Exploring the Impact of Temperature on Large Language Models: Hot or Cold?
Open accessAbstract
The sampling temperature, a critical hyperparameter in large language models (LLMs), modifies the logits before the softmax layer, thereby reshaping the distribution of output tokens. Recent studies have challenged the “Stochastic Parrots” analogy by demonstrating that LLMs are capable of understanding semantics rather than merely memorizing data and that randomness, modulated by sampling temperature, plays a crucial role in model inference. In this study, we systematically evaluated the impact of temperature in the range of 0 to 2 on data sets designed to assess six different capabilities, conducting statistical analyses on open source models of three different sizes: small (1B–4B), medium (6B–13B), and large (40B–80B). Our findings reveal distinct skill-specific effects of temperature on model performance, highlighting the complexity of optimal temperature selection in practical applications. To address this challenge, we propose a BERT-based temperature selector that takes advantage of these observed effects to identify the optimal temperature for a given prompt. We demonstrate that this approach can significantly improve the performance of small and medium models in the SuperGLUE datasets. Furthermore, our study extends to FP16 precision inference, revealing that temperature effects are consistent with those observed in 4-bit quantized models. By evaluating temperature effects up to 4.0 in three quantized models, we find that the “Mutation Temperature”—the point at which significant performance changes occur—increases with model size 1 .
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
A learning algorithm for Boltzmann machines
Ackley, D. H., Hinton, G. E., & Sejnowski, T. J. (1985) · Cognitive Science · doi:10.1207/s15516709cog0901_7 · Cited by 3,402 · see citing works
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604 · see citing works
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093 · see citing works
Efficient Memory Management for Large Language Model Serving with PagedAttention
Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J., Zhang, H., & Stoica, I. (2023) · Proceedings of the 29th Symposium on Operating Systems Principles · doi:10.1145/3600006.3613165 · Cited by 1,817 · see citing works
Efficient Memory Management for Large Language Model Serving with PagedAttention
Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J. E., Zhang, H., & Stoica, I. (2023) · arXiv · doi:10.48550/arxiv.2309.06180 · Cited by 1,802 · see citing works
Hierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1082 · Cited by 1,266 · see citing works
Hierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.04833 · Cited by 1,242 · see citing works
G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
Liu, Y., Iter, D., Xu, Y., Wang, S., Xu, R., & Zhu, C. (2023) · arXiv · doi:10.48550/arxiv.2303.16634 · Cited by 948 · see citing works
G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment
Liu, Y., Iter, D., Xu, Y., Wang, S., Xu, R., & Zhu, C. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.153 · Cited by 948 · see citing works
Lin, C.-Y., & Och, F. J. (2004) · Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04 · doi:10.3115/1218955.1219032 · Cited by 737 · see citing works
Benchmarking Large Language Models for News Summarization
Zhang, T., Ladhak, F., Durmus, E., Liang, P., McKeown, K., & Hashimoto, T. B. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00632 · Cited by 415 · see citing works
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
Bai, Y., Lv, X., Zhang, J., Lyu, H., Tang, J., Huang, Z., Du, Z., Liu, X., Zeng, A., Hou, L., et al. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.172 · Cited by 400 · see citing works
AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration
Lin, J., Tang, J., Tang, H., Yang, S., Xiao, G., & Han, S. (2025) · GetMobile: Mobile Computing and Communications · doi:10.1145/3714983.3714987 · Cited by 274 · see citing works
The effect of sampling temperature on problem solving in large language models
Renze, M. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.432 · Cited by 212 · see citing works
AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
Zhong, W., Cui, R., Guo, Y., Liang, Y., Lu, S., Wang, Y., Saied, A., Chen, W., & Duan, N. (2024) · Findings of the Association for Computational Linguistics: NAACL 2024 · doi:10.18653/v1/2024.findings-naacl.149 · Cited by 211 · see citing works
Causal Reasoning and Large Language Models: Opening a New Frontier for Causality
Kıcıman, E., Ness, R., Sharma, A., & Tan, C. (2023) · arXiv · doi:10.48550/arxiv.2305.00050 · Cited by 210 · see citing works
The Flores-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation
Goyal, N., Gao, C., Chaudhary, V., Chen, P., Wenzek, G., Ju, D., Krishnan, S., Ranzato, M., Guzmán, F., & Fan, A. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00474 · Cited by 209 · see citing works
The originality of machines: AI takes the Torrance test
Guzik, E. E., Byrge, C., & Gilde, C. (2023) · Journal of Creativity · doi:10.1016/j.yjoc.2023.100065 · Cited by 165 · see citing works
Art or Artifice? Large Language Models and the False Promise of Creativity
Chakrabarty, T., Laban, P., Agarwal, D., Muresan, S., & Wu, C.-S. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642731 · Cited by 135 · see citing works
Caccia, M., Caccia, L., Fedus, W., Larochelle, H., Pineau, J., & Charlin, L. (2020) · International Conference on Learning Representations · Cited by 103 · see citing works
Creativity research: Originality, utility, and integration
Runco, M. (1988) · Creativity Research Journal · doi:10.1080/10400418809534283 · Cited by 97 · see citing works
InFoBench: Evaluating Instruction Following Ability in Large Language Models
Qin, Y., Song, K., Hu, Y., Yao, W., Cho, S., Wang, X., Wu, X., Liu, F., Liu, P., & Yu, D. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.772 · Cited by 77 · see citing works
Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models
Zhu, Y., Li, J., Li, G., Zhao, Y., Li, J., Jin, Z. G., & Mei, H. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i1.27798 · Cited by 48 · see citing works
KL-Divergence Guided Temperature SamplingPreprint
Chang, C.-C., Reitter, D., Aksitov, R., & Sung, Y.-H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.01286 · Cited by 25 · see citing works
This is not correct! Negation-aware Evaluation of Language Generation Systems
Anschütz, M., Lozano, D. M., & Groh, G. (2023) · International Conference on Natural Language Generation · doi:10.18653/v1/2023.inlg-main.12 · Cited by 16 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Ning, W., Li, M., Reimers, J. R., & Kobayashi, R. (2026) · Digital Discovery · doi:10.1039/d5dd00482a · Cited by 8 · see citing works
Delre, P., Bellofatto, G., & Lavecchia, A. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c00535 · Cited by 6 · see citing works
Han, C., & Lu, X. (2025) · Language Testing · doi:10.1177/02655322251406297 · Cited by 5 · see citing works
Multi-agent artificial intelligence designs novel catalysts for ultrafast water purification
Pan, Y., Guo, J., Huang, Y., Zhou, J., Niu, S., Yin, R., Ding, L., Xu, N., Fan, Y., Ren, X., et al. (2026) · Nature Water · doi:10.1038/s44221-026-00634-9 · Cited by 5 · see citing works
May, M., Jacobs, G., Dehn, S., Höpfner, G., Zerwas, T., Boelsen, K., & Hacker, S. (2026) · Systems · doi:10.3390/systems14030302 · Cited by 4 · see citing works
Ronan, I., Crowley, P., Rombouts, E., Cornally, N., Saab, M. M., Murphy, D., & Tabirca, S. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2025.104936 · Cited by 3 · see citing works
