Image de couverture de livre

Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cui, Huizi, Ma, Huan, Wang, Qilin, Gao, Yuhang, Zhang, Changqing
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Estimating LLM Uncertainty with Evidence
par: Ma, Huan, et autres
Publié: (2025)

LLM-Generated Black-box Explanations Can Be Adversarially Helpful
par: Ajwani, Rohan, et autres
Publié: (2024)

Towards LLM-guided Causal Explainability for Black-box Text Classifiers
par: Bhattacharjee, Amrita, et autres
Publié: (2023)

Robust Reasoning via Dynamic Token Selection for Distribution-Aligned Self-Distillation
par: Zhang, Ruiqi, et autres
Publié: (2026)

Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty
par: Feng, Yu, et autres
Publié: (2024)

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
par: Yan, Shaotian, et autres
Publié: (2026)

Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis
par: Lu, Junyu, et autres
Publié: (2026)

Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models
par: Lin, Zhen, et autres
Publié: (2023)

Exploiting Class Probabilities for Black-box Sentence-level Attacks
par: Moraffah, Raha, et autres
Publié: (2024)

Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Models
par: Zhao, Yicong, et autres
Publié: (2025)

TroubleLLM: Align to Red Team Expert
par: Xu, Zhuoer, et autres
Publié: (2024)

Aligning Black-box Language Models with Human Judgments
par: Burg, Gerrit J. J. van den, et autres
Publié: (2025)

Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering
par: Wang, Yubo, et autres
Publié: (2023)

From Images to Words: Efficient Cross-Modal Knowledge Distillation to Language Models from Black-box Teachers
par: Sengupta, Ayan, et autres
Publié: (2026)

Length Controlled Generation for Black-box LLMs
par: Gu, Yuxuan, et autres
Publié: (2024)

ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
par: Zhang, Lingxi, et autres
Publié: (2024)

ALIEN: Aligned Entropy Head for Improving Uncertainty Estimation of LLMs
par: Zabolotnyi, Artem, et autres
Publié: (2025)

Semantic Self-Distillation for Language Model Uncertainty
par: Phillips, Edward, et autres
Publié: (2026)

Split and Merge: Aligning Position Biases in LLM-based Evaluators
par: Li, Zongjie, et autres
Publié: (2023)

RDRec: Rationale Distillation for LLM-based Recommendation
par: Wang, Xinfeng, et autres
Publié: (2024)

Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation
par: Shao, Shuo, et autres
Publié: (2025)

On true empty category
par: Tian, Qilin
Publié: (2025)

Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation
par: Li, Changcheng, et autres
Publié: (2026)

Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
par: Srey, Ponhvoan, et autres
Publié: (2026)

Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
par: Zhang, Yuanhe, et autres
Publié: (2024)

Bounded Behavioral Indistinguishability for Black-Box LLM Distillation
par: Hasan, Munawar
Publié: (2026)

Leveraging Uncertainty Estimation for Efficient LLM Routing
par: Zhang, Tuo, et autres
Publié: (2025)

Distribution-Aligned Decoding for Efficient LLM Task Adaptation
par: Hu, Senkang, et autres
Publié: (2025)

Automated Detection of Pre-training Text in Black-box LLMs
par: Hu, Ruihan, et autres
Publié: (2025)

StoryLens: Preference-Aligned Story Rewriting via Context-Aware Narrative Enrichment
par: Cui, Hanwen, et autres
Publié: (2026)

Can We Trust a Black-box LLM? LLM Untrustworthy Boundary Detection via Bias-Diffusion and Multi-Agent Reinforcement Learning
par: Zhou, Xiaotian, et autres
Publié: (2026)

Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents
par: Wang, Chunxiao
Publié: (2026)

Smaller Language Models are Better Black-box Machine-Generated Text Detectors
par: Mireshghallah, Niloofar, et autres
Publié: (2023)

$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
par: Li, Pengyu, et autres
Publié: (2026)

AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation
par: Zhang, Songming, et autres
Publié: (2025)

CBP-Tuning: Efficient Local Customization for Black-box Large Language Models
par: Zhao, Jiaxuan, et autres
Publié: (2025)

Black-box Prompt Tuning with Subspace Learning
par: Zheng, Yuanhang, et autres
Publié: (2023)

Estimating Semantic Alphabet Size for LLM Uncertainty Quantification
par: McCabe, Lucas H., et autres
Publié: (2025)

Investigating Human-Aligned Large Language Model Uncertainty
par: Moore, Kyle, et autres
Publié: (2025)

RM-Distiller: Exploiting Generative LLM for Reward Model Distillation
par: Zhou, Hongli, et autres
Publié: (2026)