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 4,201–4,300 of 4,340
Mehmood, S., Khan, F. M., Alharbi, A. A. K., Saudagar, A. K. J., Alkhattabi, M., Khan, M. A., & Khan, M. A. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1958283
Gürsoy, G., & Güvenoğlu, E. (2026) · International Artificial Intelligence and Data Processing Symposium (IDAP) · doi:10.1109/idap71869.2026.11727964
Muksalmina, M., & Taufiq, T. (2026) · SULIWA Jurnal Multidisiplin Teknik Sains Pendidikan dan Teknologi · doi:10.62671/suliwa.v3i3.350
Vrabie, C. I. (2026) · Teaching Public Administration · doi:10.1177/01447394261502444
Helpfulness Tax: A Per-Category Measurement of Refusal-Driven Helpfulness Gaps in LLM Safety
Uluırmak, B. A., & Kurban, R. (2026) · International Artificial Intelligence and Data Processing Symposium (IDAP) · doi:10.1109/idap71869.2026.11728145
Biomedical QA: Factorial Study of Architecture and PEFT on PubMedQA
Teker, Ö. F., Kaçıkan, E., & Onan, A. (2026) · International Artificial Intelligence and Data Processing Symposium (IDAP) · doi:10.1109/idap71869.2026.11728240
Contextual Language Modeling for Domain-Specific Knowledge Generation
Patkar, P., BasiReddy, S. R., Kasimala, K., Pappula, K. K., Enjam, G. R., & Sadat, Q. T. (2026) · doi:10.1109/incect72370.2026.11742603
Turner, L., Kelleher, M., Zahn, A., Sathyan, A., Warm, E. J., Furniss, D., Overla, S., Zheng, W., & Cohen, K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-35459-4_16
Ma, H., & Kwan, M. (2026) · Transactions in GIS · doi:10.1111/tgis.70434
Advanced Secure Knowledge Extraction Techniques for Large Language Models
-, L. C. B., Syed, K., Vepachedu, N., Oinam, R. S., Vaithiyalingam, R. V., & Sadat, Q. T. (2026) · doi:10.1109/incect72370.2026.11742788 · Cited by 4
VSRL: A Unified Reinforcement Learning Framework for Autonomous Search in Vertical Domains
Li, S., Gao, Z., Cheng, W., Ji, W., Yuan, C., & Zhu, X. (2026) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2026.089753
PersonaBreak: inducing low-safety personas for automated LLM jailbreaking
Qiu, L.-Q., Xie, H., Kang, Q., & Chen, J. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08954-z · Cited by 1
Li, J. (2026) · International Conference on Biomedical and Intelligent Systems (IC-BIS) · doi:10.1145/3841905.3841977
Aligning AI Requires Aligning with Each Other: A Covenant
Tsiokos, I. (2026) · PhilPapers (PhilPapers Foundation) · doi:10.5281/zenodo.23413555
Prince, E. H. (2026) · Synthesis lectures on visualization · doi:10.1007/978-3-032-37873-6_2
Roumeliotis, K. I., Margaris, D., Spiliotopoulos, D., & Vassilakis, C. (2026) · Information · doi:10.3390/info17111073
A Semantic and Lexical Analysis of LLM-Generated Responses in Comparison with Stack Overflow Answers
CELEPKOLU, K. C., Ortakcı, Y., & Karaoğlan, K. M. (2026) · Sakarya University Journal of Computer and Information Sciences · doi:10.35377/saucis...1865546
Jaffri, S. U., Koo, A. C., Ting, C., & Hussain, S. (2026) · Healthcare · doi:10.3390/healthcare14213643
Lee, C.-H., An-Zhe, L. A., Yu-Hsin, L., Guan-Hsiung, L., & Wu-Chuan, Y. (2026) · doi:10.1109/iot-life68455.2026.11746235
EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy DistillationPreprint
Xiao, Y., Zhang, X., Cheng, Y., Guo, S., Sun, Y., Zhu, Z., 谢思桃, Tong, G., & Luo, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.35690
Guo, R., 薛典军, Zhu, B., Liu, X., Geng, Y., & Meng, X. (2026) · Future Internet · doi:10.3390/fi18110583
Safety Attention Heads are Fragile: Gradient-Guided Covert Poisoning in LLM Fine-Tuning
Tong, D., Lin, J., & Zhao, J. (2026) · IEEE International Conference on Artificial Intelligence, Computer Science and Information Processing (AICSIP) · doi:10.1109/aicsip69702.2026.11743997
Lu, J. G., Zhao, G. G., & Zheng, A. (2026) · Strategic Entrepreneurship Journal · doi:10.1002/sej.70050
Chatbots, Virtual Assistants, and AI-Enhanced Customer Service
Sharma, G. M., Tiwari, N. K., Najeeb, A., Shikha, M., & Mishra, R. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-4967-9.ch001
