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 4,101–4,200 of 4,340
Amiri, M., Mokari, A., & Bocklitz, T. W. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02369-8
Compact Wisdom at Small Scale: Small Language Models as Cultural Assistants
Manimegalai, R., M, S. S., Aravinda Krishnan, L., & Subramanian, V. (2026) · International Conference on Smart Systems for Electrical, Electronics, Communication and Computer Engineering (ICSSEECC) · doi:10.1109/icsseecc69062.2026.11722292
Das, S. K., Burchfield, R., Wiggins, G. M., Guy, A., & Ghosal, T. (2026) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/3805696.3846509
GÜLTEKİN, A. (2026) · Philosophies · doi:10.3390/philosophies11050186
Popun, J., Lee, W., Srisomboon, K., Pipanmekaporn, L., & Prayote, A. (2026) · Applied Sciences · doi:10.3390/app162010076
Применение больших языковых моделей (LLM) в психологии
Владимирович, О. А. (2026) · CyberLeninK (CyberLeninka) · doi:10.24412/2223-6872-2026-258-38-49
Fan, X., Zhu, L., & Qin, C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7601923
Pragmatics-zombies: Trust and communication in the age of artificial intelligence
Firt, E., & Nir, B. (2026) · Pragmatics and Society · doi:10.1075/ps.25161.fir
LLM-Empowered Syntactic Parsing With In-Context Learning for Multifunction Radar
Zhao, Y., Wang, X., & Huang, Z. (2026) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2026.3742698 · Cited by 1
Lodrant, K. (2026) · Repository of the University of Ljubljana (University of Ljubljana)
Two-Layer RAG for Value Grounding and Schema Linking in LLM-Based Text-to-SQL Systems
MACÊDO, J. G. U. D., Miyaji, R. O., Moulin, R., & Machado, L. (2026) · Simpósio Brasileiro de Bancos de Dados (SBBD) · doi:10.5753/sbbd.2026.249462
Kutsiuk, D., & Gorokhovskyi, K. (2026) · Cybersecurity Education Science Technique · doi:10.28925/2663-4023.2026.34.1269
Exposing and Securing LLMs Against Hypocrisy-Induced Manipulation
Wang, Z., Li, G., Zhang, B., & Guo, L. (2026) · IEEE Conference on Communications and Network Security · doi:10.1109/cns69863.2026.11720885
When Pleasing the User Compromises Care: AI Sycophancy in Caregiver-Mediated HealthcarePreprint
Mishra, P., Beniwal, A., Yi, Z., Ding, Y., & Liu, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.14360
Ren, Y., Li, A., Cheng, C., Hu, H., Liang, H., Xie, B., Yuan, J., Wu, H., Fu, Y., & Wang, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.16927
A BERT based LLM System for Legal Cases with Feedback Mechanism
Du, S., Xu, Y., & Song, W. W. (2026) · International Conference on Big Data Technologies (ICBDT) · doi:10.1145/3830360.3830377
Gao, L., Li, Y., Zhang, T., Huang, Q., Zhao, C., Kang, Z., Hu, J., Zhong, Y., Gao, Z., Tang, F., et al. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835750
Structure-Aware Behavioral Alignment of Large Language Models for Robust Time Series ForecastingPreprint
Hu, M. (2026) · Research Square · doi:10.21203/rs.3.rs-11151674/v1
Zhao, Z., Wang, Y., Li, J., & Lah, S. C. (2026) · Symmetry · doi:10.3390/sym18101714
Cheng, A., Tong, S., & Peng, K. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-6916-7_19
Sun, Y. (2026) · International Conference on Computer Science, Machine Learning and Agents (CSMLA) · doi:10.1109/csmla70906.2026.11724504
Textbook-Enriched Training for Language Models: Boosting Answer Quality in Specialized Contexts
Mota, L. B. B., Dantas, L., Claro, D. B., Paes, A., Freitas, C., Souza, M., Caseli, H. M., & Real, L. (2026) · Simpósio Brasileiro de Tecnologia da Informação e da Linguagem Humana (STIL) · doi:10.5753/stil.2026.26566
Yu, M. (2026) · Advances in Education · doi:10.12677/ae.2026.16102156
Contextual Credit Policy OptimizationPreprint
Han, H., Zeng, Z., Zhu, Z., Bei, S., Wang, H., Xu, H., Han, Y., Zhi, D., & Fan, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.19103
Tao, Y., Li, J., & Kong, D. (2026) · International Conference on Computer Science, Machine Learning and Agents (CSMLA) · doi:10.1109/csmla70906.2026.11724463
UnifiedBench: Toward a Unified Dataset for Red-Teaming Language Models
