Image de couverture de livre

Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's Characteristics

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Flores, Lorenzo Jaime Yu, Ernst, Ori, Cheung, Jackie Chi Kit
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PreSumm: Predicting Summarization Performance Without Summarizing
par: Koniaev, Steven, et autres
Publié: (2025)

Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
par: Flores, Lorenzo Jaime Yu, et autres
Publié: (2026)

Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
par: Yu, Lei, et autres
Publié: (2024)

$\texttt{COSMIC}$: Mutual Information for Task-Agnostic Summarization Evaluation
par: Darrin, Maxime, et autres
Publié: (2024)

Testing the Assumptions of Active Learning for Translation Tasks with Few Samples
par: Flores, Lorenzo Jaime Yu, et autres
Publié: (2026)

$(RSA)^2$: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative Language Understanding
par: Piano, Cesare Spinoso-Di, et autres
Publié: (2025)

Can Vision Language Models Be Adaptive in Mathematics Education? A Learner Model-based Rubric Study
par: Gao, Jie, et autres
Publié: (2026)

Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing
par: Shayegh, Behzad, et autres
Publié: (2024)

Calibrating Verbalized Confidence with Self-Generated Distractors
par: Wang, Victor, et autres
Publié: (2025)

Agentic Confidence Calibration
par: Zhang, Jiaxin, et autres
Publié: (2026)

Unsupervised Layer-wise Score Aggregation for Textual OOD Detection
par: Darrin, Maxime, et autres
Publié: (2023)

From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models
par: Liu, Junhao, et autres
Publié: (2025)

Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation
par: Lin, Zhen, et autres
Publié: (2024)

On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization
par: Flores, Lorenzo Jaime Yu, et autres
Publié: (2024)

Fact-Level Confidence Calibration and Self-Correction
par: Yuan, Yige, et autres
Publié: (2024)

Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
par: Lu, Yuyin, et autres
Publié: (2026)

Solving the Challenge Set without Solving the Task: On Winograd Schemas as a Test of Pronominal Coreference Resolution
par: Porada, Ian, et autres
Publié: (2024)

Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration
par: Yuan, Yi, et autres
Publié: (2026)

STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability
par: Wang, Guanghui, et autres
Publié: (2025)

Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoring
par: Chen, Shiting, et autres
Publié: (2025)

Don't Think Twice! Over-Reasoning Impairs Confidence Calibration
par: Lacombe, Romain, et autres
Publié: (2025)

A Survey of Confidence Estimation and Calibration in Large Language Models
par: Geng, Jiahui, et autres
Publié: (2023)

How Teachers Can Use Large Language Models and Bloom's Taxonomy to Create Educational Quizzes
par: Elkins, Sabina, et autres
Publié: (2024)

LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
par: Stengel-Eskin, Elias, et autres
Publié: (2024)

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
par: Torrielli, Federico, et autres
Publié: (2026)

Confidence Improves Self-Consistency in LLMs
par: Taubenfeld, Amir, et autres
Publié: (2025)

Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores
par: Balkır, Esma, et autres
Publié: (2026)

Linguistic Characteristics of AI-Generated Text: A Survey
par: Terčon, Luka, et autres
Publié: (2025)

Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models
par: Chhikara, Prateek
Publié: (2025)

The Dunning-Kruger Effect in Large Language Models: An Empirical Study of Confidence Calibration
par: Ghosh, Sudipta, et autres
Publié: (2026)

Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning
par: Zhang, Chuang, et autres
Publié: (2026)

Making Retrieval-Augmented Language Models Robust to Irrelevant Context
par: Yoran, Ori, et autres
Publié: (2023)

DecMetrics: Structured Claim Decomposition Scoring for Factually Consistent LLM Outputs
par: Huang, Minghui
Publié: (2025)

Calibrating Verbalized Probabilities for Large Language Models
par: Wang, Cheng, et autres
Publié: (2024)

MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools
par: Subramani, Nishant, et autres
Publié: (2025)

Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model
par: Tian, Yuanhe, et autres
Publié: (2025)

Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces
par: Pathak, Manas, et autres
Publié: (2026)

DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains
par: Chen, Zhihui, et autres
Publié: (2025)

OpenFActScore: Open-Source Atomic Evaluation of Factuality in Text Generation
par: Lage, Lucas Fonseca, et autres
Publié: (2025)

Generative Ontology: When Structured Knowledge Learns to Create
par: Cheung, Benny
Publié: (2026)