Image de couverture de livre

On the Rejection Criterion for Proxy-based Test-time Alignment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hammal, Ayoub, Zweigenbaum, Pierre, Corro, Caio
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

Kad: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral
par: Hammal, Ayoub, et autres
Publié: (2025)

Suffix-Constrained Greedy Search Algorithms for Causal Language Models
par: Hammal, Ayoub, et autres
Publié: (2026)

Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection
par: Hammal, Ayoub, et autres
Publié: (2024)

A fast and sound tagging method for discontinuous named-entity recognition
par: Corro, Caio
Publié: (2024)

Am I eligible? Natural Language Inference for Clinical Trial Patient Recruitment: the Patient's Point of View
par: Aguiar, Mathilde, et autres
Publié: (2025)

SEME at SemEval-2024 Task 2: Comparing Masked and Generative Language Models on Natural Language Inference for Clinical Trials
par: Aguiar, Mathilde, et autres
Publié: (2024)

Sparse Logistic Regression with High-order Features for Automatic Grammar Rule Extraction from Treebanks
par: Herrera, Santiago, et autres
Publié: (2024)

A Study on Building Efficient Zero-Shot Relation Extraction Models
par: Thomas, Hugo, et autres
Publié: (2026)

DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures
par: Uthayasooriyar, Benno, et autres
Publié: (2025)

Training LayoutLM from Scratch for Efficient Named-Entity Recognition in the Insurance Domain
par: Uthayasooriyar, Benno, et autres
Publié: (2024)

Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms
par: Corro, Caio, et autres
Publié: (2025)

Is Clinical Text Enough? A Multimodal Study on Mortality Prediction in Heart Failure Patients
par: Khettari, Oumaima El, et autres
Publié: (2026)

Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLM
par: Tan, Chenkun, et autres
Publié: (2025)

PARHAF, a human-authored corpus of clinical reports for fictitious patients in French
par: Tannier, Xavier, et autres
Publié: (2026)

EuroBERT: Scaling Multilingual Encoders for European Languages
par: Boizard, Nicolas, et autres
Publié: (2025)

Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
par: Zhu, Yu, et autres
Publié: (2024)

Nested Named Entity Recognition as Single-Pass Sequence Labeling
par: Muñoz-Ortiz, Alberto, et autres
Publié: (2025)

Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
par: Kwon, Jihoon, et autres
Publié: (2026)

Rethinking the Role of Proxy Rewards in Language Model Alignment
par: Kim, Sungdong, et autres
Publié: (2024)

The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas
par: Marraffini, Giovanni Franco Gabriel, et autres
Publié: (2025)

Omnimodal Dataset Distillation via High-order Proxy Alignment
par: Gao, Yuxuan, et autres
Publié: (2026)

A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification
par: Meyoyan, Gonzalo Ariel, et autres
Publié: (2026)

Entropy Sentinel: Continuous LLM Accuracy Monitoring from Decoding Entropy Traces in STEM
par: Buffa, Pedro Memoli, et autres
Publié: (2026)

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models
par: Zhang, Yang, et autres
Publié: (2025)

Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation
par: Zhang, Haoran, et autres
Publié: (2025)

SaulLM-7B: A pioneering Large Language Model for Law
par: Colombo, Pierre, et autres
Publié: (2024)

$k$NNProxy: Efficient Training-Free Proxy Alignment for Black-Box Zero-Shot LLM-Generated Text Detection
par: Wong, Kahim, et autres
Publié: (2026)

ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models
par: Anugraha, David, et autres
Publié: (2024)

GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment
par: Xu, Yuancheng, et autres
Publié: (2024)

Tuning Language Models by Proxy
par: Liu, Alisa, et autres
Publié: (2024)

ProxyThinker: Test-Time Guidance through Small Visual Reasoners
par: Xiao, Zilin, et autres
Publié: (2025)

Autoregressive vs. Masked Diffusion Language Models: A Controlled Comparison
par: Vicentino, Caio
Publié: (2026)

Reasons to Reject? Aligning Language Models with Judgments
par: Xu, Weiwen, et autres
Publié: (2023)

Statistical Rejection Sampling Improves Preference Optimization
par: Liu, Tianqi, et autres
Publié: (2023)

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
par: Hazra, Rima, et autres
Publié: (2024)

"Mirror" Language AI Models of Depression are Criterion-Contaminated
par: Li, Tong, et autres
Publié: (2025)

Fast Best-of-N Decoding via Speculative Rejection
par: Sun, Hanshi, et autres
Publié: (2024)

Proxy Compression for Language Modeling
par: Zheng, Lin, et autres
Publié: (2026)

TARo: Token-level Adaptive Routing for LLM Test-time Alignment
par: Rai, Arushi, et autres
Publié: (2026)

Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning
par: Deng, Jie, et autres
Publié: (2026)