Barman, N. R., Sharma, K., & Hazra, R. (2023) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/cict59886.2023.10455356 · Cited by 2
Decoupling and Refilling: A Simple Data Augmentation Method for Aspect Term Extraction
Chen, J., Hong, Y., Liu, C., Xu, Q., & Zhou, G. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446120 · Cited by 2
Homomorphic Evaluation Friendly Vision Transformer Design
Wang, A., & Lao, Y. (2023) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf59524.2023.10476853 · Cited by 2
Enhancing Argument Pair Extraction Through Supervised Fine-Tuning of the Llama Model
Mao, T., Fu, J., & Yoshie, O. (2024) · IEEE International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) · doi:10.1109/eebda60612.2024.10485782 · Cited by 2
Gonsalves, R., Li, K., Wilson, S., López, N. N., & Mathur, S. (2024) · SMPTE Motion Imaging Journal · doi:10.5594/jmi.2024/wren8857 · Cited by 2
Visual question answering based evaluation metrics for text-to-image generation
Miyamoto, M., Morita, R., & Zhou, J. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10558259 · Cited by 3
GalaxyGPT: A Hybrid Framework for Large Language Model Safety
Zhou, H., Zheng, J., & Zhang, L. (2024) · IEEE Access · doi:10.1109/access.2024.3425662 · Cited by 3
QGen: Automated Question Paper Generator
Paul, R. J., Jamal, S., Bejoy, S., Daniel, R. J., & Aju, N. (2024) · International Conference on Innovative Trends in Information Technology (ICITIIT) · doi:10.1109/icitiit61487.2024.10580391 · Cited by 2
Oh, J. (2024) · IEEE Access · doi:10.1109/access.2024.3437197 · Cited by 4
Guiding ChatGPT to Generate Salient Domain Summaries
Gao, J. H., Cao, Z., Huang, S., Qin, L., & Ai, C. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650616 · Cited by 2
Epic-Level Text Generation with LLM through Auto-prompted Reinforcement Learning
Qi, Q., Ni, L., Wang, Z., Zhang, L., Liu, J., & Witbrock, M. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650358 · Cited by 2
DIEM: Decomposition-Integration Enhancing Multimodal Insights
Jiang, X., Wang, G., Guo, J., Li, J., Zhang, W., Lu, R., & Tang, S. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02578 · Cited by 6
Self-citationToward Immersive Computational Storytelling: Card-Framework for Enhanced Persona-Driven Dialogues
Liao, B., & Vargas, D. V. (2024) · IEEE Transactions on Games · doi:10.1109/tg.2024.3466898 · Cited by 2
Peng, S., Qu, D., Zhang, W., Zhang, H., Li, S., & Xu, M. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128724 · Cited by 2
Vengala, K., Cherukuri, N. K., Annavarapu, P., & Dodla, P. (2024) · International Conference on Computational Intelligence for Green and Sustainable Technologies (ICCIGST) · doi:10.1109/iccigst60741.2024.10717596 · Cited by 2
Cao, J. D., & Cao, J. (2024) · Electronics · doi:10.3390/electronics13214195 · Cited by 4
Retrieving Operation Insights with GenAI LLM: Comparative Analysis and Workflow Enhancement
Lee, M., & Wang, Z. (2024) · Abu Dhabi International Petroleum Exhibition & Conference (ADIPEC) · doi:10.2118/222023-ms · Cited by 2
Large Language Models-aided Literature Reviews: A Study on Few-Shot Relevance Classification
Giobergia, F., Koudounas, A., & Baralis, E. (2024) · IEEE International Conference on Application of Information and Communication Technologies (AICT) · doi:10.1109/aict61888.2024.10740404 · Cited by 9
A Novel Summarization Framework based on Reference-Free Evaluation of Multiple Large Language Models
Feng, W., Zhao, H., Zhang, M., Yang, H., & Tang, W. (2024) · IEEE International Conference on Metaverse Computing, Networking and Applications (MetaCom) · doi:10.1109/metacom62920.2024.00047 · Cited by 2
Chaudhary, S. (2024) · Conference on AI, Science, Engineering, and Technology (AIxSET) · doi:10.1109/aixset62544.2024.00014 · Cited by 3
Abe, H., Osa, T., Omura, M., Chang, J.-Y., & Harada, T. (2024) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids58906.2024.10769872 · Cited by 2
RAG for Question-Answering for Vocal Training Based on Domain Knowledge Base
Leung, C.-H. J., Yi, Y., Kuai, L., Li, Z., Yeung, S.-K. A., Lee, K.-W. J., Ho, K.-H. K., & Hung, K. (2024) · International Conference on Behavioral, Economic, and Socio-Cultural Computing · doi:10.1109/besc64747.2024.10780718 · Cited by 2
Tailored Definitions With Easy Reach: Complexity-Controllable Definition Generation
Yang, L., Yuan, J., Kong, C., Yu, J., Chong, R., Liu, Z., & Yang, E. (2024) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2024.3522805 · Cited by 2
Qi, C., Zheng, L., Wei, Y., Xu, H., Chen, P., & Gu, X. (2024) · Applied Sciences · doi:10.3390/app15010154 · Cited by 5
