Copertina

Deliberative Dynamics and Value Alignment in LLM Debates

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sachdeva, Pratik S., van Nuenen, Tom
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Normative Evaluation of Large Language Models with Everyday Moral Dilemmas
di: Sachdeva, Pratik S., et al.
Pubblicazione: (2025)

The Fragility Of Moral Judgment In Large Language Models
di: van Nuenen, Tom, et al.
Pubblicazione: (2026)

Stress Testing Deliberative Alignment for Anti-Scheming Training
di: Schoen, Bronson, et al.
Pubblicazione: (2025)

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety
di: Jin, Can, et al.
Pubblicazione: (2026)

Multiple LLM Agents Debate for Equitable Cultural Alignment
di: Ki, Dayeon, et al.
Pubblicazione: (2025)

Voice Under Revision: Large Language Models and the Normalization of Personal Narrative
di: van Nuenen, Tom
Pubblicazione: (2026)

Recognition Without Authorization: LLMs and the Moral Order of Online Advice
di: van Nuenen, Tom
Pubblicazione: (2026)

Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with constraints
di: Yin, Zhenyun, et al.
Pubblicazione: (2025)

Gradual Vigilance and Interval Communication: Enhancing Value Alignment in Multi-Agent Debates
di: Zou, Rui, et al.
Pubblicazione: (2024)

Value Alignment Tax: Measuring Value Trade-offs in LLM Alignment
di: Chen, Jiajun, et al.
Pubblicazione: (2026)

Deliberative Alignment: Reasoning Enables Safer Language Models
di: Guan, Melody Y., et al.
Pubblicazione: (2024)

An Evaluation of Cultural Value Alignment in LLM
di: Sukiennik, Nicholas, et al.
Pubblicazione: (2025)

VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment
di: Chen, Jiawei, et al.
Pubblicazione: (2026)

Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model Debate
di: Pecher, Tom
Pubblicazione: (2026)

Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment
di: Corrêa, Nicholas Kluge
Pubblicazione: (2024)

To Redact, or not to Redact? A Local LLM Approach to Deliberative Process Privilege Classification
di: Larooij, Maik, et al.
Pubblicazione: (2026)

Alignment Dynamics in LLM Fine-Tuning
di: Huang, Yuhan, et al.
Pubblicazione: (2026)

Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning
di: Wang, Chaojie, et al.
Pubblicazione: (2024)

AI-Enhanced Deliberative Democracy and the Future of the Collective Will
di: Revel, Manon, et al.
Pubblicazione: (2025)

DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation
di: Li, Zhenghao, et al.
Pubblicazione: (2026)

On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity
di: Huang, Muhua, et al.
Pubblicazione: (2025)

Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model
di: Pathmanathan, Pankayaraj, et al.
Pubblicazione: (2026)

LLM-FS-Agent: A Deliberative Role-based Large Language Model Architecture for Transparent Feature Selection
di: Bal-Ghaoui, Mohamed, et al.
Pubblicazione: (2025)

Question the Questions: Auditing Representation in Online Deliberative Processes
di: De, Soham, et al.
Pubblicazione: (2025)

Reason-to-Transmit: Deliberative Adaptive Communication for Cooperative Perception
di: Bansal, Aayam, et al.
Pubblicazione: (2026)

Systematic Biases in LLM Simulations of Debates
di: Taubenfeld, Amir, et al.
Pubblicazione: (2024)

D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents
di: Mi, Hongze, et al.
Pubblicazione: (2025)

Ensemble Debates with Local Large Language Models for AI Alignment
di: Sarabamoun, Ephraiem
Pubblicazione: (2025)

Baba is LLM: Reasoning in a Game with Dynamic Rules
di: van Wetten, Fien, et al.
Pubblicazione: (2025)

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
di: Hu, Tianyu, et al.
Pubblicazione: (2025)

MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction
di: Huang, Wei-Chieh, et al.
Pubblicazione: (2025)

Simulating the Evolution of Alignment and Values in Machine Intelligence
di: Eicher, Jonathan Elsworth
Pubblicazione: (2026)

Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
di: Chen, Wenhao, et al.
Pubblicazione: (2026)

Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making
di: Ma, Shuai, et al.
Pubblicazione: (2024)

AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs
di: Carro, María Victoria, et al.
Pubblicazione: (2025)

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

OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration
di: Zhang, Jusheng, et al.
Pubblicazione: (2025)

The Goofus & Gallant Story Corpus for Practical Value Alignment
di: Nahian, Md Sultan Al, et al.
Pubblicazione: (2025)

From Descriptive to Prescriptive: Uncover the Social Value Alignment of LLM-based Agents
di: Qu, Jinxian, et al.
Pubblicazione: (2026)

Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation
di: Xu, Hefei, et al.
Pubblicazione: (2025)