de Sá, M. A., de Senna, P. H. G., Neto, M. P. P., & Miers, C. C. (2026) · Simpósio Brasileiro de Cibersegurança (SBSeg) · doi:10.5753/sbseg_estendido.2026.29187
OPTICODE: AI-Powered Python Code Enhancement with Explainable Insights
Stalin, T. S., Alna Tomy, A., Kadheeja, N., Swathi, S., Parichippully, N., & Wilson, B. (2026) · International Conference on Trends in Engineering Systems and Technologies (ICTEST) · doi:10.1109/ictest69239.2026.11722635
Safety-Usefulness Relative Shift in Multi-turn Dialogues of Large Language Models
Li, W., Li, R., & Li, M. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-6621-0_8
Bootstrapping Knowledge Acquisition from Domain Text with a Seed Ontology and Small Language Models
Tan, H., Yang, Y., Yuan, T., & Li, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-41614-8_11
Evaluating LLMs for named entity recognition: a cost-benefit analysis in the legal domain
Singhal, S., O’Connell, E., McCarroll, N., Keogh, N., Doherty, M., Munasinghe, V., Rani, S., Curran, K., McNamee, E., Clist, A., et al. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-026-02886-z
AI sycophancy, self-interpretation, and conversational contentment
Tiran, N. (2026) · AI and Ethics · doi:10.1007/s43681-026-01451-2
Kabakuş, A. T. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12557-3
Introduction to Large Language Models (LLMs)
Tashdid, I., Tasnia, K., & Rahman, S. (2026) · Springer eBooks · doi:10.1007/978-3-032-34116-7_2
An Exploratory Comparison of LoRA Adaptation Configurations for Tic-Tac-Toe
Morillo, P., Bermeo, Y., & Vega, A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-42763-2_12
Tressyalina, T., Ghaluh, B. M., & Wulandari, E. (2026) · Journal of Pragmatics · doi:10.1016/j.pragma.2026.09.009
DynamicGater: Fine-Grained Recovery for Machine Unlearning via Dynamic Neuron Gating
Chen, X., Cai, H., Guo, E., Qu, S., & Shang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-6834-4_14
Zheng, C., Peng, C., Liang, S., Cai, Z., Peng, Z., & Chen, Z. (2026) · Research Square · doi:10.21203/rs.3.rs-11029574/v1
Decolonizing Digital Dialogues: A Critical Theory Analysis of Large Language Models
Tingelhoff, F., & Marga, J. J. (n.d.) · AIS Electronic Library (AISeL)
The Intrinsic Low-Rank Geometry of LLM Alignment: Universality and Scaling Laws of the Gradient
Fang, C., Xi, W., Shi, Q., Fang, Y., & Ding, Z. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728649
Action Selection Advantage Estimation in Multi-Agent Reinforcement Learning
Zhao, X., & Sugawara, T. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11730019
Generative Value ClassifierPreprint
Swerdlow, A., Dong, P., & Finn, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.22497
Deep fitted value iteration: Algorithm and theory
Jiao, Y., Kang, L., Yang, J. Z., & Zhang, P. (2026) · Science China Mathematics · doi:10.1007/s11425-025-2674-4
Guo, Y., Li, A., Tang, Q., & Ma, H. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729084
Mitigating Context Divergence in Multi-Turn Embodied Reasoning via Hierarchical Decay
Liu, G., Wang, M., & Li, P. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11730063
Explainable Recommendation with Topic-enhanced Personalized Prompt Learning
Tang, R., Yang, C., & Yi, P. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728608
Wei, J., Yang, Y., & Xu, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-6910-5_10
AS-SYNERGIC: Orchestrating Synergistic Safety and Availability Attacks on Large Language Models
Liu, Y., Wang, X., Zhang, Z., Yang, M., & Wu, X. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729398
Generating Plausible Sequences of Protein Groups with Latent Optimal Transport Flow Matching
Kong, Z., Xu, Y., Jiang, X., Wu, J., & Xu, H. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728557
Self-citationShi, D., Zhuang, Z., & Wang, D. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728762
A Market-Aligned Reinforcement Learning Framework for Financial Sentiment Analysis
