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 3,401–3,500 of 4,340
Knowledge-Grounded Adaptive Reflection for Reliable and Fair Educational LLM Agents
Pan, K., Bi, Z., Zhao, K., Wang, Z., Liu, Z., & Lou, J. (2026) · International Conference on Large Models and Intelligent Agent Technologies (LMIAT) · doi:10.1109/lmiat70705.2026.11682086
VADA: A Multicultural Benchmark for Value-Aware Data Generation and Alignment Evaluation in LLMs
Zhang, Z., Feng, Y., Weng, S., Yin, Y., Li, J., & Liu, J. (2026) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3744916.3787807
Rahmani, A. S. E. I., Yahiaoui, Y., & Bouziane, A. (2026) · SN Computer Science · doi:10.1007/s42979-026-05333-6
Derivation boundaries: A structural source of faithfulness failure in large language models
Sreekumar, V. (2026) · Journal of Computer and Forensic Sciences · doi:10.5937/jcfs5-68363
Pal, A. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02240-w
Learning Active Perception for Pixel-Space Reasoning via Visual-Intent Stratified GRPO
Zhu, M., Chen, X., Yang, S., Yu, B., Zhao, H., & Jia, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36969-7_16
Ye, B., Zhu, F., & Lv, X. (2026) · International Conference on Educational Digitalization and Computer Science in the Guangdong-Hong Kong-Macao Greater Bay Area · doi:10.1145/3828183.3828323
Security and Safety of Large Language Models—A Use Case for Extended Reality Environments
Marin, L., Cidota, M. A., Ciocan, I., & Maathuis, C. (2026) · Applied Sciences · doi:10.3390/app16189093
Balancing Accuracy and Confidence in LLMs: Reinforcement Learning with Entropy-Calibrated Rewards
Kato, K., Chu, C., Murawaki, Y., & Kurohashi, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32732-1_12 · Cited by 1
Kale, Y. S., & Ocansey, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7460118
Aggarwal, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32732-1_10
Kim, C. (2026) · Applied Sciences · doi:10.3390/app16189098
Pandey, J., Pillai, H. R., & Semmandampalayam, P. (2026) · MEC International Conference on Big Data and Smart City (ICBDSC) · doi:10.1109/icadaai64945.2026.11679290
Stenzel, D. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-32729-1_30
Xu, Y., Yu, Q., Xu, B., Ye, F., & Feng, Z. (2026) · International Conference on Educational Digitalization and Computer Science in the Guangdong-Hong Kong-Macao Greater Bay Area · doi:10.1145/3828183.3828333
Hunk-Constrained DPO: Segment-Level Optimization for Secure and Correct LLM Code Generation
Huang, Q., Yin, X., Li, X., & Ni, C. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3816250
Liu, R. (2026) · International Conference on Educational Digitalization and Computer Science in the Guangdong-Hong Kong-Macao Greater Bay Area · doi:10.1145/3828183.3828371
TransAegis: Cross-Lingual Representation Steering-Based Low Resource Language Jailbreak Defense
Li, W., Wu, F., Yao, S., & Chen, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38410-2_19
Cultural bias or universal traits? Exploring personality-like profiles of large language models
Hang, Y., Soto, C. J., Lignier, B., Ling, Z., Liu, Q., Wang, Y., Zhu, J., He, X., & Wu, W. (2026) · Royal Society Open Science · doi:10.1098/rsos.252491
A Risk-Governed Deployment Framework for LLM-Powered Educational Companion Robots in K--12 Education
Wu, L., Zhang, M., Zhai, P., & Cao, Y. (2026) · International Conference on Digital Society and Artificial Intelligence (DSAI) · doi:10.1145/3833541.3833774
DisRM: Reward Modeling as Discriminative Prediction
Liu, R., Zhan, J., Guo, Y., He, Y., Wei, C., Yuille, A., & Chen, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37490-5_34
Baghel, S. S., Rathore, Y., Vatsi, R., Shukla, A., & Goyal, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38410-2_24
Function Space Search and Its Evolution: A Survey on Large Language Models in Algorithm Discovery
Fang, X. (2026) · International Conference on Machine Learning and Neural Networks · doi:10.1145/3821725.3821807
LLM-Enhanced Experience Replay for Reinforcement Learning-based Path Planning
