Copertina

Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhou, Yuxuan, Keuper, Margret, Fritz, Mario
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Divide & Bind Your Attention for Improved Generative Semantic Nursing
di: Li, Yumeng, et al.
Pubblicazione: (2023)

Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations
di: Yu, Sunny, et al.
Pubblicazione: (2025)

The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation
di: Carlsson, Fredrik, et al.
Pubblicazione: (2024)

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
di: Samvelyan, Mikayel, et al.
Pubblicazione: (2024)

MultiMax: Sparse and Multi-Modal Attention Learning
di: Zhou, Yuxuan, et al.
Pubblicazione: (2024)

Reverse-Engineered Reasoning for Open-Ended Generation
di: Wang, Haozhe, et al.
Pubblicazione: (2025)

ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
di: Choi, Hyeong Kyu, et al.
Pubblicazione: (2026)

Assessing Bias in Metric Models for LLM Open-Ended Generation Bias Benchmarks
di: Demchak, Nathaniel, et al.
Pubblicazione: (2024)

Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation
di: Chen, Nuo, et al.
Pubblicazione: (2026)

DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking
di: Hu, Tianyi, et al.
Pubblicazione: (2026)

Generating Planning Feedback for Open-Ended Programming Exercises with LLMs
di: Demirtaş, Mehmet Arif, et al.
Pubblicazione: (2025)

AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses
di: Lu, Xiaotian, et al.
Pubblicazione: (2024)

MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation
di: Li, Yu, et al.
Pubblicazione: (2024)

How Do Training Methods Influence the Utilization of Vision Models?
di: Gavrikov, Paul, et al.
Pubblicazione: (2024)

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
di: Zhang, Jiayi, et al.
Pubblicazione: (2025)

A Mixture-of-Experts Approach to Few-Shot Task Transfer in Open-Ended Text Worlds
di: Cui, Christopher Z., et al.
Pubblicazione: (2024)

Basis Vector Metric: A Method for Robust Open-Ended State Change Detection
di: Oprea, David, et al.
Pubblicazione: (2025)

MIRROR: A Novel Approach for the Automated Evaluation of Open-Ended Question Generation
di: Deroy, Aniket, et al.
Pubblicazione: (2024)

From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation
di: Guo, Zhihan, et al.
Pubblicazione: (2025)

A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
di: Wang, Zhanliang, et al.
Pubblicazione: (2026)

Towards Open-Ended Discovery for Low-Resource NLP
di: Dossou, Bonaventure F. P., et al.
Pubblicazione: (2025)

Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding
di: Jinnai, Yuu, et al.
Pubblicazione: (2024)

MiRD: Reliable Set-Valued Prediction for Open-Ended Question Answering via Miscoverage Risk Decomposition
di: Hu, Anqi, et al.
Pubblicazione: (2026)

Open-Ended Wargames with Large Language Models
di: Hogan, Daniel P., et al.
Pubblicazione: (2024)

Dynamic Alignment for Collective Agency: Toward a Scalable Self-Improving Framework for Open-Ended LLM Alignment
di: Anantaprayoon, Panatchakorn, et al.
Pubblicazione: (2025)

An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems
di: Shaik, Hashmath, et al.
Pubblicazione: (2024)

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
di: Xie, Tianbao, et al.
Pubblicazione: (2024)

IRLBench: A Multi-modal, Culturally Grounded, Parallel Irish-English Benchmark for Open-Ended LLM Reasoning Evaluation
di: Tran, Khanh-Tung, et al.
Pubblicazione: (2025)

Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs
di: Troshin, Sergey, et al.
Pubblicazione: (2025)

GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows
di: Wang, Jize, et al.
Pubblicazione: (2026)

Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
di: Yang, Zixuan, et al.
Pubblicazione: (2026)

DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generation
di: Franceschelli, Giorgio, et al.
Pubblicazione: (2025)

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
di: Lee, Jaehyeok, et al.
Pubblicazione: (2026)

AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research
di: Li, Yishan, et al.
Pubblicazione: (2026)

R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning
di: Liu, Wanlong, et al.
Pubblicazione: (2026)

Transparent Reference-free Automated Evaluation of Open-Ended User Survey Responses
di: An, Subin, et al.
Pubblicazione: (2025)

GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models
di: Hutson, Dylan, et al.
Pubblicazione: (2025)

Decoding Open-Ended Information Seeking Goals from Eye Movements in Reading
di: Hadar, Cfir Avraham, et al.
Pubblicazione: (2025)

O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering
di: Mei, Jianbiao, et al.
Pubblicazione: (2025)

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors
di: Fang, Hao, et al.
Pubblicazione: (2025)