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 1,601–1,700 of 4,340
FINCH: Prompt-guided Key-Value Cache Compression for Large Language Models
Corallo, G., & Papotti, P. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00716 · Cited by 5
Sok: Evaluating Jailbreak Guardrails for Large Language Models
Wang, X., Ji, Z., Wang, W., Li, Z., Wu, D., & Wang, S. (2026) · 2026 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp63933.2026.00076 · Cited by 5
“Let G R denote the guardrail system, and Assess ( G R , X ) be its assessment function, which returns allow if content X (either P , R , or the internal feature F of the LLM) is deemed permissible, and block otherwise.”
Data Augmentation with Large Language Models for Vietnamese Abstractive Text Summarization
Le, H. M., Luong, V. T., & Luong, N. H. (2023) · International Conference on Multimedia Analysis and Pattern Recognition (MAPR) · doi:10.1109/mapr59823.2023.10288906 · Cited by 8
Learning Audio Concepts from Counterfactual Natural Language
Vosoughi, A., Bondi, L., Wu, H.-H., & Xu, C. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446736 · Cited by 6
Learning With an Open Horizon in Ever-Changing Dialogue Circumstances
Geishauser, C., van Niekerk, C., Lubis, N., Lin, H.-C., Heck, M. C., Feng, S., Ruppik, B., Vukovic, R., & Gašić, M. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3385289 · Cited by 10
DANTE: Dialog graph enhanced prompt learning for conversational question answering over KGs
Li, J., Song, S., Yan, S., Hu, G., Lai, C., & Zhou, Y. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112294 · Cited by 5
Interactive Reinforcement Learning from Natural Language Feedback
Tarakli, I., Vinanzi, S., & Nuovo, A. G. D. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10803055 · Cited by 8
RESPECT: A framework for promoting inclusive and respectful conversations in online communications
Raza, S., Muaad, A. Y. M., Hasan, E., Garg, M., Al-Zanbouri, Z., & Bashir, S. R. (2025) · Natural Language Processing Journal · doi:10.1016/j.nlp.2025.100126 · Cited by 5
Description-Based Controllable Text-to-Speech With Cross-Lingual Voice Control
Yamamoto, R., Shirahata, Y., Kawamura, M., & Tachibana, K. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10887783 · Cited by 5
Bao, Z., Ji, Y., Wu, W. R., Chen, X., & He, L. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890479 · Cited by 7
Adopting Whisper for Confidence Estimation
Aggarwal, V., Nair, S. S., Verma, Y., & Jogi, Y. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888254 · Cited by 10
RECoT: Relation-enhanced Chains-of-Thoughts for knowledge-intensive multi-hop questions answering
Li, R., Li, D., Yang, H., Liu, X., Jin, H., Pu, R., & Miao, Q. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129903 · Cited by 7
Dynamic Graph Convolution and Spatiotemporal Self-Attention Network for Traffic Flow Prediction
Liu, Z., Qin, Z., Huang, T., & Ding, G. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3562861 · Cited by 5
Cyberattacks on Large Language Models - Attack Detection and Architecture Adaptability
Alla, S., & Sichani, A. S. (2025) · IEEE SoutheastCon · doi:10.1109/southeastcon56624.2025.10971722 · Cited by 8
Improving LLM-Based Verilog Code Generation with Data Augmentation and RL
Min, K., Park, S., Park, H., Cho, J., & Kang, S. (2025) · Design, Automation, and Test in Europe · doi:10.23919/date64628.2025.10992897 · Cited by 7
Large-model-based smart agent for time series anomaly detection in power systems
Wang, B., Zhou, Y., Ge, L., & Kung, S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128917 · Cited by 6
Act-LLM: A whole-process chain for character-centric role-playing with large language models
Han, X., Zhao, W., Guan, Z., & Peng, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129024 · Cited by 12
SegMIC: A universal model for medical image segmentation through in-context learning
Jianwei, Z., Yang, F., Li, X., Jiao, Z., Zhai, Q., Li, X., Wu, D., Fu, H., & Cheng, H. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112179 · Cited by 17