Knowledge and Task-Driven Multimodal Adaptive Transfer Through LLMs with Limited Data
Zhang, X., Chen, Z., Ren, H., & Tian, Y. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822808 · Cited by 2
Enhancing Financial Reasoning in Large Language Models: The Role of Gold Facts
Zhu, S., Yuan, Z., Wang, K., Zhang, Y., & Wei, W. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825021 · Cited by 3
Preserving Privacy During Reinforcement Learning With AI Feedback
Gao, D., Miller, I. J., Allami, A. A., & Lin, D. (2024) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa62245.2024.00033 · Cited by 3
Bai, S., & Chan, T.-T. (2024) · International Conference on Educational Technology (ICET) · doi:10.1109/icet62460.2024.10867905 · Cited by 3
Iterative Feedback-Enhanced Prompting: A Green Algorithm for Reducing Household Food Waste
Wang, Y. (2024) · International Conference on Machine Learning and Applications · doi:10.1109/icmla61862.2024.00295 · Cited by 2
Aligning Text-to-Image Diffusion Models without Human Feedback
Liu, T., Kuang, H., & Lin, X. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888279 · Cited by 2
Leveraging Large Language Models in Multiagent System
saxena, P., & Lal, R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32483-2_16 · Cited by 2
Evolving AI: What Lies Beyond Today’s Language Models
Jovanovic, M., & Campbell, M. (2025) · Computer · doi:10.1109/mc.2025.3546045 · Cited by 2
Enhancing Patient Intake Process in Mental Health Consultations Using RAG-Driven Chatbot
Shayaninasab, M., Zahoor, M., & Yalçın, Ö. N. (2024) · International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) · doi:10.1109/aciiw63320.2024.00053 · Cited by 5
Question Selection for Multimodal Code Search Synthesis Using Probabilistic Version Spaces
Wu, J., Jiang, Y., Wei, L., Xu, C., Cheung, S.-C., & Xu, C. (2025) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2025.3565387 · Cited by 4
Self-citationRecommendation Module Based on Web Scraping and LLM Models with the RAG Technique
Hachicha, M., Omezine, M. A., Zghal, M. K., Riahi, M. H., & Ncib, L. (2024) · Artificial Intelligence Revolutions (AIR) · doi:10.1109/air63653.2024.00025 · Cited by 3
Alotaibi, N. N., Saberi, M., Bandara, M., Hussain, O. K., & Al-Najjar, H. A. H. (2024) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat62293.2024.00087 · Cited by 2
MSLoRA: Meta-learned scaling for adaptive fine-tuning of LoRA
Dan, L., Zheng, K., Wu, C., & Wang, X. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130374 · Cited by 5
Zhang, Y., Lai, Y., Wang, Z., & Zhou, D. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128369 · Cited by 3
The Fair Game: Auditing & debiasing AI algorithms over time
Basu, D., & Das, U. (2025) · Cambridge Forum on AI Law and Governance · doi:10.1017/cfl.2025.8 · Cited by 3
Ran, D., Cao, Y., Guo, Y., Li, Y., Wu, M. S., Chen, S. H., Yang, W. M., & Xie, T. (2025) · Proceedings of the ACM on software engineering. · doi:10.1145/3729385 · Cited by 3
Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation
Fang, K., Tao, Q., He, M., Lv, K., Yang, R., Hu, H., Huang, X., Yang, J., & Cao, L. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3705778 · Cited by 4
VPO: Leveraging the Number of Votes in Preference Optimization
Cho, J. H., Park, M., & Lee, B.-J. (2025) · Computational Linguistics · doi:10.1162/coli.a.579 · Cited by 2
Design topological materials by reinforcement fine-tuned generative model
Xu, H., Qian, D., Liu, Z., Jiang, Y., & Wang, J. (2026) · Nature Communications · doi:10.1038/s41467-026-73321-8 · Cited by 4
ULTHO: Ultra-Lightweight Yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning
Yuan, M., Li, B., Jin, X., & Zeng, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00252 · Cited by 2
Wang, Z., Liao, Y., Rong, K., Rao, F., Yang, Y., & Liu, S. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00195 · Cited by 2
All Learning Has an Emotional Basis, So Does Task-Oriented Dialogue
Feng, S., Lin, H.-C., Lubis, N., van Niekerk, C., Heck, M. C., Ruppik, B., Vukovic, R., & Gašić, M. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.812 · Cited by 2
Doropoulos, S., Vologiannidis, S. D., & Magnisalis, I. D. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108078 · Cited by 2
Split liability assessment in car accident using 3D convolutional neural network
Lee, S., & Lee, Y. (2023) · Journal of Computational Design and Engineering · doi:10.1093/jcde/qwad063 · Cited by 2
Perko, A., Zhao, H., & Wotawa, F. (2023) · International Conference on Dependable Systems and Their Applications (DSA) · doi:10.1109/dsa59317.2023.00034 · Cited by 2