Liu, Z., Sham, C., Li, J., Ma, S. L., Yue, Z., & Fu, C. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729208
CADRL: Aligning LLMs with Context-Aware Disentangled Reward Learning
Xu, B. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729714
CoSu-UQ: Uncertainty Quantification for Reasoning via Confidence and Semantic Support
Feng, Y., Lin, Q., Zhang, Y., Yang, Z., & Zhou, L. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11730028
Motion Generation from Fine-grained Textual Descriptions With AI Feedback
Wang, R., & Wang, K. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729526
Kofránek, J. (2026) · Medsoft · doi:10.35191/medsoft_2026_1_38_kofranek_i
Medium-GRPO: Online Difficulty-Adaptive Calibration for Enhancing LLM Reasoning
Feng, Y., Su, F., & Cui, Z. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728651
Beyond Reward Scoring: Online Multi-Agent Preference Learning for Multimodal Response GenerationPreprint
Zou, Z., Hong, J., Lu, Y., Tang, S., Wu, W., Gupta, A., Tian, J., & Razzak, I. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.23256
RL-Enhanced ProRAG: A Proactive Retrieval-Augmented Generation Framework for Multi-Hop Reasoning
Luo, X., Huo, Y., Qin, Y., Feng, F., Liu, G., Xia, D., & Wong Derek, F. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728741
Hortea, G., Romano, S. P., Tapiador, J., & Varlese, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.23534
Modular Fine Tuning of Large Language Models for Specialized Knowledge Domains
Rajpoot, A. K., Virdee, B., & Khanna, A. (2026) · International Conference on Computational Intelligence Systems and Devices (ICCISD) · doi:10.1109/iccisd69924.2026.11731955
ReaSafe: Reasoning-Centric Safety Alignment for Multimodal LLMs via Preference Optimization
Dong, X., Zhao, K., Hu, W., & Su, H. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729963
Robustness of Language Models against Portuguese Harmful Prompts
de Amorim, E. A., & Zanchettin, C. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729377
MTOD: An LLM-Based Proactive Task-Oriented Dialogue System for Latent Goal Discovery and Completion
Zhang, H., Wang, B., Yu, Z., Xue, C., He, R., & Hou, Y. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729298
Li, W., Song, S., Liu, X., Ji, B., Xiao, J., Wang, J., Gao, Z., & Yu, J. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729050
Position Paper: Just as Humans Need Vaccines, So Do Models - Immunization to Combat Falsehoods
Raza, S., Qureshi, R., Farooq, A., Lotif, M., Chadha, A., Pandya, D. A., & Emmanouilidis, C. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728502
Boosting Triple Extraction and Relation Normalization with Trained Retrieval and Policy Optimization
Bai, Y., 卞建胜, & Chen, J. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729960
Chuon, C., Leechat, P., & Vittayakorn, S. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108364
FAIRITHM: Unlearning Bias and Rewriting for Fairness
Nam, Y., Lim, D., Im, S., Xiong, Z., & Park, J. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2744493
Flourishing-centered AI: designing AI for the multiple goods and tensions of living well
Tay, L., Vold, K., Liou, G., Kumar, H., Harris, D., & Anderson, A. (2026) · The Journal of Positive Psychology · doi:10.1080/17439760.2026.2758626
Talati, S., & Fatahi, S. (2026) · IEEE International Conference on Intelligent Systems · doi:10.1109/is71416.2026.11727334
Além da Distância Linguística: Jailbreaks Multilíngues em LLMs Especializados por Idioma
da Silva, G. D. J. C., & Westphall, C. B. (2026) · Anais do XXVI Simpósio Brasileiro de Cibersegurança (SBSeg 2026) · doi:10.5753/sbseg.2026.27096
Qu, P., Wang, S., & Song, L. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116701
197Chapter 9 Machine Translation in Migratory Contexts
Pérez, C. R., & Alvarez-Vidal, S. (2026) · De Gruyter eBooks · doi:10.1515/9783112205945-010
Choi, D., & Park, J. (2026) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/10711813261493607
RG-Agent: Risk-Gated and Adaptive LLM Agents for Reliable Automated Tabular Data Analysis
