Image de couverture de livre

Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Geng, Saibo, Döner, Berkay, Wendler, Chris, Josifoski, Martin, West, Robert
Format:	Preprint
Publié:	2024
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

Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
par: Geng, Saibo, et autres
Publié: (2023)

Byte BPE Tokenization as an Inverse string Homomorphism
par: Geng, Saibo, et autres
Publié: (2024)

Agentic AI: The Era of Semantic Decoding
par: Peyrard, Maxime, et autres
Publié: (2024)

zip2zip: Inference-Time Adaptive Tokenization via Online Compression
par: Geng, Saibo, et autres
Publié: (2025)

Combining Constrained and Unconstrained Decoding via Boosting: BoostCD and Its Application to Information Extraction
par: Šakota, Marija, et autres
Publié: (2025)

Do Llamas Work in English? On the Latent Language of Multilingual Transformers
par: Wendler, Chris, et autres
Publié: (2024)

TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards
par: Nica, Andreea, et autres
Publié: (2025)

Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
par: Dumas, Clément, et autres
Publié: (2024)

Localized Cultural Knowledge is Conserved and Controllable in Large Language Models
par: Veselovsky, Veniamin, et autres
Publié: (2025)

JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models
par: Geng, Saibo, et autres
Publié: (2025)

Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
par: Brinkmann, Jannik, et autres
Publié: (2025)

Evaluating Language Model Agency through Negotiations
par: Davidson, Tim R., et autres
Publié: (2024)

Multilingual Contrastive Decoding via Language-Agnostic Layers Skipping
par: Zhu, Wenhao, et autres
Publié: (2024)

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
par: Zhang, Jianyi, et autres
Publié: (2024)

SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable
par: Zhang, Jiaxin, et autres
Publié: (2025)

API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access
par: Su, Jiayuan, et autres
Publié: (2024)

A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
par: Monea, Giovanni, et autres
Publié: (2023)

VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits
par: Shao, Jintian, et autres
Publié: (2025)

LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models
par: Wang, Zhenyu
Publié: (2025)

Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models
par: Ye, Haotian, et autres
Publié: (2025)

DSCD: Large Language Model Detoxification with Self-Constrained Decoding
par: Dong, Ming, et autres
Publié: (2025)

PostMark: A Robust Blackbox Watermark for Large Language Models
par: Chang, Yapei, et autres
Publié: (2024)

First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models
par: Ha, Jiwoo, et autres
Publié: (2026)

Translate-and-Revise: Boosting Large Language Models for Constrained Translation
par: Huang, Pengcheng, et autres
Publié: (2024)

Discovering Forbidden Topics in Language Models
par: Rager, Can, et autres
Publié: (2025)

Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models
par: Arad, Dana, et autres
Publié: (2025)

Controllable Context Sensitivity and the Knob Behind It
par: Minder, Julian, et autres
Publié: (2024)

Sketch-to-Layout: Sketch-Guided Multimodal Layout Generation
par: Brioschi, Riccardo, et autres
Publié: (2025)

Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
par: Das, Souvik, et autres
Publié: (2024)

LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation
par: Chen, Jizheng, et autres
Publié: (2026)

DALD: Improving Logits-based Detector without Logits from Black-box LLMs
par: Zeng, Cong, et autres
Publié: (2024)

DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching
par: Xu, Zicheng, et autres
Publié: (2025)

Blackbox Model Provenance via Palimpsestic Membership Inference
par: Kuditipudi, Rohith, et autres
Publié: (2025)

Thinking Before Constraining: A Unified Decoding Framework for Large Language Models
par: Nguyen, Ngoc Trinh Hung, et autres
Publié: (2026)

(G)I-DLE: Generative Inference via Distribution-preserving Logit Exclusion with KL Divergence Minimization for Constrained Decoding
par: Lee, Hanwool
Publié: (2025)

Position-Aware Depth Decay Decoding ($D^3$): Boosting Large Language Model Inference Efficiency
par: Fan, Siqi, et autres
Publié: (2025)

Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding
par: Tu, Lifu, et autres
Publié: (2023)

UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models
par: Dong, Yijiang River, et autres
Publié: (2024)

ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding
par: Zhong, Qihuang, et autres
Publié: (2024)

Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model
par: Zhang, Biao, et autres
Publié: (2025)