Evaluating Large Language Models as Judicial Decision-Makers
Gazal‐Ayal, O., Elyoseph, Z., & Solomon, A. (2026) · Justice Quarterly · doi:10.1080/07418825.2026.2618254 · Cited by 3 · see citing works
LLM-assisted genre analysis: The effect of sampling temperature on reliability
Grullon-Polanco, L. (2026) · Research Methods in Applied Linguistics · doi:10.1016/j.rmal.2026.100314 · Cited by 3 · see citing works
Identifying performance-sensitive configurations in software systems with LLM-based agents
Wang, Z., Kim, D. J., & Chen, T.-H. P. (2026) · Empirical Software Engineering · doi:10.1007/s10664-026-10883-7 · Cited by 3 · see citing works
Large Language Models Acing Chartered Accountancy
Gupta, J., Sharma, A. K., Singhania, S., Adnan, M., Deo, S., Abidi, A. I., & Gupta, K. (2025) · SN Computer Science · doi:10.1007/s42979-025-04497-x · Cited by 1 · see citing works
Exploring Spontaneous Social Interaction Swarm Robotics Powered by Large Language Models
Jiang, Y., Zhao, L., Li, A. Q., Chen, M., & Balkcom, D. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246362 · Cited by 1 · see citing works
Lee, D. Y. H., Parker, A. J., Norbury, C., & Shanks, D. R. (2026) · Royal Society Open Science · doi:10.1098/rsos.250381 · Cited by 1 · see citing works
Sumanathilaka, D. K., Micallef, N., & Hough, J. (2026) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/3oun2fvikwt5 · Cited by 1 · see citing works
Nwokeji, J. C., Nkwo, M. S., Ikwunne, T. A., & Yeerbo, M. (2026) · AI and Ethics · doi:10.1007/s43681-026-01151-x · Cited by 1 · see citing works
Sampaio, A., & Stoelinga, M. I. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-26220-2 · Cited by 1 · see citing works
Freeman, B., Kicklighter, A., Erdman, M., & Gordon, Z. (2026) · Computer and Information Science · doi:10.5539/cis.v19n2p1 · Cited by 1 · see citing works
Pan, Y.-L., Yu, P.-F., Yin, X.-L., Hong-sheng, Y., Long, X., & Tong, Q. (2026) · Educational Technology Research and Development · doi:10.1007/s11423-026-10659-2 · Cited by 1 · see citing works
Pavilion, G. L., Mbigidde, C., Tubelleza, R., Ramarao-Milne, P., & Kulasinghe, A. (2026) · Immunology and Cell Biology · doi:10.1111/imcb.70146 · Cited by 1 · see citing works
Martinez-Sanchez, A., Roy, P., & Greer, R. (2026) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv66570.2026.11624036 · Cited by 1 · see citing works
Generative AI Technologies, Techniques and Tensions: A Primer
Behrens, J. T. (2026) · Springer eBooks · doi:10.1007/978-3-032-24819-0_2 · Cited by 1 · see citing works
Temperature in SLMs: Impact on Incident Categorization in On-Premises Environments
Pohlmann, M., Severo, A. S. P., de Almeida, G. A., Kreutz, D., Heinrich, T., & Pereira, L. (2025) · Escola Regional de Redes de Computadores (ERRC) · doi:10.5753/errc.2025.17813 · Cited by 1 · see citing works
Impact of Large-Model Temperature on Generative Relation Extraction Results
Sun, X., Zhang, P., Zhao, M., & He, S. (2025) · IEEE International Conference on Pattern Recognition, Machine Vision and Artificial Intelligence (PRMVAI) · doi:10.1109/prmvai65741.2025.11108614
Beyond Accuracy in Small Open-Source Medical Large Language Models for Pediatric EndocrinologyPreprint
D’Amario, V., Daniel, R., Edamadaka, D., Alaparthy, N., & Tarkoff, J. (2025) · medRxiv · doi:10.1101/2025.08.26.25334485
Vitale, F., Flammini, F., Caporuscio, M., & Mazzocca, N. (2026) · Information and Software Technology · doi:10.1016/j.infsof.2026.108133
Generative AI as chemist’s virtual assistant: a case study with the chemistry of SmI2
Das, A., Behera, S., Haldar, R., Dawar, P., Maity, S., & De, S. (2025) · Discover Applied Sciences · doi:10.1007/s42452-025-07913-2
Using GPT-4 to Automate the Generation of Lay Summaries for Cancer PublicationsPreprint