LLMs for Transforming Data-Driven Research Discovery
Sharma, S. (2026) · IGI Global eBooks · doi:10.4018/979-8-2600-1227-7.ch010
From observation to generation: A complex-systems perspective on generative Human–AI social systems
Ma, Y., Peng, M., Hu, S., Zhu, B., Wang, Y., Chen, Y., Liu, S., & Cheong, K. H. (2026) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2026.119312
Kishore, M. N., & Navaneethan, C. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1983619
Conservative Dueling Bandits: Preference Learning under Baseline ConstraintsPreprint
Deb, R., Ghavamzadeh, M., & Banerjee, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.36708
Neto, J. L. A., Teixeira, C. A. D. M., de León, C. P., & Francês, C. R. L. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117230
Özdemir, M. A., Özcan, H., & Pehlivanoğlu, M. K. (2026) · Applied Sciences · doi:10.3390/app162110690
Brain-RL: Logic-consistent reinforcement learning for multimodal fMRI-to-text decoding
Zhang, L., Qin, F., Pan, Q., Liu, Y., Wang, R., Xiong, Y., Chen, H., Li, R., & Huang, W. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104911
When AI Helps Too Well: Transformative Inquiry and the Risk of Second-Order Drift in Ethics Research
Titz, I. (2026) · Philosophy & Technology · doi:10.1007/s13347-026-01209-y
Xu, Y. (2026) · Computers and artificial intelligence. · doi:10.70267/cai.v3n5.3339
Damastuti, F. A., Gumelar, A. B., Firmansyah, K., & Jodhinata, A. (2026) · Entertainment Computing · doi:10.1016/j.entcom.2026.101257
MutQA: A Cross-Validated Q&A Dataset for Genetic MutationsPreprint
McCourt, R., Arredondo, D., Macaulay, O., Poshiya, S., Edeh, O., Virupakshappa, K., Bach, M. N., Ruiz, E. A., Hu, Y., Tafoya, L. E., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.10.27.762236
Guo, M., Likun, L., Hu, Z., Ge, M., Zhang, Y., Guo, Y., Wang, H., & Yu, X. (2026) · Cybersecurity · doi:10.1186/s42400-026-00685-1
Hilbert, M. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2610670123
AI-Driven Enterprise Information Orchestration Framework
Selvanayagi, A., Rakshaa Bala, B., Rohini, S., & Sandhiya, M. (2026) · International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) · doi:10.1109/i-smac70384.2026.11747938
Language-Based Task Routing for Vision-Language-Action Systems
Farkas, B. K., Galambos, P., & Széll, K. (2026) · IEEE International Symposium on Intelligent Systems and Informatics (SISY) · doi:10.1109/sisy71351.2026.11738549
Detecting Jailbreak Attacks Through Unrestricted Model Responses for Large Language Models
Sánchez-Arévalo, F. Á., Martínez-Cruz, A., & Campos-Sánchez, R. C. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-42770-0_10
Preference-Gradient Subspaces for Memory-Efficient Zeroth-Order Alignment of Large Language Models
Zhou, S., & Ji, J. (2026) · International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI) · doi:10.1109/ichci71425.2026.11739849
Handling LLM Output Instability in Production Routing Systems: A Systems and ML Empirical Study
Aravind, P. M., & Rambabu, P. (2026) · International Conference on Innovative Mechanisms for Industry Applications · doi:10.1109/icimia69818.2026.11744902
How I Aligned Your Model: Scaling Up Multilingual Safety Training with TemplatesPreprint
Neuwinger, M., Yukhymenko, H., & Schlag, I. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.40516
A unified evaluation framework for revising inappropriate arguments with edit-level guidance
Ziegenbein, T., Lukic, S., & Wachsmuth, H. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1869755
Hanh, N. D., & Thu, H. L. T. (2026) · Journal of Military Science and Technology · doi:10.54939/1859-1043.j.mst.114.2026.175-182
LoRA Fine-Tuning of Traditional Chinese Medicine Large Language Models
Zheng, J., Cao, R., He, S., Su, W., & Wang, T. (2026) · International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI) · doi:10.1109/ichci71425.2026.11739828
LLM-Driven Multi-Agent Reinforcement Learning for Autonomous Industrial Systems
