Image de couverture de livre

NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jin, Hyundong, Han, Yo-Sub
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models
par: Jin, Hyundong, et autres
Publié: (2026)

Steering Language Models Before They Speak: Logit-Level Interventions
par: An, Hyeseon, et autres
Publié: (2026)

RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problems
par: Jin, Hyundong, et autres
Publié: (2025)

DLM-SWAI: Steering Diffusion Language Models Before They Unmask
par: An, Hyeseon, et autres
Publié: (2026)

From Intuition to Calibrated Judgment: A Rubric-Based Expert-Panel Study of Human Detection of LLM-Generated Korean Text
par: Park, Shinwoo, et autres
Publié: (2026)

AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection
par: Lee, Yejin, et autres
Publié: (2025)

A Linguistics-Aware LLM Watermarking via Syntactic Predictability
par: Park, Shinwoo, et autres
Publié: (2025)

Linguistics-Aware Non-Distortionary LLM Watermarking
par: Park, Shinwoo, et autres
Publié: (2026)

Obfuscation Rules for Detecting and Detoxifying Korean Toxicity
par: Lee, Yejin, et autres
Publié: (2025)

KatFishNet: Detecting LLM-Generated Korean Text through Linguistic Feature Analysis
par: Park, Shinwoo, et autres
Publié: (2025)

TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents
par: Jin, Hyundong, et autres
Publié: (2025)

RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection
par: Lee, Yejin, et autres
Publié: (2025)

How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMs
par: Kim, Su-Hyeon, et autres
Publié: (2026)

CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders
par: Kim, Su-Hyeon, et autres
Publié: (2026)

Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Features
par: Park, Shinwoo, et autres
Publié: (2025)

STAB: Specification-driven Testing for Algorithmic Bottlenecks
par: Lim, Soohan, et autres
Publié: (2026)

Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models
par: Cao, Jiaqi, et autres
Publié: (2025)

DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check
par: Qiao, Ziheng, et autres
Publié: (2024)

A Method for Handling Negative Similarities in Explainable Graph Spectral Clustering of Text Documents -- Extended Version
par: Kłopotek, Mieczysław A., et autres
Publié: (2025)

Repairing Regex Vulnerabilities via Localization-Guided Instructions
par: Sung, Sicheol, et autres
Publié: (2025)

Semantic Gravity Wells: Why Negative Constraints Backfire
par: Rana, Shailesh
Publié: (2026)

DeepEdit: Knowledge Editing as Decoding with Constraints
par: Wang, Yiwei, et autres
Publié: (2024)

ECO: Enhanced Code Optimization via Performance-Aware Prompting for Code-LLMs
par: Kim, Su-Hyeon, et autres
Publié: (2025)

Plug, Play, and Fuse: Zero-Shot Joint Decoding via Word-Level Re-ranking Across Diverse Vocabularies
par: Koneru, Sai, et autres
Publié: (2024)

Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs
par: Ma, Maotian, et autres
Publié: (2026)

Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion
par: Cheng, Zhen, et autres
Publié: (2026)

Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models
par: Yao, Jui-Ming, et autres
Publié: (2025)

Handling Ontology Gaps in Semantic Parsing
par: Bacciu, Andrea, et autres
Publié: (2024)

Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models
par: Kim, Kyeonghyun, et autres
Publié: (2025)

Decoding Large-Language Models: A Systematic Overview of Socio-Technical Impacts, Constraints, and Emerging Questions
par: Kaya, Zeyneb N., et autres
Publié: (2024)

ProbGate at EHRSQL 2024: Enhancing SQL Query Generation Accuracy through Probabilistic Threshold Filtering and Error Handling
par: Kim, Sangryul, et autres
Publié: (2024)

LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions
par: Song, Maojia, et autres
Publié: (2025)

Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations
par: Kim, Su-Hyeon, et autres
Publié: (2026)

Decoupled Alignment for Robust Plug-and-Play Adaptation
par: Luo, Haozheng, et autres
Publié: (2024)

How do Large Language Models Handle Multilingualism?
par: Zhao, Yiran, et autres
Publié: (2024)

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization
par: Duan, Shitong, et autres
Publié: (2024)

Enhancing Semantics in Multimodal Chain of Thought via Soft Negative Sampling
par: Zheng, Guangmin, et autres
Publié: (2024)

How does a Multilingual LM Handle Multiple Languages?
par: Kakarla, Santhosh, et autres
Publié: (2025)

Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
par: Jin, Tao, et autres
Publié: (2026)

PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents
par: Yang, Ke, et autres
Publié: (2026)