ShoppingGPT: A GPT-based Product Recommendation Dialogue System
Yu, R., Guan, Y., & Zhan, Y. (2023) · IEEE International Conference on Pattern Recognition and Machine Learning (PRML) · doi:10.1109/prml59573.2023.10348314 · Cited by 4
Generative AI Frameworks for Web for Good: Food Pantry Information Seeking as an Example
Chen, H.-Y. (2023) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat59888.2023.00057 · Cited by 2
The Necessity of Machine Learning Theory in Mitigating AI Risk
Belkin, M. (2024) · ACM / IMS Journal of Data Science · doi:10.1145/3643694 · Cited by 6
A Study Case of Automatic Archival Research and Compilation using Large Language Models
Guo, D., Yue, A., Ning, F., Huang, D., Chang, B., Duan, Q., Zhang, L., Chen, Z., Zhang, Z., Zhan, E., et al. (2023) · IEEE International Conference on Knowledge Graph (ICKG) · doi:10.1109/ickg59574.2023.00012 · Cited by 2
The Era of Generative Artificial Intelligence: In-Memory Computing Perspective
Kang, S.-H., Lee, S., & Sohn, K. (2023) · Technical digest - International Electron Devices Meeting/Technical digest · doi:10.1109/iedm45741.2023.10413786 · Cited by 2
Enhancing Steganography of Generative Image Based on Image Retouching
Gao, Y., Yang, J., Chen, C., Pang, K., & Huang, Y. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448006 · Cited by 2
A ChatGPT-like Solution for Power Transformer Condition Monitoring
Accurso, J. M., Mendy, R., Torres, A., & Tang, Y. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00260 · Cited by 2
High-quality distractor generation framework for English reading comprehension
Guo, Z., Wang, H., & Guo, G. (2023) · International Academic Exchange Conference on Science and Technology Innovation (IAECST) · doi:10.1109/iaecst60924.2023.10502585 · Cited by 2
Aligning Crowd-sourced Human Feedback for Code Generation with Bayesian Inference
Wong, M. F., & Tan, C. W. (2024) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai59869.2024.00037 · Cited by 8
Generative AI Models with Their Full Reveal*
Chekhovich, Y. V., Grabovoy, A., & Gritsai, G. (2024) · International Conference on Technology Enhanced Learning in Higher Education (TELE) · doi:10.1109/tele62556.2024.10605662 · Cited by 2
The Blessing of Reasoning: LLM-Based Contrastive Explanations in Black-Box Recommender SystemsPreprint
Wang, Y., Li, P., & Chen, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5099067 · Cited by 5
Gatt, A. (2025) · Oxford University Press eBooks · doi:10.1093/acrefore/9780199384655.013.896 · Cited by 2
Deep reinforcement learning for the vehicle routing problem
Yaddaden, A. (2023) · theses.fr (ABES) · doi:10.70675/e02b7a6cz150az4b0azac87z3050656f40f0 · Cited by 3
RIPA: Sensory-Vector Prompt Injection Attacks on LLM-Controlled ROS 2 RobotsPreprint
Dorzhiev, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.28649 · Cited by 2
BOTANIC-1: a series of long-context plant genomic foundation models in the agentic eraPreprint
Barozet, A., Cabeli, V., du Terrail, J. O., Rukhovich, A., Janssoone, T., Klajer, G., Sheikhitarghi, Z., Andrews, G., Véran, C., & Strouk, L. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.04.749355 · Cited by 3
Fish Audio Drama 3 Technical ReportPreprint
Han, D., Li, S., Liao, S., Liu, J., Liu, S., Wang, Q., Wang, Y., Xin, C., Cheng, Y., Li, T., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.18010 · Cited by 3
"Just Asking Questions": Doing Our Own Research on Conspiratorial Ideation by Generative AI Chatbots
FitzGerald, K. M., Riedlinger, M., Bruns, A., Harrington, S., Graham, T., & Angus, D. (2026) · Media and Communication · doi:10.17645/mac.11337 · Cited by 1
Li, J., Yin, W., & Wang, L. (2026) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2026.3653869 · Cited by 3
UniEval-RAG: A Unified End-to-End Evaluation Framework for RAG Systems
Liang, S., Gong, X., Li, F., Zhou, H., Wu, Y., & Liao, C. (2025) · International Conference on Computer, Internet of Things and Smart City (CIoTSC) · doi:10.1109/ciotsc67482.2025.11412981 · Cited by 1
Culinary Class Wars: Evaluating LLMs Using ASH in Cuisine Transfer Task
Lee, H., Gim, M., Choi, D., & Kang, J. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00080 · Cited by 1
DyRRS: A Learning-based Dynamic Retrieval and Routing Optimization Scheme for Edge–Cloud RAG
Song, J., Sun, H., & Xiao, W. (2026) · International Conference on Embedded Systems, Mobile Communication and Computing (EMC²) · doi:10.1109/emc68537.2026.11441659 · 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.