Yu, Z., 代一霜, Fang, Y., Xie, H., & Li, J. (2026) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea69962.2026.11743612
LLM-Guided Procedural Content Generation: A Multi-Engine 3D Level Generation Framework
Varun, G., S, R. R., & Kavitha, G. (2026) · IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET) · doi:10.1109/acroset70960.2026.11742338
Chen, T., & Cai, Y. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.819
Zhang, W., & Liu, P. (2026) · International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI) · doi:10.1109/ichci71425.2026.11739832
Dang, W., & Gao, L. (2026) · PLoS ONE · doi:10.1371/journal.pone.0357928
MemCanvas: A Structured Memory Canvas for Evolving Intent Alignment in LLM Dialogues
Ye, J., Fei, Y., Lu, Y., Zhou, Z., & You, W. (2026) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3830398.3830596
Gao, E.-T., & Chen, Z. (2026) · ACM Symposium on User Interface Software and Technology · doi:10.1145/3830398.3830669
Research Trends in Human-Agent Interaction Using Intelligent Systems Technology
Kobayashi, K. (2026) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.146.979
Hallucinations in generative LLMs for radiology: a comprehensive review
Martín‐Noguerol, T., Úbeda, P. L., & Luna, A. (2026) · Current Problems in Diagnostic Radiology · doi:10.1067/j.cpradiol.2026.10.014
Structural Collateralism: Architecture, Function, and the Co-production of Harm
Vidotto, G. (2026) · Philosophy & Technology · doi:10.1007/s13347-026-01222-1
A Tutorial on Reinforcement Learning for LLMs: RLHF and Beyond
Jiang, D. R. (2026) · doi:10.1287/educ.2026.0311
Karunanayaka, I. P. (2026) · INTELETICA · doi:10.4114/inteletica.vol3iss6pp40-61
Lukianchuk, I., Бойко, Л. С., & Кондіус, І. (2026) · Applied Computer Systems · doi:10.2478/acss-2026-0017
POLAR: Policy Optimization through Larger Reasoners
Yuan, Y., Xiao, Z., & Zhang, M. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3841057
TUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework
Yuan, L., Mi, C., Shi, X., Mao, Y., Niu, S., Zhu, X., He, J., Lin, Z., & Law, C. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840154
Panagoulias, D. P., Tsichrintzi, E.-A., Savvidis, G., Tsoureli‐Nikita, E., & Sakkopoulos, E. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.09.267
Entropy Interventions Do Not Transfer: Why RLVR Entropy Control Misfires in On-Policy Distillation
Lin, X., Hao, Z., Liu, L., Lin, X., Ji, W., Nie, Z., & Yongkang, Y. A. N. G. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840067
Liu, T. (2026) · International Journal of Computer Science and Information Technology · doi:10.62051/ijcsit.v8n7.12
Inverse Adaptation: Cross-Cultural Moral Divergence in Large Language Models
Bellini, E., Bucur, A.-M., & Crestani, F. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.09.296
Wang, X., Guo, Y., Yao, S., Wang, Z., Lin, W., Feng, W., Wen, A., Pan, P., Zheng, P., Chen, G., et al. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840990
Semantic diffusion and large language model collaboration for cross-modal sign language translation
Wei, S., & Yuan, T. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02768-y
Introduction: Why AI Fairness Needs a Diagnostic Toolkit
Tavakoli, H. (2026) · Apress eBooks · doi:10.1007/979-8-8688-2885-0_1
OPERA: Option-level Pedagogical Explanation via Reasoning for Augmented Knowledge Tracing
Huang, Z., Li, X., Zheng, J., Zhao, X., & Liu, Z. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3841111
A Speech-Driven 3D Virtual Teacher with Pedagogical Adaptation and Retrieval-Augmented Generation
He, Y., Hou, X., Liu, H., Zhao, Y., & 刘京昕 (2026) · doi:10.1109/icaie70080.2026.11751070
Tao, W., Gou, Z., Chen, Z., Dai, Q., Lu, Q., & Jiang, N. (2026) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3799682.3840164
Clustering agent representation for explaining reinforcement learning policies
Alaarabiou, M., Delestre, N., & Vercouter, L. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.09.302
