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 3,801–3,900 of 4,340
Thoughts Behind Attack: Enhancing Security Against Jailbreak Attacks Using Chain-of-Thought
Tao, Z., Xu, B., Yang, M., Guan, H., Lü, W., Cao, H., Zhu, C., & Zhao, T. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3352-7_16
Very-Long-Distance Dependency Capturing Evaluation via Language Modeling Based on Gender Consistency
Xu, H., Liang, Z., van Genabith, J., Xiong, D., Zan, H., Liu, Q., & Zhang, T. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3352-7_3
Applying Text-to-SQL in Process Mining: Leveraging Natural Language for Data Insights
Yamate, B. Y., Neubauer, T. R., Fantinato, M., & Peres, S. M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-01130-5_16 · Cited by 1
Kashefi, A., Bosschaerts, K., Marez, L. D., Ongenae, F., & Conradie, P. D. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-27582-0_3
It's All Connected: A Survey for Multimodal Arabic AIPreprint
Aldabbas, F., Elsafty, H., & Sifa, R. (2025) · Research Square · doi:10.21203/rs.3.rs-8007923/v1
Quota Hiring Using Artificial Intelligence
Viganò, A., & Magnani, A. (2025) · Springer eBooks · doi:10.1007/978-3-031-40858-8_579-1
Bi-directional Semantic Alignment for Large Vision Language Model Training via Echo-Former
Wang, Y., Liu, Q., Li, Z., Wang, S., Guo, S., & Wei, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3346-6_6
Large Language Model Based Multi-agent Learning for Mixed Cooperative-Competitive Environments
He, C., Yin, Q., Chang, Y., & Yu, T. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3343-5_37
A Human-Centered AI Agent Framework with Large Language Models for Academic Research Tasks
Chen, Z., Chen, J., Wang, Y. G., & Shen, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3343-5_28
Luo, J., Hong, Y., Yang, S., Xu, Q., & Yao, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3343-5_21
Propagandistic Meme Detection via Large Language Model Distillation
Zou, X. G., Li, D., Wang, J., & Lin, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3343-5_25
Enhancing concept alignment with explanatory interactive disentangled representation learning
Meng, X., Lin, Y., Wu, Y., & Lü, Y. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108346
Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking
Creo, A., Fernandez, R. C., & Cebrián, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-11402-0_5
Training LLM with Human Feedback
Rezaei, H., Beheshti, A., & Rabhi, F. (2025) · Springer eBooks · doi:10.1007/978-981-95-3658-0_53 · Cited by 2
A Comparative Study of Reward Functions in Learning Prompt-Based Length Control of LLMs via GRPO
FUJIKOSHI, H., & Okadome, T. (2025) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2025dkp0001
Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning
Cao, J., Wang, Y., Zheng, T., Song, J., Guo, Q., Ren, Z., Jin, C., Chen, G., & Song, M. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3708608 · Cited by 1
Formal Knowledge Augmented Language Models for Explainable and Robust Reasoning
Nguyen, N.-K., Nguyen, V.-H., & Le, A.-C. (2025) · Journal of Intelligent & Fuzzy Systems · doi:10.1177/18758967251394597 · Cited by 1
Chen, L., Yan, S., Guo, Q., Sun, J., Cheng, F., Liu, Z., Xiao, W., Wang, M., Wang, H., & Zhao, X. (2025) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784486115.014
Research on adaptive strategy optimization for open source large language model alignment testing
Wang, C., & Wang, S. (2025) · doi:10.1117/12.3092777
Pungitore, S. A., Yadav, S., Maughan, D., & Subbian, V. (2026) · Machine Learning Health · doi:10.1088/3049-477x/aea0d7
Khosravi, T., Rahimzadeh, A., Motallebi, F., Vaghefi, F., Sudani, Z. M. A., & Oladnabi, M. (2024) · Journal of Clinical and Basic Research · doi:10.66224/jcbr.8.4.22
PGD: Probe Guided Decoding for Alignment
Chen, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04549-2_28
Hidayati, N. N., Santosa, A., Nurfadhilah, E., Latief, A. D., Komariah, K. S., Jarin, A., Pebiana, S., Wabula, Y., Fajri, R., & Sampurno, T. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-0250-8.ch005
Real-Time Text-to-Video Synthesis Using Large Language Models
Das, M., Srivastava, Y., Yerram, M., Shenoy, M., Parashar, J., & Kushwah, V. S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5732-2_18
KA-CDRE: Knowledge-Augmented Cross-Document Relation Extraction
Liu, H., Li, P., Gu, J., Fu, P., Lin, Z., & Wang, W. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3462-3_33
DEO: Jailbreak a Black-box Multimodal Large Language Model with Dual-Embedding Alignment
Zhang, L., Wang, M., Zhao, Y., Lin, Z., & Chen, K. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229281
Beyond One-Size-Fits-All: Adaptive Fine-Tuning for LLMs Based on Data Inherent Heterogeneity
Zhang, W., Xu, Y., Ren, S., & Zhang, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3343-5_22
SIMIONESCU, V.-A. (2026) · International Conference on Cybersecurity and AI-Based Systems (Cyber-AI) · doi:10.1109/cyber-ai70573.2026.11755214
Intention-like representations in language models?
