Copertina

Estimating the Probabilities of Rare Outputs in Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Gabriel, Hilton, Jacob
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Estimating Tail Risks in Language Model Output Distributions
di: Angell, Rico, et al.
Pubblicazione: (2026)

Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference
di: Zhao, Stephen, et al.
Pubblicazione: (2025)

Towards a Law of Iterated Expectations for Heuristic Estimators
di: Christiano, Paul, et al.
Pubblicazione: (2024)

Understanding Token Probability Encoding in Output Embeddings
di: Cho, Hakaze, et al.
Pubblicazione: (2024)

Accurately Predicting Probabilities of Safety-Critical Rare Events for Intelligent Systems
di: Bai, Ruoxuan, et al.
Pubblicazione: (2024)

GPT, But Backwards: Exactly Inverting Language Model Outputs
di: Skapars, Adrians, et al.
Pubblicazione: (2025)

Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
di: Cloud, Alex, et al.
Pubblicazione: (2025)

SLOT: Structuring the Output of Large Language Models
di: Wang, Darren Yow-Bang, et al.
Pubblicazione: (2025)

PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation
di: Lemos, Pablo, et al.
Pubblicazione: (2024)

Backdoor defense, learnability and obfuscation
di: Christiano, Paul, et al.
Pubblicazione: (2024)

Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networks
di: Bramlage, Lennart, et al.
Pubblicazione: (2025)

An Evaluation on Large Language Model Outputs: Discourse and Memorization
di: de Wynter, Adrian, et al.
Pubblicazione: (2023)

Leviathan: Decoupling Input and Output Representations in Language Models
di: Batley, Reza T., et al.
Pubblicazione: (2026)

E-Scores for (In)Correctness Assessment of Generative Model Outputs
di: Dhillon, Guneet S., et al.
Pubblicazione: (2025)

Output Supervision Can Obfuscate the Chain of Thought
di: Drori, Jacob, et al.
Pubblicazione: (2025)

Estimating the Empowerment of Language Model Agents
di: Song, Jinyeop, et al.
Pubblicazione: (2025)

Graph-based Uncertainty Metrics for Long-form Language Model Outputs
di: Jiang, Mingjian, et al.
Pubblicazione: (2024)

Group-Aware Reinforcement Learning for Output Diversity in Large Language Models
di: Anschel, Oron, et al.
Pubblicazione: (2025)

Enhancing Rare Codes via Probability-Biased Directed Graph Attention for Long-Tail ICD Coding
di: Chen, Tianlei, et al.
Pubblicazione: (2025)

RL-Struct: A Lightweight Reinforcement Learning Framework for Reliable Structured Output in LLMs
di: Hu, Ruike, et al.
Pubblicazione: (2025)

Derivation of Output Correlation Inferences for Multi-Output (aka Multi-Task) Gaussian Process
di: Watanabe, Shuhei
Pubblicazione: (2025)

Confidence Calibration in Large Language Models
di: Michael, Noam, et al.
Pubblicazione: (2026)

Generative Modeling of Class Probability for Multi-Modal Representation Learning
di: Shin, Jungkyoo, et al.
Pubblicazione: (2025)

On the Generalization Properties of Deep Learning for Aircraft Fuel Flow Estimation Models
di: Jarry, Gabriel, et al.
Pubblicazione: (2024)

Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
di: Kumar, Abhishek, et al.
Pubblicazione: (2024)

Fourier Head: Helping Large Language Models Learn Complex Probability Distributions
di: Gillman, Nate, et al.
Pubblicazione: (2024)

LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences
di: Wu, Wenbo, et al.
Pubblicazione: (2025)

Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
di: Jeon, Dongjae, et al.
Pubblicazione: (2024)

Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification
di: Fadeeva, Ekaterina, et al.
Pubblicazione: (2024)

When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models
di: Galeone, Cosimo, et al.
Pubblicazione: (2026)

Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks
di: Li, Yuangang, et al.
Pubblicazione: (2026)

Phase Transitions in the Output Distribution of Large Language Models
di: Arnold, Julian, et al.
Pubblicazione: (2024)

Always Tell Me The Odds: Fine-grained Conditional Probability Estimation
di: Wang, Liaoyaqi, et al.
Pubblicazione: (2025)

Data Descriptions from Large Language Models with Influence Estimation
di: Kim, Chaeri, et al.
Pubblicazione: (2025)

Learning to Solve the Constrained Most Probable Explanation Task in Probabilistic Graphical Models
di: Arya, Shivvrat, et al.
Pubblicazione: (2024)

Time Series Forecasting via Direct Per-Step Probability Distribution Modeling
di: Kong, Linghao, et al.
Pubblicazione: (2025)

Rare Class Prediction Model for Smart Industry in Semiconductor Manufacturing
di: Farrag, Abdelrahman, et al.
Pubblicazione: (2024)

Can Machines Learn the True Probabilities?
di: Kim, Jinsook
Pubblicazione: (2024)

A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs
di: Watts, Jake R., et al.
Pubblicazione: (2024)

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study
di: Bouchard, Dylan, et al.
Pubblicazione: (2026)