Image de couverture de livre

A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sivaprasad, Sarath, Kaushik, Pramod, Abdelnabi, Sahar, Fritz, Mario
Format:	Preprint
Publié:	2024
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

Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
par: Abdelnabi, Sahar, et autres
Publié: (2023)

Models That Know How Evaluations Are Designed Score Safer
par: Deckenbach, Katharina, et autres
Publié: (2026)

Linguistically Communicating Uncertainty in Patient-Facing Risk Prediction Models
par: Sivaprasad, Adarsa, et autres
Publié: (2024)

From Descriptive to Prescriptive: Uncover the Social Value Alignment of LLM-based Agents
par: Qu, Jinxian, et autres
Publié: (2026)

Decomposing and Measuring Evaluation Awareness
par: Li, Changling, et autres
Publié: (2026)

Certifiably robust malware detectors by design
par: Gimenez, Pierre-Francois, et autres
Publié: (2025)

Reasoning in Large Language Models: A Geometric Perspective
par: Cosentino, Romain, et autres
Publié: (2024)

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
par: Nakamura, Mason, et autres
Publié: (2026)

Do LLMs Exhibit Human-Like Reasoning? Evaluating Theory of Mind in LLMs for Open-Ended Responses
par: Amirizaniani, Maryam, et autres
Publié: (2024)

Towards Practical Tool Usage for Continually Learning LLMs
par: Huang, Jerry, et autres
Publié: (2024)

Mapping Clinical Doubt: Locating Linguistic Uncertainty in LLMs
par: Sridhar, Srivarshinee, et autres
Publié: (2025)

GenKnowSub: Improving Modularity and Reusability of LLMs through General Knowledge Subtraction
par: Bagherifard, Mohammadtaha, et autres
Publié: (2025)

Do Large Language Models Know Conflict? Investigating Parametric vs. Non-Parametric Knowledge of LLMs for Conflict Forecasting
par: Nemkova, Apollinaire Poli, et autres
Publié: (2025)

LLMs-in-the-Loop Part 2: Expert Small AI Models for Anonymization and De-identification of PHI Across Multiple Languages
par: Gunay, Murat, et autres
Publié: (2024)

Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation
par: Zhou, Yuxuan, et autres
Publié: (2024)

The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness
par: Abdelnabi, Sahar, et autres
Publié: (2025)

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
par: Zverev, Egor, et autres
Publié: (2024)

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning
par: Lan, Guangchen, et autres
Publié: (2025)

BBPOS: BERT-based Part-of-Speech Tagging for Uzbek
par: Bobojonova, Latofat, et autres
Publié: (2025)

Part-of-speech tagging for Nagamese Language using CRF
par: Shohe, Alovi N, et autres
Publié: (2025)

Towards Anthropomorphic Conversational AI Part I: A Practical Framework
par: Wei, Fei, et autres
Publié: (2025)

Grammar and Gameplay-aligned RL for Game Description Generation with LLMs
par: Tanaka, Tsunehiko, et autres
Publié: (2025)

LLMs-in-the-loop Part-1: Expert Small AI Models for Bio-Medical Text Translation
par: Keles, Bunyamin, et autres
Publié: (2024)

Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
par: Salem, Ahmed, et autres
Publié: (2026)

O1 Replication Journey: A Strategic Progress Report -- Part 1
par: Qin, Yiwei, et autres
Publié: (2024)

Exploring Chinese Humor Generation: A Study on Two-Part Allegorical Sayings
par: Xu, Rongwu
Publié: (2024)

PartialFormer: Modeling Part Instead of Whole for Machine Translation
par: Zheng, Tong, et autres
Publié: (2023)

Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs
par: Labroo, Arya, et autres
Publié: (2026)

How Can I Improve? Using GPT to Highlight the Desired and Undesired Parts of Open-ended Responses
par: Lin, Jionghao, et autres
Publié: (2024)

Safety Must Precede the Deployment of Open-Ended AI
par: Sheth, Ivaxi, et autres
Publié: (2025)

AI Agents May Always Fall for Prompt Injections
par: Abdelnabi, Sahar, et autres
Publié: (2026)

Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies
par: Nakamura, Mason, et autres
Publié: (2025)

LLM Generated Distribution-Based Prediction of US Electoral Results, Part I
par: Bradshaw, Caleb, et autres
Publié: (2024)

Data Science and Technology Towards AGI Part I: Tiered Data Management
par: Wang, Yudong, et autres
Publié: (2026)

Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training
par: Qin, Yiwei, et autres
Publié: (2026)

REAL: Response Embedding-based Alignment for LLMs
par: Zhang, Honggen, et autres
Publié: (2024)

LogiPart: Local Large Language Models for Data Exploration at Scale with Logical Partitioning
par: Tavares, Tiago Fernandes
Publié: (2025)

Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs
par: Kim, Junsol, et autres
Publié: (2026)

Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs
par: Sen, Jaydip, et autres
Publié: (2025)

CoRet: Improved Retriever for Code Editing
par: Fehr, Fabio, et autres
Publié: (2025)