Williams, I. (2026) · Philosophical Studies · doi:10.1007/s11098-026-02605-y · Cited by 2
Estimating Consumer Preferences for LLMs: Evidence from LMArenaPreprint
Caoui, E. H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5970054 · Cited by 2
Unstable Sample based Style Enhancement for Invisible Text Backdoor Attack
Qin, J., Yang, X., & Liu, B. (2025) · International Conference on New Trends in Computational Intelligence (NTCI) · doi:10.1109/ntci67886.2025.11308675
Generative AI and the Strategic Redefinition of Enterprise Information Systems
Özden, C. (2025) · Özgür Yayınları eBooks · doi:10.58830/ozgur.pub1143.c4718
Ren, X., Song, J., Liu, C., Li, J., Ma, L., & Xue, Y. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3787101
Uncovering capabilities of hash function in graph classification
Liu, Y., Li, S., Shi, B., & Wu, J. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2025.113034
Self-citationFine-Tuning Large Language Models Using Entity Hallucination Index for Text Summarization
Praveenkumar, K., Balabantaray, R. C., Vittala, K. P., & Sahu, M. (2026) · Journal of Visualized Experiments · doi:10.3791/68962
HyDaST: Mortality risk prediction via EHR-hypergraph and dual-scale temporal pattern extraction
Li, W., & Law, K. L. E. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123093 · Cited by 2
Human-in-the-Loop Generative Policy Learning from Demonstrations and Preferences
Uchibe, E. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-4445-5_22
Do LLMs Possess Strategic Intelligence? Testing LLMs in Iterated Prisoner’s DilemmasPreprint
Kommandeur, J., Vonk, M., Spiegeleire, S. D., & Sweijs, T. (2026) · Research Square · doi:10.21203/rs.3.rs-8405969/v1
Sen, A., Panda, S., Arya, M., Patra, S., Zheng, Z., & Bondar, D. I. (2026) · Low Temperature Physics · doi:10.1063/10.0044783
CHOLD: Offensive Language Detection Method for Chinese Texts
Wu, H., Li, X., & Zhang, S. S. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-5294-8_17
Distant Poesis: Stochastic Prompting as Literary Creation
Young, H. (2026) · Digital studies in language and literature · doi:10.1515/dsll-2025-0015
Scaling effects and uncertainty quantification in neural actor-critic algorithms
Georgoudios, N., Spiliopoulos, K., & Sirignano, J. A. (2026) · Foundations of Data Science · doi:10.3934/fods.2026032
A Zero-Training Data Cleaning System With Large Language Models
Yang, C., Huang, K., Wu, Y., Wu, Y., Zhu, M., Miao, X., Xi, M., Zheng, X., & Yin, J. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3658627 · Cited by 1
Wj, Z., Tong, Y., Gao, T., & Zhu, L. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356283
Hamedani, M., Patel, R. P., Bizrah, M., Phylactou, M., & Din, N. (2026) · European Journal of Ophthalmology · doi:10.1177/11206721261419675
A Monad-Based Clause Architecture for Artificial Age Score (AAS) in Large Language ModelsPreprint
Kayadibi, S. Y. (2026) · Research Square · doi:10.21203/rs.3.rs-8736598/v1
Deep learning for psychiatric genomics: from tools to applications
Liu, J., Xu, S., Sun, D., Wang, C., & Zhang, J. (2026) · Current Opinion in Genetics & Development · doi:10.1016/j.gde.2026.102442 · Cited by 1
Fine-Tuning LLMs to Generate Economical and Reliable Actions for the Power Grid
Chehade, M. F. E. H., & Zhu, H. (2026) · IEEE Power Engineering Society General Meeting · doi:10.1109/pesgm58988.2026.11693462
Recursive identity and ethical recognition in humans, robots, and AI
Sawyer, C. H. (2026) · AI & Society · doi:10.1007/s00146-026-02943-9 · Cited by 1
Knowledge design in complex domains
Giretti, A., Durmus, D., Carbonari, A., & Isaac, S. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105134
Chinese Implicit Offensive Speech Detection Based on Knowledge Graph and Fuzzy Semantic
Liu, H., Guo, T., Zheng, C., Lin, L., Tu, Z., Wang, H., & Zhang, L. (2026) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3799418