The deployment of general large language models and corporate value: Evidence from the stock market
Dong, L., Liu, J., Yang, J., & Zhang, X. (2025) · Finance research letters · doi:10.1016/j.frl.2025.108625 · Cited by 7
On the Evaluation of Large Language Models in Multilingual Vulnerability Repair
Wang, D., Yu, J., Shu, H., Fu, M. C., Tantithamthavorn, C. K., Kamei, Y., & Chen, J. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3771930 · Cited by 9
ENCHTABLE: Unified Safety Alignment Transfer in Fine-Tuned Large Language Models
Wu, J., Li, K., Huang, Z., Li, X., Wang, X., & Cheng, H. (2026) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp63933.2026.00072 · Cited by 9
Self-citationLee, K., Yoon, S., & Lim, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130633 · Cited by 6
A Unified Generative-Predictive Framework for Deterministic Inverse Design
Batley, R. T., & Saha, S. K. (2026) · AIAA SciTech Forum · doi:10.2514/6.2026-0365 · Cited by 5
XBreaking: understanding how LLMs security alignment can be broken
Arazzi, M., Kembu, V. K., Nocera, A., & Vinod, P. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12511-3 · Cited by 5
Addressing vulnerability in customer experience with AI-agents
Jha, G., Wright, J., Singhal, A., Zhang, Y., Burton, J., & McColl‐Kennedy, J. R. (2026) · Journal of service management · doi:10.1108/josm-04-2025-0182 · Cited by 6
Jalali, P., Wang, F., Ourang, S. A., Zahedrozegar, S., Mohammad‐Rahimi, H., & Nosrat, A. (2026) · Journal of Endodontics · doi:10.1016/j.joen.2026.02.014 · Cited by 6
Fodeh, S. J., Wang, Y. Y., Ma, L., Talakokkul, S., Alpert, J. M., & Schellhorn, S. E. (2026) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2026.103429 · Cited by 5
Liu, P., Yan, Q., Cui, Z., Liang, D., Wang, X., & Ye, W. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809631 · Cited by 5
Chen, R., Hu, J., Ye, K., & Xu, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39631-0_3 · Cited by 5
Enhancing Web Search Agents With Self-Play Contrastive Fine-Tuning
Rhee, M., Zou, J., Mo, T., Dai, T., & Yang, J.-S. (2026) · IEEE Access · doi:10.1109/access.2026.3717594 · Cited by 16
Open-Ended Multi-Modal Relational Reasoning for Video Question Answering
Luo, H., Qin, R., Xu, C., Ye, G., & Luo, Z. (2023) · IEEE RO-MAN · doi:10.1109/ro-man57019.2023.10309342 · Cited by 8
Learning to Generate Radiology Findings from Impressions Based on Large Language Model
Wu, W., Li, M., Wu, J., Ni, M., & Yuan, H. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386916 · Cited by 6
Self-citationLiu, D., Wang, B., Peng, L., Wang, H., Wang, Y., & Pan, Y. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2080 · Cited by 5
Authorship style transfer with inverse transfer data augmentation
Shao, Z., Zhang, J., Li, H., Huang, X., Zhou, C., Wang, Y., Gong, J., Li, C., & Chen, H. (2024) · AI Open · doi:10.1016/j.aiopen.2024.08.003 · Cited by 8
Shankamarayanan, A., Syed, T., Shapsough, S., & Zualkeman, I. (2024) · IEEE International Conference on Advanced Learning Technologies (ICALT) · doi:10.1109/icalt61570.2024.00063 · Cited by 5
Generating P4 Dataplanes Using LLMs
Dumitru, M.-V., Bădoiu, V.-A., Gherghescu, A. M., & Raiciu, C. (2024) · IEEE International Conference on High Performance Switching and Routing (HPSR) · doi:10.1109/hpsr62440.2024.10635926 · Cited by 7
Log-Based Anomaly Detection with Transformers Pre-Trained on Large-Scale Unlabeled Data
Yan, S., Shi, L., Ren, J., Wang, W., Liu, Y., Sun, L., Wang, X., & Zhang, W. (2024) · International Conference on Communications · doi:10.1109/icc51166.2024.10623067 · Cited by 5
Text-to-text generative approach for enhanced complex word identification
Śliwiak, P., & Shah, S. A. A. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128501 · Cited by 5
CPGA-BOT: A Customized Power Grid Assistant chatBOT Fine-Tuning in Large Language Model
Wang, Q., & Zhou, Z. (2024) · International Conference on Information Science, Parallel and Distributed Systems (ISPDS) · doi:10.1109/ispds62779.2024.10667517 · Cited by 5
Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning
Li, R., Wu, Y., & He, X. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01275 · Cited by 5
Text3DAug - Prompted Instance Augmentation for LiDAR Perception
Reichardt, L., Uhr, L., & Wasenmüller, O. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802726 · Cited by 5
Pan, M., Zhou, S., Chen, J., Huang, E. A., & Huang, J. X. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2024.104058 · Cited by 5
Li, J., Yuan, R., Tian, Y., & Li, J. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822624 · Cited by 6
Graph of Logic: Enhancing LLM Reasoning with Graphs and Symbolic Logic
Alotaibi, F., Kulkarni, A., & Zhou, D. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825450 · Cited by 9
Improving Rare-Word Recognition of Whisper in Zero-Shot Settings
Jogi, Y., Aggarwal, V., Nair, S. S., Verma, Y., & Kubba, A. (2024) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt61566.2024.10832199 · Cited by 5
Sun, Y., Han, Y., & Liu, X. (2025) · Electronics · doi:10.3390/electronics14020379 · Cited by 8
MAST: Multiagent Safe Transformer for Reinforcement Learning
Wei, S., Wang, X., Feng, X., & Yu, H. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3533744 · Cited by 5
Speech Recognition with LLMs Adapted to Disordered Speech Using Reinforcement Learning
Nagpal, C., Venugopalan, S., Tobin, J., Ladewig, M. A., Heller, K., & Tomanek, K. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888006 · Cited by 9
Askar, F., & Baizal, Z. K. A. (2025) · International Conference on Advancement in Data Science, E-learning and Information System (ICADEIS) · doi:10.1109/icadeis65852.2025.10933318 · Cited by 6
Reading Between the Lines: Commonsense Reasoning in Small Language Models
Feroze, W., Qu, H., Shahid, M., & Cheng, S. (2024) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc62609.2024.10941834 · Cited by 5
LLMs for Microservice Generation: Capabilities, Challenges, and Advancements
Spista, R., Crispo, B., Giorgini, P., Marchetto, A., & Riccardi, G. (2025) · IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT) · doi:10.1109/iaict65714.2025.11100313 · Cited by 5
UniRes: Universal Image Restoration for Complex Degradations
Zhou, M., Ye, K., Delbracio, M., Milanfar, P., Patel, V. M., & Talebi, H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01230 · Cited by 8
End-to-end spoken grammatical error correction
Qian, M., Ma, R., Bannò, S., Gales, M., & Knill, K. (2026) · Speech Communication · doi:10.1016/j.specom.2026.103492 · Cited by 7
Wang, M., Li, Q., Gu, Y., & Pan, J. (2023) · Remote Sensing · doi:10.3390/rs15153854 · Cited by 6
Classification of integers based on residue classes via modern deep learning algorithms
Wu, D., Yang, J., Ahsan, M. U., & Wang, K. (2023) · Patterns · doi:10.1016/j.patter.2023.100860 · Cited by 7
Multi-Source Log Parsing With Pre-Trained Domain Classifier
Liu, Y., Tao, S., Meng, W., Wang, J., Yang, H., & Jiang, Y. (2023) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2023.3329144 · Cited by 6
Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks
Sammani, F., & Deligiannis, N. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00498 · Cited by 5
Intelligence artificielle et didactique des mathématiques : état des lieux et questionnements
Emprin, F., & Richard, P. R. (2023) · Annales de didactique et de sciences cognitives · doi:10.4000/adsc.3286 · Cited by 5
Information bottleneck based knowledge selection for commonsense reasoning
Yang, Z., Zhang, Y., Cao, P., Cao, L., Chen, J., Zhao, J., & Liu, K. (2024) · Information Sciences · doi:10.1016/j.ins.2024.120134 · Cited by 7
From Base to Conversational: Japanese Instruction Dataset and Tuning Large Language Models
Suzuki, M., Hirano, M., & Sakaji, H. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386605 · Cited by 8
Improving Braille–Chinese translation with jointly trained and pre-trained language models
Huang, T., Su, W., Liu, L., Cai, C., Yu, H., & Yuan, Y. (2024) · Displays · doi:10.1016/j.displa.2024.102660 · Cited by 5
Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems
Udagawa, T., Suzuki, M., Kurata, G., Muraoka, M., & Saon, G. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448022 · Cited by 5
CompanyKG: A Large-Scale Heterogeneous Graph for Company Similarity Quantification
Cao, L., von Ehrenheim, V., Granroth-Wilding, M., Stahl, R. A., McCornack, A., Catovic, A., & Rocha, D. D. C. (2024) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2024.3407573 · Cited by 5
Privacy Risks in Reinforcement Learning for Household Robots
Li, M., Ding, W., & Zhao, D. X. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610832 · Cited by 9
Cascade & allocate: A cross-structure adversarial attack against models fusing vision and language
Zhang, B., Shi, Y., Han, Y., Hu, Q., & Ding, W. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102179 · Cited by 5
Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training
Wei, Y., Sun, Y., Zheng, R., Vemprala, S. H., Bonatti, R., Chen, S., Madaan, R., Ba, Z., Kapoor, A., & Ma, S. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01486 · Cited by 21
Abdul, A., Chen, B., Phani, S., & Chen, J. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108051 · Cited by 7
Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis
Li, H.-K., Wang, M., Zhang, S., Liu, S., & Chen, P.-Y. (2024) · International Conference on Security and Management · doi:10.1109/sam60225.2024.10636559 · Cited by 12
Precision at hand: Revolutionising surgery with generative AI
Rajaratnam, V., May, S. T. S., & Jerome, J. T. J. (2024) · Journal of Hand and Microsurgery · doi:10.1016/j.jham.2024.100090 · Cited by 5
Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
Gero, Z., Singh, C., Xie, Y., Zhang, S., Subramanian, P., Vozila, P., Naumann, T., Gao, J., & Poon, H. (2024) · arXiv · doi:10.48550/arxiv.2403.01002 · Cited by 5
Yeleussinov, A., Buribayev, Z., Beisov, N., Kalzhanov, N. Y., Satymbekov, M., Akhatov, U. A., & Alimkulov, Y. (2026) · Applied Sciences · doi:10.3390/app16136777 · Cited by 4
Deng, J., Zhang, W., Jiao, Z., & Ren, F. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791186 · Cited by 5
Guiding Reinforcement Learning Using Uncertainty-Aware Large Language Models
Shoaeinaeini, M., & Harrison, B. E. (2025) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa67132.2025.00045 · Cited by 4
ScotRec: Social Chain-of-Thought LLM Reasoning for Recommendation
Li, K., Zou, J., Lin, Q., Guo, W., He, Q., & Yang, Y. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792313 · Cited by 7
Agentic AI system for generating evidence-based second medical opinions
Hawashin, D., Salah, K., Jayaraman, R., & Ellahham, S. H. (2026) · Clinical eHealth · doi:10.1016/j.ceh.2026.04.001 · Cited by 6
Recent Advances on Off-Policy Reinforcement Learning for Optimization Control
Luo, B., Liu, D., Wu, H.-N., Huang, T., Yang, C., & Gui, W. (2026) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2026.3683384 · Cited by 4
PolicyPad: Collaborative Prototyping of LLM Policies
Feng, K. J. K., Kuo, T.-S., Chen, Q. Z., Cheong, I., Holstein, K., & Zhang, A. X. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791689 · Cited by 5
Generative Refinement Networks for Visual Synthesis
Han, J., Liu, J., Wang, J., Peng, B., & Yuan, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37098-3_31 · Cited by 6
The Asymmetric Vulnerability: Bypassing LLM Defenses via Guardrail-Model Mismatch
Wang, J., Zhu, Z., & Liu, C. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792438 · Cited by 6
Plausibility, persuasion, and truth: why language models may appear designed to deceive
Vidotto, G. (2026) · Humanities and Social Sciences Communications · doi:10.1057/s41599-026-07513-4 · Cited by 5
Wang, B., Kabir, D., Clark, C. R., Choi, K. W., & Smoller, J. W. (2026) · JMIR Medical Informatics · doi:10.2196/89534 · Cited by 5
Zhang, H., Yan, X., Yang, Y., Jin, L., Yang, P., & Wang, J. (2026) · Journal of Dentistry · doi:10.1016/j.jdent.2026.106853 · Cited by 4
