Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
token probabilities
Description:
Probabilities assigned to possible next tokens by a language model, used in natural language processing and generative text systems.
Primary topic:
Topic Modeling (39%)
Related topics:
Topic Modeling (39%),
Adversarial Robustness in Machine Learning (11%),
Natural Language Processing Techniques (8%)
OpenAlex ID:
keywords/token-probabilities
ClashEval: Quantifying the tug-of-war between an LLM’s internal prior and external evidence
2024
·
Kevin Wu
, Eric Wu
, et al.
·
neural information processing systems
·
235
PDF
A multimodal grammar of artificial intelligence: Measuring the gains and losses in generative AI
2023
·
Bill Cope
, Mary Kalantzis
·
Multimodality & Society
·
85
Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
2024
·
Abhishek Kumar
, Robert Morabito
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
·
62
PDF
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
2026
·
Chen, Shirui
, Harrison, Cole
, et al.
·
arXiv (Cornell University)
·
48
PDF
Rethinking the Trust Region in LLM Reinforcement Learning
2026
·
Qi, Penghui
, Zhou, Xiangxin
, et al.
·
arXiv (Cornell University)
·
47
PDF
Lightweight global and local contexts guided method name recommendation with prior knowledge
2021
·
Shangwen Wang
, Ming Wen
, et al.
·
ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)
·
43
Closing the Curious Case of Neural Text Degeneration
2023
·
Finlayson, Matthew
, Hewitt, John
, et al.
·
International Conference on Learning Representations
·
41
Token Probabilities to Mitigate Large Language Models Overconfidence in Answering Medical Questions: Quantitative Study
2025
·
Raphaël Bentegeac
, Bastien Le Guellec
, et al.
·
Journal of Medical Internet Research
·
40
PDF
Selective-LAMA: Selective Prediction for Confidence-Aware Evaluation of Language Models
2023
·
Hiyori Yoshikawa
, Naoaki Okazaki
·
Findings of the Association for Computational Linguistics: EACL
·
38
PDF
Lightweight reranking for language model generations
2024
·
Siddhartha Jain
, Xiaofei Ma
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
·
28
PDF
Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners
2024
·
Zheng, Zhi
, Feng, Qian
, et al.
·
arXiv (Cornell University)
·
27
PDF
Multiple Choice Questions: Reasoning Makes Large Language Models More Self-Confident, Especially When They Are Wrong
2026
·
Tairan Fu
, Javier Conde
, et al.
·
IEEE Intelligent Systems
·
26
Decoding Secret Memorization in Code LLMs Through Token-Level Characterization
2025
·
Yuqing Nie
, Chong Wang
, et al.
·
ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)
·
26
PDF
Understanding Knowledge Drift in LLMs Through Misinformation
2025
·
Alina Fastowski
, Gjergji Kasneci
·
Lecture notes in computer science
·
26
PDF
ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection
2026
·
Liu, Tao
, Wu, Taiqiang
, et al.
·
arXiv (Cornell University)
·
21
PDF
Black-box Uncertainty Quantification Method for LLM-as-a-Judge
2024
·
Wagner, Nico
, Desmond, Michael
, et al.
·
arXiv (Cornell University)
·
20
PDF
HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs
2025
·
Sharanya Dasgupta
, Sujoy Nath
, et al.
·
International Joint Conference on Neural Networks (IJCNN)
·
18
PDF
Beyond Reproducibility: Token Probabilities Expose Large Language Model Nondeterminism
2026
·
Tairan Fu
, Gonzalo Martínez
, et al.
·
IEEE Transactions on Computers
·
13
PDF
Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration
2026
·
Kim, Hankyeol
, Kang, Pilsung
·
arXiv (Cornell University)
·
13
PDF
How new data permeates LLM knowledge and how to dilute it
2025
·
Sun, Chen
, Aksitov, Renat
, et al.
·
International Conference on Learning Representations
·
13
Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks
2023
·
Piotr Gaiński
, Klaudia Bałazy
·
Conference of the European Chapter of the Association for Computational Linguistics
·
12
PDF
Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs
2024
·
Yaldiz, Duygu Nur
, Bakman, Yavuz Faruk
, et al.
·
arXiv (Cornell University)
·
10
PDF
Detecting LLM Hallucinations Using Monte Carlo Simulations on Token Probabilities
2024
·
Grant Ledger
, Rafael Mancinni
·
10
PDF
Large Language Model Recall Uncertainty is Modulated by the Fan Effect
2024
·
Jesse Roberts
, Kyle Moore
, et al.
·
Conference on Computational Natural Language Learning
·
9
PDF
UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models
2025
·
Roman Vashurin
, Maiya Goloburda
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
8
PDF
Show more works
View as search
Works count:
98
Citation count:
1,021
Year
Topic
Type