Purdie, E., Yu, T., Weile, J., Lemaire, D., & Courtot, M. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2025.12.11.693290
Lv, X., Cheng, L., Qi, L., Li, Q., Liu, Y., & Tang, L. (2025) · International Journal of Reliability Quality and Safety Engineering · doi:10.1142/s0218539325500639
Toward Automated Interdisciplinary Checks in EPC Projects: A Human-AI Collaborative Approach
Banotra, R., Diaz, D. A. Y., Balamurugan, N., Dzsuhupova, R., Bosch, J., & Olsson, H. H. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343056
Yelmo, J. C., Martín, Y.-S., & Perez-Acuna, S. (2026) · IEEE Access · doi:10.1109/access.2026.3658339
de Souza, D. A. R. L., Ramos, F. C., Veras, E. L., Lopes, P. F. D. F., Santos, B. L. D., Oliveira, C. S. D., Souza, J. D. B. D., & Oliveira, A. D. O. (2025) · International Conference on Soft Computing & Machine Intelligence (ISCMI) · doi:10.1109/iscmi67495.2025.11358591
Automating Threat-Aligned Testflows Generation Using Ontology-Grounded RAG From CTI Reports
Ahmadou, F., Nour, B., Pourzandi, M., Debbabi, M., & Assi, C. M. (2026) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2026.3684808
Xiao, Y., Zhao, S., Zhou, Q., Zhang, Y., Han, J., Ji, F., & He, J. (2026) · Body Image · doi:10.1016/j.bodyim.2026.102097
Tasting Emotions with GPT-4o: Comparing AI and Human Norms in Metaphoric Associations
Zhou, Y., Li, W., Tse, C., Xie, J., & HUANG, Y. (2026) · Cognitive Computation · doi:10.1007/s12559-026-10594-7
Can LLM Aid in Solving Constraints with Inductive Definitions?
Feng, W., Shen, S., Liu, J. J., Chen, T., Song, F., & Wu, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-26220-2_6
Dual-Mode Explanations for Suicide Risk Detection in Online Mental Health Support
Munz, N., Segal, A., Grimland, M., Yeshayahu, H., Benatov, J., Shenfeld, I., Dayan, L. B., Levi‐Belz, Y., & Gal, K. (2026) · Information Systems Frontiers · doi:10.1007/s10796-026-10740-4
Agentic Runtime Reconfiguration of Architectural Patterns in Federated Learning
Compagnucci, I., Lu, Q., & Trubiani, C. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.112966
FashionAtlas: Enhancing Semantics and Control in Multimodal Fashion Image Editing
Gu, E., Wang, J., & Shi, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-9694-2_7
Testing Framework Migration with Large Language Models
Alves, A., Montandon, J. E., & Hora, A. (2026) · doi:10.1145/3793654.3793749
Berardelli, S., Brière, G., Loire, B., Paoli, F. D., Gazzo, A. M., Limongelli, I., Magni, P., Zucca, S., & Baudot, A. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.22.733382
Wang, L., Zhang, H., Macken, L., & Liu, K. (2026) · International Conference on New Trends in Translation and Technology (NeTTT) · doi:10.26615/issn.2815-4711.2026_014
A GRPO-Enhanced Agentic RAG Framework for English-to-Indic Machine Translation
Sree, K. D., Nair, A. R., & Gupta, D. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.065
Rafiei, A., Seo, J., Yürdem, B., & Çatak, F. Ö. (2026) · International Conference on Human Centric Artificial Intelligence (ICHCAI) · doi:10.1109/ichcai70183.2026.11607654
Automated Generation of Interconnected Learning Objects Using a Large Language Model
Demčák, M., & Lang, J. (2026) · Information Technology Scientific Research Conference (IIT.SRC) · doi:10.1109/iit.src67760.2026.11628843
Self-referential consistency in stateless language models: a behavioral perspective
Prestes, J. A. D. L. (2026) · AI & Society · doi:10.1007/s00146-026-03292-3
CMA-ES Decoding Optimization for MedGemma: A Flat Landscape on Chest X-Ray Reports
Chen-Wang, M., Abreu-Cardenas, M., & Ramírez, S. C. (2026) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3795101.3814726
Rojas, N. P., Xie-Li, D., Solís, M., Ramírez, S. C., Gonzalez, S. R., & Ruíz, V. O. (2026) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3795101.3814720