Meng, W. (2026) · IEEE Access · doi:10.1109/access.2026.3745424
Sittakul, V., Ioannou, I. I., Nagaradjane, P., Sirikunchittavorn, O., Ampasavat, S., Benjakhan, B., & Sinrungtham, S. (2026) · International Conference on Networks, Computers and Communications (ICNCCom) · doi:10.1109/icnccom69117.2026.11736285
Son, T. N., Trinh, T. N., Dang, T. P., Pham, L. T., & Thai, Q. H. L. (2026) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/1674/1/012063
Jiang, X. (2026) · Energies · doi:10.3390/en19205020
Self-citationGenerative künstliche Intelligenz
Ambach, D. (2026) · Springer eBooks · doi:10.1007/978-3-662-73474-2_5
Large Industry Models: Konzept und Reifegradmodell
Luckow, A., Klepsch, J., Karch, L., Bertle, V., Sturm, J., & Pichlmeier, J. (2026) · Springer eBooks · doi:10.1007/978-3-662-73474-2_17
MACRA: a training-free multi-agent framework for reliable and cost-aware clinical summarization
Yin, P., Zhu, C., & Tao, W. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08944-1
Synthetic Intimacy: Relational AI and the Interface of the Self
Shin, D. (2026) · Springer eBooks · doi:10.1007/978-3-032-39278-7_6
Safitri, A. D., Fatmawati, V. A., Salsabilah, I. N., Rachmawati, R. D., & MZ, A. F. S. A. (2025) · Journal of Digital Learning and Education · doi:10.52562/jdle.2025.1503
Kasab, B. S., Sai, T., & Parihar, V. R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7655832
MIST: Malicious In-Distribution Stealth Attack on LLMs via Benign Interspersion
Chen, Y., He, Z., & Hong, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-6837-5_8
DDMedChat: DoRA fine-tuning and DRAGIN RAG based medical chat framework with LLMs
Wang, S., Qu, G., Yu, D., & Wu, C. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135449
Digital mayflies: transient personhood of AI companions
Tait, I. (2026) · AI and Ethics · doi:10.1007/s43681-026-01465-w
Paired response final divergence signatures of jailbreak vulnerability in large language models
Ismail, H. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02593-2
Wang, J., Zhao, H., Wu, L., Lv, B., & Jia, N. (2026) · Production and Operations Management · doi:10.1177/10591478261502836
Zhou, Y. (2026) · Journal of Engineering and Applied Science · doi:10.1186/s44147-026-01288-w
Chen, M., Zhang, J., Wang, B., Ma, H., Xiao, H. R., & Ma, F. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.113746
AuditJudgLLM: a domain-specific large language model and benchmark for evaluating audit judgment
Huang, J., Xu, Z., Xu, C., Jiang, M., Li, P., Tiwari, P., & Xie, Q. (2026) · Information Sciences · doi:10.1016/j.ins.2026.124338
Chen, Z., Zheng, L. N., & Zhu, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.30763
People expect less but show equal influence of LLM versus human moral advice
Engelmann, N., Schmidt, E., Alhosseini, A., Hannikainen, I. R., & Dong, M. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101413
Shapley-based feature valuation with human feedback in data markets
Yin, B., & Wang, T. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117253
Bongiorno, V., Curioni, M., Hijnen, N., & Zhou, X. (2026) · Corrosion Engineering Science and Technology The International Journal of Corrosion Processes and Corrosion Control · doi:10.1177/1478422x261499611
Christa Daryn, P., Rishika, R., Christydass, S. P. J., Karthika, S. K., & Eswaran, M. (2026) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2026.101229
Large model empowered embodied AI: A survey on decision-making and embodied learning
Zhou, R., Liang, W., Ma, Y., Zhang, B., Li, S., Liao, Y., & Kuang, P. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135458
WANG, Y., & Zhang, Y. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02575-4
COMPASS: Benchmarking Safety‐Aware Vision‐Language Navigation in Intelligent Transport Environments
Dolgopolyi, R., Khan, M. S., Ahmad, J. E., Vavousis, K., & Pitropakis, N. (2026) · IET Intelligent Transport Systems · doi:10.1049/itr2.70347
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.