Challenges and Improvements in Mathematical Reasoning for Large Models
Wang, Z. (2026) · Science and Technology of Engineering Chemistry and Environmental Protection · doi:10.61173/gbgrkk38
Training Dialogue Systems Using Entire Dialogue Context Evaluation
Yoshida, K., Mizukami, M., Kawano, S., Kruengkrai, C., Sugiyama, H., & Yoshino, K. (2026) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.41-2_ids26-b
Li, R., Mo, R., Zeng, Y., Liu, Z., Li, Z., & Ma, Y. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3800582 · Cited by 5
Vo, H., Tran, N., Vo, K., Tran-Truong, P. T., & Ha, S. (2026) · IEEE International Conference on Software Architecture Companion (ICSA-C) · doi:10.1109/icsa-c68850.2026.00020
Chen, X., Liu, Y., Wang, P., Li, J., Zhou, J., Wang, Y., & Miu, H. (2026) · International Conference on New Power System and Power Electronics (NPSPE) · doi:10.1117/12.3111094
Harada, Y., & Yamauchi, Y. (2026) · Journal of Natural Language Processing · doi:10.5715/jnlp.33.388 · Cited by 1
From Doyle to AGM: A Survey and an Implementation Roadmap for Belief Change
Almeida, Y., & Casals, A. (2026) · The European Journal on Artificial Intelligence · doi:10.1177/30504554261426170
CLAIM: Mitigating Catastrophic Forgetting in Continual Instruction Fine-Tuning Large Language Models
Qiu, X., Shi, S., Hao, T., & Tan, X. (2026) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2026.3674105
Jin, Y., Gao, M. Y., Tang, J., Fan, W., Yang, Y., & An, J. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104741
Making Large Language Models More Flexible to Changing Contingencies through Tracking Induction
Ruiz, F. J., & Martínez-Carrillo, E. (2026) · The Psychological Record · doi:10.1007/s40732-026-00698-9
Research on large model reasoning optimization integrating result rewards and thought chain prompts
Li, C., & Ning, M. A. (2026) · International Conference on Algorithms, High Performance Computing and Artificial Intelligence (AHPCAI) · doi:10.1117/12.3107807
Teng, Y., & Wang, C. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00643-4
Dynamically local-enhancement planner for large-scale autonomous driving
Deng, N., Zhou, W., He, Y., Cheng, Q., Zhang, B., Wen, J., Liu, C., He, J., Sha, X., Qian, Z., et al. (2026) · Communications in Transportation Research · doi:10.26599/commtr.2026.9640020
Towards an LLM-Powered Expert System for AAS-Based Product Digital Twin Development
Nguyen, Q.-D., Suri, K., & Sidibé, G. D. S. (2026) · IEEE International Conference on Software Architecture Companion (ICSA-C) · doi:10.1109/icsa-c68850.2026.00081
Bonás, G. K., Junior, R. M., Piau, M., Laitz, T., Almeida, T. S., Abonizio, H., Larcher, C. H. N., Pires, R., & Nogueira, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39898-7_25
Chen, X., Gong, Y., Ye, J., Li, C., Yang, S., & Wang, W. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.108896
Engineering Agent Feedback Loops
Nagasubramanian, D. (2026) · Apress eBooks · doi:10.1007/979-8-8688-2361-9_11
Refactoring Object‐Oriented Software With ChatGPT: An Empirical Study
Abdulsalam, H. M., Alawadhi, R., Ali, B. A., Alkandari, A. A., & Dallal, J. A. (2026) · IET Software · doi:10.1049/sfw2/3348017
Meena, S., Jain, A., & Saini, A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14186-6_33
Evaluation and Hardening of LLM System Instructions Against Extraction via Encoding Attacks
Sahu, A., Samanta, D., & Soosahabi, R. (2026) · International Conference on Cybersecurity and AI-Based Systems (Cyber-AI) · doi:10.1109/cyber-ai70573.2026.11755165
An Empirical Study on Reasoning and Generalization in Large Language Models
Xiang, L., Zhao, Y., Zhang, Y., Ren, Z., Zhang, X., Chen, Z., & Zong, C. (2026) · Computational Linguistics · doi:10.1162/coli.a.619 · Cited by 1
Li, D., Liang, Y., Qian, S., Sun, Y., Wu, H., Jia, W., Han, W., & Fu, Y. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114705
