Imagen de Portada

When Should a Language Model Trust Itself? Same-Model Self-Verification as a Conditional Confidence Signal

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Phalod, Aditya Ajay
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Trust in One Round: Confidence Estimation for Large Language Models via Structural Signals
por: Yang, Pengyue, et al.
Publicado: (2026)

Self-Training Large Language Models with Confident Reasoning
por: Jang, Hyosoon, et al.
Publicado: (2025)

When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
por: Xu, Haoming, et al.
Publicado: (2026)

Self-ensemble: Mitigating Confidence Mis-calibration for Large Language Models
por: Xu, Zicheng, et al.
Publicado: (2025)

Confidence in the Reasoning of Large Language Models
por: Pawitan, Yudi, et al.
Publicado: (2024)

QA-Calibration of Language Model Confidence Scores
por: Manggala, Putra, et al.
Publicado: (2024)

When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
por: Liu, Xiaoze, et al.
Publicado: (2025)

LaMsS: When Large Language Models Meet Self-Skepticism
por: Wu, Yetao, et al.
Publicado: (2024)

Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
por: Zhao, Siyan, et al.
Publicado: (2026)

Confidence over Time: Confidence Calibration with Temporal Logic for Large Language Model Reasoning
por: Mao, Zhenjiang, et al.
Publicado: (2026)

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning
por: Singhi, Nishad, et al.
Publicado: (2025)

Let the Code LLM Edit Itself When You Edit the Code
por: He, Zhenyu, et al.
Publicado: (2024)

Confidence Calibration in Large Language Model-Based Entity Matching
por: Kamsteeg, Iris, et al.
Publicado: (2025)

Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence
por: Hager, Sophia, et al.
Publicado: (2025)

Learning When to Attend: Conditional Memory Access for Long-Context LLMs
por: Choudhary, Sakshi, et al.
Publicado: (2026)

Confidence Regulation Neurons in Language Models
por: Stolfo, Alessandro, et al.
Publicado: (2024)

When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models
por: Wang, Danny, et al.
Publicado: (2026)

Unsupervised Pretraining for Fact Verification by Language Model Distillation
por: Bazaga, Adrián, et al.
Publicado: (2023)

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

Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models
por: Lin, Zhen, et al.
Publicado: (2023)

When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars
por: Higuchi, Rei, et al.
Publicado: (2025)

A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction
por: van Niekerk, Carel, et al.
Publicado: (2023)

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

LLM-Independent Adaptive RAG: Let the Question Speak for Itself
por: Marina, Maria, et al.
Publicado: (2025)

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models
por: Syed, Mohammed Sameer, et al.
Publicado: (2026)

Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning
por: Liu, Shuo, et al.
Publicado: (2026)

Recurrent Confidence Chain: Temporal-Aware Uncertainty Quantification in Large Language Models
por: Mao, Zhenjiang, et al.
Publicado: (2026)

Variation in Verification: Understanding Verification Dynamics in Large Language Models
por: Zhou, Yefan, et al.
Publicado: (2025)

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher
por: Uzunoglu, Arda, et al.
Publicado: (2026)

Machine Learning Research Has Outpaced Its Communication Norms and NeurIPS Should Act
por: Rangarajan, Ajay Mandyam, et al.
Publicado: (2026)

Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective
por: Gonzalez, Emmanuel Anaya, et al.
Publicado: (2025)

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding
por: Feng, Qi, et al.
Publicado: (2025)

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
por: Li, Pengyi, et al.
Publicado: (2025)

A Context-Aware Dual-Metric Framework for Confidence Estimation in Large Language Models
por: Yuan, Mingruo, et al.
Publicado: (2025)

Confidence-Modulated Speculative Decoding for Large Language Models
por: Sen, Jaydip, et al.
Publicado: (2025)

Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models
por: Cao, Jinghan, et al.
Publicado: (2026)

Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models
por: Naderi, Nariman, et al.
Publicado: (2025)

Benchmarking Distilled Language Models: Performance and Efficiency in Resource-Constrained Settings
por: Wani, Sachin Gopal, et al.
Publicado: (2026)

Large Language Models Can Self-Improve At Web Agent Tasks
por: Patel, Ajay, et al.
Publicado: (2024)

Query-Conditioned Test-Time Self-Training for Large Language Models
por: Song, Chaehee, et al.
Publicado: (2026)