Long, H., Zhou, J., & Wang, J. (2026) · International Conference on Machine Learning and Neural Networks · doi:10.1145/3821725.3821812
LLM-Empowered Intelligent Data Querying: A Unified Metadata Approach
Zhang, J., Ma, Z., Li, Z., Gao, Z., Shen, X., & Liao, Y. (2026) · International Symposium on Machine Learning and Media Computing (MLMC) · doi:10.1109/mlmc69743.2026.11686821
Zhong, Y., El-Diraby, T. E., & Goodfellow, S. D. (2026) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-7192
Kim, S., & Ko, B. (2026) · Applied Sciences · doi:10.3390/app16189190
Tucker, C., & León, M. (2026) · IEEE Opportunity Research Scholars Symposium (ORSS) · doi:10.1109/orss71174.2026.11684276
Generative Artificial Intelligence for vehicular networks: A survey
Elbey, N. E., Bitam, S., & Zeadally, S. (2026) · Ad Hoc Networks · doi:10.1016/j.adhoc.2026.104420
Quem controla o passado? IA generativa e as disputas pela memória coletiva na era digital
Huertas, E. M. C. G., & Fernandes, C. M. (2026) · Anagramas - Rumbos y sentidos de la comunicación · doi:10.22395/angr.v25n49a11
Table Understanding Enhanced Large Language Models for Chinese Table-to-Text Generation
Ni, Y., Li, Y., Li, S., He, Y., Li, Y., & Zeng, J. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684533
Evidence-Constrained Explanation Auditing for Targeted Policy Repair in Autonomous Pursuit Tasks
Zeng, Y., Ming, M., Chai, X., Luo, Y., He, Y., & Huang, H. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684582
Cross-layer manifold attack and projection for robust safety alignment of large language models
Peng, Z., Du, J., Zhou, Q., Zhu, J., & Li, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135082
GAVL-Diag: Graph-Augmented Vision-Language Diagnosis for Electric Vehicle Battery Faults
Liu, Y., Zhang, X., Luo, X., Tang, Y., Dong, S., & Xiao, H. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684584
Evaluating the Robustness of Safety-Aligned LLM Behavior to Short Contextual PrefixesPreprint
Cholewa, M., & Głomb, P. (2026) · Research Square · doi:10.21203/rs.3.rs-10590385/v1
Mohandoss, A. A., Thavarajah, R., Donthu, R. K., Sahoo, S., Tikka, S. K., & Ameen, S. (2026) · Indian Journal of Psychiatry · doi:10.4103/indianjpsychiatry_426_26
Yu, S., Li, L., Zhao, W., & Yang, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7478103
Guo, Z.-M., Dong, C.-Y., & Huang, X.-T. (2026) · Journal of Theoretical and Applied Electronic Commerce Research · doi:10.3390/jtaer21090329
Zhang, J., Wang, M., & Liu, Z. (2026) · International Conference on Artificial Intelligence and Product Design · doi:10.1145/3829918.3829963
Li, L. T., & Shi, L. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-37199-7_17
When AI Agents Rewrite Their Own Rules: Power-Seeking in Endogenously Changing Environments
Rozinek, O. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-37933-7_2
Chen, X., & Zhao, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7470718
Cao, J., Lv, H., Xue, J., Wang, S., Wang, H., Zhao, M., & Wang, W. (2026) · Cybernetics and Intelligence · doi:10.26599/cai.2026.9390020
Continuous Mitigation of Intersectional Algorithmic Pink Tax via PCA-Driven Latent Space Projection
Wang, T., & Sun, P. (2026) · International Conference on Machine Learning and Intelligent Computing · doi:10.1145/3829441.3829623
Mechanism of Generative AI Interaction Experience on Consumer Trust and Consumption Behavior
Tian, P. (2026) · International Conference on Machine Learning and Intelligent Computing · doi:10.1145/3829441.3829561
Detecting LLM Hallucinations via Anomaly Detection on Latent Representations
Malchiodi, D., Mas, L. D., Frasca, M., Rivolta, M. W., & Mazzon, I. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37976-4_10
Decoupling Reasoning from Execution: A Deterministic Runtime Architecture for Autonomous LLM Agents
Artur, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39143-8_22
SyncVL: Synchronizing Vision $$\Longleftrightarrow $$ Language Using Unsupervised Adaptation
Marrium, M., Khan, M. H., Javed, S., & Mahmood, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_21