Sorour, S. E., El-deep, S. E., Alojail, A., & Kahouf, S. A. E. (2026) · Journal Of Big Data · doi:10.1186/s40537-026-01420-w
Paper Espresso: From Paper Overload to Research Insight
Du, M., Tuan, L. A., Huang, D., & Ng, S.-K. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840141
Exploring ‘Value Alignment’: A Genealogy and Three Conceptions
López-Castro, D. (2026) · Law, governance and technology series · doi:10.1007/978-3-032-13063-1_11
Extraction d'événements à partir de peu d'exemples par méta-apprentissage
Tuo, A. (2023) · theses.fr (ABES) · doi:10.70675/c0e71ba9zea5ez41b5zaa59z4b6fb1a1c0c9
Applications of AI to study of finite algebraic structures and automated theorem proving
Shminke, B. (2023) · theses.fr (ABES) · doi:10.70675/0d737c2fz40cfz4bdez97baz0e818934e2c5 · Cited by 1
Learning Semantics and Geometry for Scene Understanding
Cao, A. Q. (2024) · theses.fr (ABES) · doi:10.70675/7a57d933z692ez463cza75cz9fda3dccff2b
Prédiction structurée basée sur des segments pour l'extraction de graphes d'information
Zaratiana, U. (2024) · theses.fr (ABES) · doi:10.70675/ae81adb9za996z4b40zb1d2z1f44e6717c93
Zhou, Y. (2024) · theses.fr (ABES) · doi:10.70675/8ec4dbe0z863dz45b6z8150zbdca53aadd38 · Cited by 1
Evaluation of probabilistic classifiers and impact on decision-making
Perez-Lebel, A. (2024) · theses.fr (ABES) · doi:10.70675/3fc4a1e5z4347z4db6za88cz981c11af63d2
Laï-king, M. (2025) · theses.fr (ABES) · doi:10.70675/e9422bf7zf52dz461bza1a5z2593be8e49c3
Human-Machine Conflict in Human-Machine TeamingPreprint
Chen, M., Xiong, W., Tsao, L., & Ma, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6508019 · Cited by 1
FedDetox: Robust Federated SLM Alignment via On-Device Data Sanitization
Zhu, S., Chen, J., Yu, Y., & Ochiai, H. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729361
Création éthique de données textuelles artificielles : application au domaine biomédical
Hiebel, N. (2025) · theses.fr (ABES) · doi:10.70675/ed1998c5z91c4z41b2z94edz9316aa820a03
Hintze, A., Sokratous, K., & Thomas, I. (2026) · Computers in Human Behavior Artificial Humans · doi:10.1016/j.chbah.2026.100306
Berhe, T., Gebreab, S. A., Musamih, A., AlKhader, W., Salah, K., Ellahham, S., & Jayaraman, R. (2026) · Array · doi:10.1016/j.array.2026.100819
Compliance co‑pilot: generative LLM for power document revision suggestions
Zhu, Z., Xu, Q., Shan, C., & Li, Y. (2026) · International Conference on Power Electronics and Artificial Intelligence (PEAI) · doi:10.1117/12.3111672
Muñoz-Babiano, F., Lamo, P., & Alonso, R. S. (2026) · ADCAIJ ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL · doi:10.14201/adcaij.32926
Lombardi, R., Destère, A., Dellamonica, J., Gérard, A. O., & Jozwiak, M. (2026) · JMIR Medical Education · doi:10.2196/82702
Duan, Y., Li, C., & Guo, B. (2026) · ISA Transactions · doi:10.1016/j.isatra.2026.04.033
Three Models of RLHF Annotation: Extension, Evidence, and Authority
Coyne, S. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812225 · Cited by 2
The ineffable heart: jeong and the fundamental limits of artificial intelligence
Kim, S. (2026) · AI and Ethics · doi:10.1007/s43681-026-01145-9
Stratified Geometry-Aware Data Selection: A Task-Dependent Analysis for Instruction Tuning
Alshamrani, S. (2026) · IEEE Access · doi:10.1109/access.2026.3689220
Liu, T., Li, S., Song, Z., Yu, S., Tian, Z., Yang, S., Huang, Y., & Yu, Z. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-6553-5_9
The Mirror Problem: Ai Bias As Reflected CognitionPreprint
Ziekenoppasser-Powell, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6638918
Ghojogh, B., & Ghodsi, A. (2026) · Springer eBooks · doi:10.1007/978-3-032-10738-1_11
Gebreegziabher, S. A., Sproul, A. E., Yang, Y., Chen, C., Gómez-Zará, D., & Li, T. J.-J. (2026) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3830398.3830543
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.