Copertina

Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xia, Yuxi, Schoenegger, Loris, Roth, Benjamin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

An Evaluation of Explanation Methods for Black-Box Detectors of Machine-Generated Text
di: Schoenegger, Loris, et al.
Pubblicazione: (2024)

Select or Project? Evaluating Lower-dimensional Vectors for LLM Training Data Explanations
di: Hinterleitner, Lukas, et al.
Pubblicazione: (2026)

Compact Example-Based Explanations for Language Models
di: Schoenegger, Loris, et al.
Pubblicazione: (2026)

Influence-driven Curriculum Learning for Pre-training on Limited Data
di: Schoenegger, Loris, et al.
Pubblicazione: (2025)

Explaining Generalization of AI-Generated Text Detectors Through Linguistic Analysis
di: Xia, Yuxi, et al.
Pubblicazione: (2026)

On Verbalized Confidence Scores for LLMs
di: Yang, Daniel, et al.
Pubblicazione: (2024)

Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations
di: Xia, Yuxi, et al.
Pubblicazione: (2026)

On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks
di: Obadinma, Stephen, et al.
Pubblicazione: (2025)

LLMs Can Teach Themselves to Better Predict the Future
di: Turtel, Benjamin, et al.
Pubblicazione: (2025)

How do LLMs Compute Verbal Confidence
di: Kumaran, Dharshan, et al.
Pubblicazione: (2026)

Black-box Model Ensembling for Textual and Visual Question Answering via Information Fusion
di: Xia, Yuxi, et al.
Pubblicazione: (2024)

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs
di: Zhao, Tianyi, et al.
Pubblicazione: (2026)

Not All Explanations Simulate Equally: Comparing Verbalized Feature Attributions and Self-Generated Rationales
di: Hong, Pingjun, et al.
Pubblicazione: (2026)

Token-wise Influential Training Data Retrieval for Large Language Models
di: Lin, Huawei, et al.
Pubblicazione: (2024)

NAACL: Noise-AwAre Verbal Confidence Calibration for Robust LLMs in RAG Systems
di: Liu, Jiayu, et al.
Pubblicazione: (2026)

Identifying Influential N-grams in Confidence Calibration via Regression Analysis
di: Ozaki, Shintaro, et al.
Pubblicazione: (2026)

Unlearning Traces the Influential Training Data of Language Models
di: Isonuma, Masaru, et al.
Pubblicazione: (2024)

ConfTuner: Training Large Language Models to Express Their Confidence Verbally
di: Li, Yibo, et al.
Pubblicazione: (2025)

Direct Confidence Alignment: Aligning Verbalized Confidence with Internal Confidence In Large Language Models
di: Zhang, Glenn, et al.
Pubblicazione: (2025)

Multicalibration for Confidence Scoring in LLMs
di: Detommaso, Gianluca, et al.
Pubblicazione: (2024)

ADVICE: Answer-Dependent Verbalized Confidence Estimation
di: Seo, Ki Jung, et al.
Pubblicazione: (2025)

Are LLM Decisions Faithful to Verbal Confidence?
di: Wang, Jiawei, et al.
Pubblicazione: (2026)

Calibrating Verbalized Confidence with Self-Generated Distractors
di: Wang, Victor, et al.
Pubblicazione: (2025)

Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?
di: Ni, Shiyu, et al.
Pubblicazione: (2024)

Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles
di: Xia, Yuxi, et al.
Pubblicazione: (2025)

LESS: Selecting Influential Data for Targeted Instruction Tuning
di: Xia, Mengzhou, et al.
Pubblicazione: (2024)

Exploring the Mystery of Influential Data for Mathematical Reasoning
di: Ni, Xinzhe, et al.
Pubblicazione: (2024)

Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning
di: Li, Xiaochuan, et al.
Pubblicazione: (2024)

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
di: Treutlein, Johannes, et al.
Pubblicazione: (2024)

Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution
di: Wang, Ante, et al.
Pubblicazione: (2025)

ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
di: Li, Chen, et al.
Pubblicazione: (2026)

Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval
di: Sinha, Aarush
Pubblicazione: (2025)

Explainable Detection of Implicit Influential Patterns in Conversations via Data Augmentation
di: Abdidizaji, Sina, et al.
Pubblicazione: (2025)

Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization
di: Wu, Di, et al.
Pubblicazione: (2025)

Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen
di: Cacioli, Jon-Paul
Pubblicazione: (2026)

Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
di: Park, Sangkwon, et al.
Pubblicazione: (2026)

Verbalizing LLMs' assumptions to explain and control sycophancy
di: Cheng, Myra, et al.
Pubblicazione: (2026)

Syntriever: How to Train Your Retriever with Synthetic Data from LLMs
di: Kim, Minsang, et al.
Pubblicazione: (2025)

DataProphet: Demystifying Supervision Data Generalization in Multimodal LLMs
di: Qi, Xuan, et al.
Pubblicazione: (2026)

LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations
di: Zhang, Caiqi, et al.
Pubblicazione: (2025)