Copertina

Knowledge Divergence and the Value of Debate for Scalable Oversight

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Young, Robin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Towards Scalable Oversight via Partitioned Human Supervision
di: Yin, Ren, et al.
Pubblicazione: (2025)

Scalable Oversight for Superhuman AI via Recursive Self-Critiquing
di: Wen, Xueru, et al.
Pubblicazione: (2025)

Why Is RLHF Alignment Shallow? A Gradient Analysis
di: Young, Robin
Pubblicazione: (2026)

Great Models Think Alike and this Undermines AI Oversight
di: Goel, Shashwat, et al.
Pubblicazione: (2025)

Towards Scalable Oversight with Collaborative Multi-Agent Debate in Error Detection
di: Chen, Yongqiang, et al.
Pubblicazione: (2025)

Scaling Laws For Scalable Oversight
di: Engels, Joshua, et al.
Pubblicazione: (2025)

Merging Methods for Multilingual Knowledge Editing for Large Language Models: An Empirical Odyssey
di: Lee, Kunil, et al.
Pubblicazione: (2026)

HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature
di: Joshi, Devvrat, et al.
Pubblicazione: (2026)

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning
di: Liu, Tianci, et al.
Pubblicazione: (2025)

Multi-Agent Debate with Memory Masking
di: Tian, Hongduan, et al.
Pubblicazione: (2026)

LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations
di: Vujanic, Robin, et al.
Pubblicazione: (2025)

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
di: Li, Han, et al.
Pubblicazione: (2025)

Convergence and Divergence of Language Models under Different Random Seeds
di: Fehlauer, Finlay, et al.
Pubblicazione: (2025)

DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models
di: Li, Zihao, et al.
Pubblicazione: (2025)

Building a Precise Video Language with Human-AI Oversight
di: Lin, Zhiqiu, et al.
Pubblicazione: (2026)

Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions
di: Wu, Haoze, et al.
Pubblicazione: (2025)

UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
di: Georgiev, Dobrik, et al.
Pubblicazione: (2026)

DebateBench: A Challenging Long Context Reasoning Benchmark For Large Language Models
di: Tiwari, Utkarsh, et al.
Pubblicazione: (2025)

Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization
di: Deiseroth, Björn, et al.
Pubblicazione: (2023)

KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
di: Wang, Fan, et al.
Pubblicazione: (2024)

Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge
di: Cui, Xinyue, et al.
Pubblicazione: (2025)

Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity
di: Zhang, Hangfan, et al.
Pubblicazione: (2025)

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values
di: Yu, Dian, et al.
Pubblicazione: (2025)

From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium
di: Yi, Xie, et al.
Pubblicazione: (2025)

Verify with Caution: The Pitfalls of Relying on Imperfect Factuality Metrics
di: Godbole, Ameya, et al.
Pubblicazione: (2025)

Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance
di: Chen, Xinzhu, et al.
Pubblicazione: (2026)

Scalable Ensembling For Mitigating Reward Overoptimisation
di: Ahmed, Ahmed M., et al.
Pubblicazione: (2024)

S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
di: Young, Jack
Pubblicazione: (2026)

Summaries as Centroids for Interpretable and Scalable Text Clustering
di: Diaz-Rodriguez, Jairo
Pubblicazione: (2025)

ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA datasets with Large Language Models
di: Pradeep, Ronak, et al.
Pubblicazione: (2024)

Value Alignment from Unstructured Text
di: Padhi, Inkit, et al.
Pubblicazione: (2024)

Value Drifts: Tracing Value Alignment During LLM Post-Training
di: Bhatia, Mehar, et al.
Pubblicazione: (2025)

Debate Helps Weak Judges Reward Stronger Models
di: Elasky, Ethan, et al.
Pubblicazione: (2026)

Evaluating the Performance of Large Language Models via Debates
di: Moniri, Behrad, et al.
Pubblicazione: (2024)

Learning to Focus: Focal Attention for Selective and Scalable Transformers
di: Ram, Dhananjay, et al.
Pubblicazione: (2025)

Robust and Scalable Model Editing for Large Language Models
di: Chen, Yingfa, et al.
Pubblicazione: (2024)

Learning to Evict from Key-Value Cache
di: Moschella, Luca, et al.
Pubblicazione: (2026)

ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs
di: Dammu, Preetam Prabhu Srikar, et al.
Pubblicazione: (2024)

Radio: Rate-Distortion Optimization for Large Language Model Compression
di: Young, Sean I.
Pubblicazione: (2025)

Foundations of Large Language Model Compression -- Part 1: Weight Quantization
di: Young, Sean I.
Pubblicazione: (2024)