Fu, Q., Que, X., Ma, X., Lin, M., Sun, S., & Chen, M. (2026) · Earth Science Informatics · doi:10.1007/s12145-026-02235-2
Dery, H., Piterman, D., Refoua, E., Meinlschmidt, G., Bar, K., Ben‐Zion, Z., & Elyoseph, Z. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101322 · Cited by 1
Messarhi, O., Kerdoudi, M. L., & Tibermacine, O. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.113101
The Evolution of Question Generation: Analyzing the Impact of Large Language Models
Bhakuni, P., Singh, G. B., Punia, A., Suyal, H., & Sharma, N. (2026) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.70133
A Controlled Study of Evidence Quality in LLM-Based Numerical Claim Verification
Le, Q. T., Badache, I., & Hamri, M. E. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39150-6_9
Personalized Alignment of Large Language Models
Woźniak, S., Koptyra, B., Gurgul, J., Kocoń, J., & Kazienko, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36868-3_26
The paradox of pleasing: therapeutic recognition and the limits of conversational AI
Haber, Y., Refoua, E., Elyoseph, Z., & Yinon, D. (2026) · AI & Society · doi:10.1007/s00146-026-03348-4
Alhwikem, F., Khan, A. R., & Jaskani, F. H. (2026) · Symmetry · doi:10.3390/sym18091572
OPVD: On-Policy Chain-of-Visual-Thought Distillation for Medical Reasoning
Zhang, N., & Yang, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38059-3_40
Effects of proactivity, autonomy, and transparency on user perception in human-AI agent interactions
Liu, N., & Zuo, Y. (2026) · International Journal of Industrial Ergonomics · doi:10.1016/j.ergon.2026.104058
Engineered approval: a critical discourse analysis of sycophancy in RLHF-trained language models
Ahmed, H., & Bhatia, S. (2026) · AI & Society · doi:10.1007/s00146-026-03350-w
Lv, Z., Xiang, L., Wang, D., Wu, H., Wang, Z., & He, Z. (2026) · International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC) · doi:10.1109/aiotc71250.2026.11688714
IDV: Customer-Context-Aware Multi-Engine Architecture for AI-Agent Intent Drift Detection in Finance
Zhou, M., & Xue, Y. (2026) · IEEE Conference on Computational Intelligence for Financial Engineering & Economics · doi:10.1109/cifer67845.2026.11692374
MedXEdit-GRPO: Reasoning-Aware Online RL for Counterfactual Medical Image Generation
Pan, Y., Xiao, R., Li, Q., Li, X., Li, X., Feng, R., & Zhang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38059-3_37 · Cited by 1
Wang, C., Zhang, Z., Xu, X., Zheng, M., Wei, G., & Zhang, X. (2026) · Foundations and Trends® in Programming Languages · doi:10.1108/ftpgl-11-2025-0068
Xu, A., Chang, B., Shu, K., Jian, L., & Song, Y. (2026) · Scientometrics · doi:10.1007/s11192-026-05807-7
Educational Paradigm Shifts in the Integration of Questioning and Prompting
Konstantinos, K. C., & Kotsanis, Y. (2026) · AI for Society · doi:10.3390/aisoc1010005
Huang, J., Wang, W., Liu, Y., & Song, F. (2026) · Applied Sciences · doi:10.3390/app16199429
Instruction-Tuned LLMs via Bayesian Mixture Model Preference Priors
Bregu, O., & Bouguila, N. (2026) · International Symposium on Networks, Computers and Communications (ISNCC) · doi:10.1109/isncc70543.2026.11693907
Jiang, Z., Zhou, X., Wang, H., Jiang, Y., Zheng, J., & Chen, Q. (2026) · International Conference on Computational Intelligence and Machine Learning (CIML) · doi:10.1109/ciml69155.2026.11692748
Zhang, Y., & Fu, P. (2026) · International Conference on Computational Intelligence and Machine Learning (CIML) · doi:10.1109/ciml69155.2026.11692804
Construction Method for Instruction Tuning Dataset for Domain-specific Entity Extraction Tasks
Kang, C., & Shen, C. (2026) · International Conference on Computational Intelligence and Machine Learning (CIML) · doi:10.1109/ciml69155.2026.11692762
Enhancing LLM Reasoning via a SLM Supervisor
Fan, Y., Xu, Y., Guo, J., Li, Y., & Zeng, J. (2026) · International Conference on Computational Intelligence and Machine Learning (CIML) · doi:10.1109/ciml69155.2026.11692811
Travasso, D. A., & Taherkhani, A. (2026) · Information · doi:10.3390/info17090920
Qiao, Z., Zhang, P., & Xue, J. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134508