Unmasking Toxicity and Vulnerabilities in Large Vision-Language Models
Erol, A., Padhi, T., Saha, A., Aktas, M. E., & Kursuncu, U. (2026) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3821418 · Cited by 4
Li, Q., Geng, H., Hu, X., Pan, D., Liu, H., Li, Y., & Guo, J. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1810097 · Cited by 4
Implicit-bias-like patterns in reasoning models
Lee, M. H. J., & Lai, C. K. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01300-1 · Cited by 4
AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation
Yin, X., Xu, C., Zhou, H., Wei, B., & Cai, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37517-9_23 · Cited by 4
Privacy-preserving reinforcement learning from human feedback via decoupled reward modeling
Cho, Y. H., & Sun, W. W. (2026) · Statistical Learning and Data Science · doi:10.1016/j.slads.2026.100021 · Cited by 5
Wan-R1: Verifiable-Reinforcement Learning for Video Reasoning
Liu, M., Zhang, Y., Liu, S., Wang, L., & Zhang, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37461-5_23 · Cited by 4
Baid, A., Xue, Z., & Grauman, K. L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37038-9_4 · Cited by 7
When the market asks no price: AI chatbot interaction as psychic market disruption
NICULESCU, L. (2026) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2026.1812464 · Cited by 4
Toward Measuring Prompt Quality: A Preliminary Investigation on Prompt Smells
Porta, A. D., Voria, G., Abbate, A., Sulipano, R., Lambiase, S., Catolino, G., & Palomba, F. (2026) · IEEE International Conference on Software Analysis, Evolution and Reengineering - Companion (SANER-C) · doi:10.1109/saner-c67878.2026.00046 · Cited by 6
Jailbreaking Embodied LLMs via Action-Level Manipulation
Huang, X., Yang, Q., Shen, L., Ma, Z., & Zheng, Y. (2026) · doi:10.1145/3774906.3802758 · Cited by 9
Hu, Y.-L., Cheng, Z.-X., Liu, W., & Song, L. (2026) · International Conference on Computer Supported Cooperative Work in Design · doi:10.1109/cscwd68734.2026.11581508 · Cited by 3
Towards Trustworthy Multimodal Moderation via Policy-Aligned Reasoning and Hierarchical Labeling
Li, A., Jin, W., Tong, J., Qin, P., Li, J., & Lu, G. S. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3783934 · Cited by 8
Mitigating GenAI-Powered Evidence Pollution for Out-Of-Context Misinformation Detection
Yan, Z., Qi, P., Hsu, W., & Lee, M. L. (2026) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65706.2026.00242 · Cited by 4
Tan, T., Tang, F., Luo, L., Li, Y., Zhao, M., & Kato, N. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3729747 · Cited by 7
A Composite Path and Answer Self-Scoring reward mechanism for test-time reinforcement learning
Xing, J., Tang, C., Liu, X., Xiong, D., Huang, S., Ju, W., Lv, J., & Qiao, Z. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114900 · Cited by 4
LP-MusicCaps: LLM-Based Pseudo Music Captioning
Doh, S., Choi, K., Lee, J., & Nam, J. (2023) · arXiv · doi:10.48550/arxiv.2307.16372 · Cited by 16
“5 Turbo [23] for its strong performance in various tasks.”
BackgroundCAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments
Liu, X., Paul, S., Chatterjee, M., & Cherian, A. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i4.28167 · Cited by 6
“In NavGPT, (Zhou et al. 2023) the possibility of integrating ChatGPT (Ouyang et al. 2022) with a vision foundation model: BLIP-2 (Li et al. 2023) into its prompting setup to perform multi-modal reasoning to navigate in a zero-shot manner was explored.”
MethodExplaining Length Bias in LLM-Based Preference Evaluations
Hu, Z., Song, L., Zhang, J., Xiao, Z., Wang, T., Chen, Z., Yuan, N. J., Lian, J., Ding, K., & Xiong, H. (2025) · Findings of the Association for Computational Linguistics: EMNLP 2025 · doi:10.18653/v1/2025.findings-emnlp.358 · Cited by 4
“This state-of-the-art reward model is licensed under PKU-Alignment/PKU-SafeRLHF-30K, demonstrating high performance across diverse metrics like chat, safety, and reasoning in Reward-Bench.”
Influential
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.