Image de couverture de livre

Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Feng, Mingqian, Liu, Xiaodong, Yang, Weiwei, Xu, Chenliang, White, Christopher, Gao, Jianfeng
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks
par: Yu, Xiaodong, et autres
Publié: (2023)

Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?
par: Feng, Mingqian, et autres
Publié: (2024)

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
par: Zhang, Zeliang, et autres
Publié: (2024)

Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment
par: Jinnai, Yuu, et autres
Publié: (2024)

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
par: Chow, Yinlam, et autres
Publié: (2024)

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
par: Feng, Mingqian, et autres
Publié: (2026)

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
par: Wang, Yiming, et autres
Publié: (2025)

Forward Learning for Gradient-based Black-box Saliency Map Generation
par: Zhang, Zeliang, et autres
Publié: (2024)

Estimating the Effects of Sample Training Orders for Large Language Models without Retraining
par: Yang, Hao, et autres
Publié: (2025)

Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding
par: Tang, Yolo Yunlong, et autres
Publié: (2024)

Best of mini-N in-loop Sampling: A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling
par: Rho, Hyung Gyu, et autres
Publié: (2025)

Language Models as Inductive Reasoners
par: Yang, Zonglin, et autres
Publié: (2022)

Best Practices for Large Language Models in Radiology
par: Bluethgen, Christian, et autres
Publié: (2024)

SAFER: Risk-Constrained Sample-then-Filter in Large Language Models
par: Wang, Qingni, et autres
Publié: (2025)

Adversarial Attacks on Large Language Models in Medicine
par: Yang, Yifan, et autres
Publié: (2024)

Personalized Risks and Regulatory Strategies of Large Language Models in Digital Advertising
par: Feng, Haoyang, et autres
Publié: (2025)

Scalable Delphi: Large Language Models for Structured Risk Estimation
par: Lorenz, Tobias, et autres
Publié: (2026)

Learning to Transform Dynamically for Better Adversarial Transferability
par: Zhu, Rongyi, et autres
Publié: (2024)

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment
par: Zhang, Shaolei, et autres
Publié: (2024)

Scalable Best-of-N Selection for Large Language Models via Self-Certainty
par: Kang, Zhewei, et autres
Publié: (2025)

Large Language Models: A Survey
par: Minaee, Shervin, et autres
Publié: (2024)

Automated Retrosynthesis Planning of Macromolecules Using Large Language Models and Knowledge Graphs
par: Ma, Qinyu, et autres
Publié: (2025)

SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
par: Diao, Muxi, et autres
Publié: (2024)

FLOPS: Forward Learning with OPtimal Sampling
par: Ren, Tao, et autres
Publié: (2024)

StreamAdapter: Efficient Test Time Adaptation from Contextual Streams
par: Muhtar, Dilxat, et autres
Publié: (2024)

Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images
par: Wang, Yubo, et autres
Publié: (2025)

CarBoN: Calibrated Best-of-N Sampling Improves Test-time Reasoning
par: Tang, Yung-Chen, et autres
Publié: (2025)

Adversarial Moral Stress Testing of Large Language Models
par: Jamshidi, Saeid, et autres
Publié: (2026)

Rethinking Interpretability in the Era of Large Language Models
par: Singh, Chandan, et autres
Publié: (2024)

Soft Best-of-n Sampling for Model Alignment
par: Verdun, Claudio Mayrink, et autres
Publié: (2025)

On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models
par: Yang, April, et autres
Publié: (2024)

PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization
par: Jiao, Yang, et autres
Publié: (2025)

Inference to the Best Explanation in Large Language Models
par: Dalal, Dhairya, et autres
Publié: (2024)

Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
par: Zhang, Qingru, et autres
Publié: (2024)

S$^4$C: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models
par: He, Tao, et autres
Publié: (2025)

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
par: Zhang, Xinwei, et autres
Publié: (2026)

AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization
par: Liu, Chaohu, et autres
Publié: (2025)

Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models
par: Wang, Qingni, et autres
Publié: (2024)

CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization
par: Sun, Weiwei, et autres
Publié: (2025)

Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models
par: Liu, Yan, et autres
Publié: (2026)