Neece, T., & Fascetti, A. (2026) · Journal of Computing in Civil Engineering · doi:10.1061/jccee5.cpeng-7383
LLMs to Augment Evaluators in Scripting Usability Tasks: An Exploratory Study
Calvano, M., Caporusso, C. B., Curci, A., Lanzilotti, R., Massaro, D., Piccinno, A., & Ragone, A. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2714305
Sauka, K., Situmeang, F., & Kackovic, M. (2026) · International Conference on Computer Communication and the Internet (ICCCI) · doi:10.1109/iccci70321.2026.11666502
Sturm, A., Unger, V., & Grünig, F. (2026) · Didaktik Deutsch · doi:10.21248/dideu.963
An AI ‐assisted workflow for generating historical species distributions from avian museum specimens
Learned, P., Adams, M., Salili‐James, A., Penn, M. G., Sweet, P., Trombone, T., & Norris, K. J. (2026) · Ibis · doi:10.1111/ibi.70116
Connection between Temperature and Emergent Behavior in Large Language Models
Balage, N. D., Mohottalage, L. D., Wickramasinghe, A. S., Liyanage, M., & Heenkenda, H. M. S. C. R. (2026) · Advances in Technology · doi:10.31357/ait.v6i01.9321
Sblendorio, E., Dentamaro, V., Maria, M. D., Tempesta, S., Barile, E., Napolitano, D., Tallini, M., Nigrelli, D., Cicolini, G., & Piredda, M. (2026) · JMIR Medical Informatics · doi:10.2196/90854
Do AI stories align with the laws of the story economy?
Raipola, J., Mäkelä, M., Björninen, S., & Piippo, L. H. (2026) · Narrative Inquiry · doi:10.1075/ni.25163.rai
Rafieyan, S., Nasr, M. P., Ansari, E., Kolour, A. K., Banimohamad‐Shotorbani, B., & Vasheghani‐Farahani, E. (2026) · Biofabrication · doi:10.1088/1758-5090/aeb162
Bertgren, A., Öhberg, F., Soda, P., Näslund, U., Wennberg, P., & Grönlund, C. (2026) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms69103.2026.00036
ОЦЕНКА ЭФФЕКТИВНОСТИ СИНТЕЗА СТОХАСТИЧЕСКИХ МОДЕЛЕЙ С УПРАВЛЯЕМЫМИ СВОЙСТВАМИ
Пустовой, Е. А., Пустовая, О. А., Раушанова, А. Н., & Заурбеков, И. С. (2026) · INTERNATIONAL JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGIES · doi:10.54309/ijict.2026.26.2.029
Pietrancosta, M., Wang, S., Wu, Y., Brulotte, V., Harutyunyan, R., Hemmerling, T. M., Morisson, L., & Laferrière-Langlois, P. (2026) · Research Square · doi:10.21203/rs.3.rs-10879359/v1
Constraint-Driven Intent-Based Networking for Interdomain Decision Support
Camargo, A. V. C., Granville, L. Z., Bertholdo, L. M., & Barreto, R. P. (2026) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc70364.2026.11740008
Trustworthy AI for Traceable High-Risk Decisions via the Deterministic Reasoning Framework
Neto, A. J. H., Salles, R. M., Goldschmidt, R. R., & dos Santos, A. F. P. (2026) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc70364.2026.11740066
Neutralizing Implicit Biases in LLM-Assisted Hiring via a Deterministic Reasoning Framework
Neto, A. J. H., Salles, R. M., Goldschmidt, R. R., & dos Santos, A. F. P. (2026) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc70364.2026.11740012
- Authors
- Li, L., Sleem, L., Gentile, N., Nichil, G., & State, R.
- Affiliations
- University of Luxembourg (LU)
- Corresponding author
- Li, Lujun
- Venue
- Procedia Computer Science
- Publisher
- Elsevier BV
- Published
- 2025
- Volume
- 264
- Pages
- 242-251
- ISSN
- 1877-0509 (ISSN-L)
- OpenAlex
- W4413167964
- Cited by
- 62
- References
- 23
- Citations by year
- 2026: 49 · 2025: 13
- FWCI
- 43.27
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Procedia Computer Science (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Open Repository and Bibliography (University of Luxembourg) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Nvidia
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- sampling temperature, large language models, temperature selection, SuperGLUE, model size effects, quantized models, 4-bit quantization, token distribution
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
