Image de couverture de livre

Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhou, Shang, Yao, Feng, Dong, Chengyu, Wang, Zihan, Shang, Jingbo
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

Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification
par: Peng, Letian, et autres
Publié: (2024)

Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation
par: Peng, Letian, et autres
Publié: (2023)

UltraGen: Extremely Fine-grained Controllable Generation via Attribute Reconstruction and Global Preference Optimization
par: Yun, Longfei, et autres
Publié: (2025)

Linear Correlation in LM's Compositional Generalization and Hallucination
par: Peng, Letian, et autres
Publié: (2025)

MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks
par: Peng, Letian, et autres
Publié: (2024)

When is the consistent prediction likely to be a correct prediction?
par: Nguyen, Alex, et autres
Publié: (2024)

Incubating Text Classifiers Following User Instruction with Nothing but LLM
par: Peng, Letian, et autres
Publié: (2024)

Codified Foreshadowing-Payoff Text Generation
par: Yun, Longfei, et autres
Publié: (2026)

Order Matters: Rethinking Prompt Construction in In-Context Learning
par: Li, Warren, et autres
Publié: (2025)

Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM's Nest
par: Peng, Letian, et autres
Publié: (2025)

Answer is All You Need: Instruction-following Text Embedding via Answering the Question
par: Peng, Letian, et autres
Publié: (2024)

Watermarks for Language Models via Probabilistic Automata
par: Wang, Yangkun, et autres
Publié: (2025)

Text Generation Beyond Discrete Token Sampling
par: Zhuang, Yufan, et autres
Publié: (2025)

Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
par: Peng, Letian, et autres
Publié: (2024)

Codifying Character Logic in Role-Playing
par: Peng, Letian, et autres
Publié: (2025)

Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning
par: Tong, Yongqi, et autres
Publié: (2024)

Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation
par: An, Chenyang, et autres
Publié: (2024)

A General Pseudonymization Framework for Cloud-Based LLMs: Replacing Privacy Information in Controlled Text Generation
par: Hou, Shilong, et autres
Publié: (2025)

Correlation and Navigation in the Vocabulary Key Representation Space of Language Models
par: Peng, Letian, et autres
Publié: (2024)

The Price of Format: Diversity Collapse in LLMs
par: Yun, Longfei, et autres
Publié: (2025)

Entangled Relations: Leveraging NLI and Meta-analysis to Enhance Biomedical Relation Extraction
par: Hogan, William, et autres
Publié: (2024)

Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text
par: Rao, Zixin, et autres
Publié: (2025)

Finish First, Perfect Later: Test-Time Token-Level Cross-Validation for Diffusion Large Language Models
par: Tian, Runchu, et autres
Publié: (2025)

Codified Finite-state Machines for Role-playing
par: Peng, Letian, et autres
Publié: (2026)

Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models
par: Mekala, Dheeraj, et autres
Publié: (2024)

FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering
par: Long, Yitao, et autres
Publié: (2025)

Controllable Stylistic Text Generation with Train-Time Attribute-Regularized Diffusion
par: Zhou, Fan, et autres
Publié: (2025)

Open-world Multi-label Text Classification with Extremely Weak Supervision
par: Li, Xintong, et autres
Publié: (2024)

Model-diff: A Tool for Comparative Study of Language Models in the Input Space
par: Liu, Weitang, et autres
Publié: (2024)

DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering
par: Nguyen, Alex, et autres
Publié: (2024)

Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
par: Zhong, Li, et autres
Publié: (2024)

READ: Improving Relation Extraction from an ADversarial Perspective
par: Li, Dawei, et autres
Publié: (2024)

Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs
par: Liang, Xun, et autres
Publié: (2024)

Towards Few-shot Entity Recognition in Document Images: A Graph Neural Network Approach Robust to Image Manipulation
par: Krishnan, Prashant, et autres
Publié: (2023)

Data Contamination Can Cross Language Barriers
par: Yao, Feng, et autres
Publié: (2024)

Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
par: Song, Maojia, et autres
Publié: (2024)

Unsupervised Text Style Transfer for Controllable Intensity
par: Gu, Shuhuan, et autres
Publié: (2026)

Deriving Character Logic from Storyline as Codified Decision Trees
par: Peng, Letian, et autres
Publié: (2026)

Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text
par: Mohamed, Amr, et autres
Publié: (2025)

AI-native Memory: A Pathway from LLMs Towards AGI
par: Shang, Jingbo, et autres
Publié: (2024)