Bao, X. (2026) · Research Square · doi:10.21203/rs.3.rs-11254502/v1
Garrido‐Merchán, E. C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.41962
Lee, J. W., Banerjee, A., & Lee, Y. C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.02319
Reducing LLM Hallucinations through Multi-Model Synthesis and Cross-Verification
Rehman, T., Seikh, M. T., Roy, R., & Siddhanta, D. (2026) · doi:10.1109/aidml70736.2026.11749336
An Artificial Immunity Framework for Resilient AI Systems
Xie, X. (2026) · International Conference on Cybersecurity and AI-Based Systems (Cyber-AI) · doi:10.1109/cyber-ai70573.2026.11755156
Verifying Alignment Constraints Under Finite-Sample Uncertainty with Inferred Data
Metevier, B., Springer, M., & Turbal, B. (2026) · ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) · doi:10.1145/3846167.3848607
Deterministic Governance for LLM-Based Technical Support: A Hybrid AI–Human Approach
Martins, E. V., & Manssour, I. H. (2026) · International Conference on Machine Learning and Applications · doi:10.1109/icmla69890.2026.00128
A Lightweight Neuro-Symbolic Approach for Alloy Counterexample Explanation
Zhou, G., Liu, J., Zhu, T., Liu, Y., Tang, X., & Li, J. (2026) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme67971.2026.00098
Shatnawi, A., Alhathli, M. A. E., Karajeh, O., & Al-Abdullah, M. (2026) · International Conference on Cybersecurity and AI-Based Systems (Cyber-AI) · doi:10.1109/cyber-ai70573.2026.11755159
Mixed-Prompt Training for Robust Tool Learning in Ship Inspection
Nyberg, C., Singh, K., & Kim, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-44176-8_31
Multimodal Agent Development and Educational Application Based on GLM-4
Huang, S., & Ma, Y. (2026) · Journal of big data and computing. · doi:10.62517/jbdc.202601331
Utility-Aware Generative Recommendation: Utility-Enriched Semantic Codes and Utility-Guided DecodingPreprint
Hu, Y., Wang, D., Li, N., Li, K., She, J., Guo, C., Cai, K., Liu, B., Liu, Y., & Chen, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.02981
Mahmood, T., Afzal, M. T., Al‐Shamayleh, A. S., Mustafa, G., Díez, I. D. L. T., Rodríguez, L. J. H., & García, P. H. (2026) · Computation · doi:10.3390/computation14110272
Digital Revenants: Voices of the Dead in the Age of AI
Ramello, S. (2026) · Society · doi:10.1007/s12115-026-01330-w
Li, J., Golilarz, N. A., & Rahimi, S. (2026) · International Conference on Machine Learning and Applications · doi:10.1109/icmla69890.2026.00173
Feng, Y., Zhang, L., Chen, Y., Zhao, J., Jin, C., Gong, L., Liu, Y., Ye, C., Li, H., Qu, L., et al. (2026) · doi:10.1145/3840470.3841781
Delta-Weight Quantization Preserves Alignment in Large Language Models
Liu, Y., Sun, Z. T., & He, X. (2026) · doi:10.1145/3846374.3846393
Lorenz, U. (2026) · Koli Calling International Conference on Computing Education Research · doi:10.1145/3856208.3856227
Abedini, K. (2026) · Koli Calling International Conference on Computing Education Research · doi:10.1145/3856208.3856274
Subhan, M., Raza, A., Yeom, S., Kim, S.-H., & Yang, H.-J. (2026) · Research Square · doi:10.21203/rs.3.rs-11206695/v1
Beyond Technocentrism: Kantian Humanism and the Ethics of AI Substitution
Mudd, S. (2026) · Canadian Journal of Philosophy · doi:10.1017/can.2026.10129
Sparse Internal Control of Language ModelsPreprint
Zhang, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.04349
Long-Horizon Vision-Language Navigation by Memory Editing
Ding, M., Xie, X., Shi, H., Wang, S., & Wu, J. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835854
Self-citationRAP: Relation-Aware Post-training for Multimodal Large Language Models
Liu, Y. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836031
LLM4Rail: An LLM-Augmented Personalized Railway Services Platform
Li, Z., Deng, X., Feng, C., Li, H., Wang, S., Fan, J., Shen, J., Wen, Z., Gao, L., & Wu, L. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-7735-3_27
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.