Huang, W., Yang, P., & Yao, G. (2026) · Language Teaching Research · doi:10.1177/13621688261483334
Mining Invariants to Enhance Fuzzing for Detecting Functional Bugs in Smart Contracts
Lin, X., Zhao, B., Xie, Q., Ruan, N., Li, J., & Ji, S. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3849091
Can Silicon Feel? Conditions for Artificial Valence and Their Implications for AI GovernancePreprint
Yauma, L. I. (2026) · Research Square · doi:10.21203/rs.3.rs-10666659/v1
Kabakuş, A. T. (2026) · Gazi University Journal of Science Part A Engineering and Innovation · doi:10.54287/gujsa.1937530
Sun, M., & Zhu, H. (2026) · IEEE Access · doi:10.1109/access.2026.3735019
Li, T. (2026) · International Conference on Electronic Information, Computer and Aerospace Remote Sensing (EICARS) · doi:10.1109/eicars71536.2026.11694433
The Reversed Turing Test: Measuring Superhuman AI Performance Beyond Imitation
León, M. (2026) · WSEAS TRANSACTIONS ON COMPUTER RESEARCH · doi:10.37394/232018.2026.14.53
Shim, J., Kim, E., & Hwang, E. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7511748
Research on Dataset Augmentation Strategies for Metallogenic Model DiagramsPreprint
Xiang, Z., He, Z., Wang, Y., Gu, X., Zhang, Y., Han, J., Yu, Y., Ma, H., & Zhu, B. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7511768
Diya, S., & Edgcomb, J. B. (2026) · JMIR Mental Health · doi:10.2196/97498
Rustamov, Z., Pashayev, M. A., Jafarov, S., Aslanli, U., Mammadov, A., Valizada, A., & Rustamov, S. (2026) · Journal of Advances in Information Technology · doi:10.12720/jait.17.9.1716-1723
Pressure-Tuned Auditor for Sycophancy-Resistant Breast Ultrasound VLM Diagnosis
Zhang, H., Fu, Y., Tan, X., & Qiu, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38098-2_52
Acharya, N., & Kar, P. (2026) · Frontiers in Future Transportation · doi:10.3389/ffutr.2026.1951756
Wendakoon, K., & Tripathi, N. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-39766-9_11
Measuring Reproducibility in LLM Research: A Rubric and Cross-Topic Corpus Study
Chong, C. J., Hou, C., Liu, S., & Yao, Z. (2026) · ACM Conference on Reproducibility and Replicability (ACM REP) · doi:10.1145/3820002.3828584
Adaptive Honey-Memory: A Semantic Deception Framework for Disrupting Agentic Malware
Ahsan, T., Asad, M., Firdous, S., Tahir, Z., Malik, A. H., & Abid, A. (2026) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/2010
Hu, Z., Peng, C., Peng, Z., Cai, Z., Zhang, Z., Sun, Z., Hu, J., & Shouyu, L. (2026) · Mathematics · doi:10.3390/math14193479
Regularizing the Prompt: Stable Model-Agnostic LLM Responses Through Inversion Theory
Silva, S. (2026) · Annals of Computer Science and Information Systems · doi:10.15439/2026f1450
AORS: Atomic Operator Driven Structured Reasoning Framework with Dual-Level Retrieval
Zhang, J., Li, W., Zhu, Z., Xie, L., & Zhang, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5693-8_23
Chen, Z., Chen, W., Zhang, S., Zheng, Z., Jin, D., Zhao, Z., Xu, T., Jing, C., Long, J., & Chen, E. (2026) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3773078.3831772
Small Language Models for Pay Equity Compliance: A Fine-Tuning and Evaluation Study
Kuna, M., & Kowalczyk, M. (2026) · Annals of Computer Science and Information Systems · doi:10.15439/2026f1202
Panel-Aware Best-of-K Selection for Mental-Health Support Dialogue
Yao, K., Cheng, Q., Ren, Z., Fu, W., & Cui, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5699-0_38
Sensitive Data Protection for Text-to-SQL Tasks in Large Language Models
Yang, W., Lu, J., Jin, R., & Paik, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5699-0_44
Zhou, X., Wu, Y., & Wu, P. (2026) · Ain Shams Engineering Journal · doi:10.1016/j.asej.2026.104476
ReasoningUIE: A reasoning paradigm for unified information extraction
Huang, H., Chen, Y., Xu, W., Huang, R., Lin, C., & Qin, Y. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134540
Budget-Constrained Preference-Aligned Prompt Optimization for Controllable Summarization
Li, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5693-8_21
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.