Image de couverture de livre

How Useful Is Cross-Domain Generalization for Training LLM Monitors?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Martin, Sam, Roger, Fabien
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Classifier Context Rot: Monitor Performance Degrades with Context Length
par: Martin, Sam, et autres
Publié: (2026)

Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents
par: Liu, Zhihan, et autres
Publié: (2026)

Target-specific Adaptation and Consistent Degradation Alignment for Cross-Domain Remaining Useful Life Prediction
par: Hou, Yubo, et autres
Publié: (2025)

Self-Attribution Bias: When AI Monitors Go Easy on Themselves
par: Khullar, Dipika, et autres
Publié: (2026)

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors
par: Najt, Elle, et autres
Publié: (2026)

Narrow Secret Loyalty Dodges Black-Box Audits
par: Lamerton, Alfie, et autres
Publié: (2026)

Mixup Domain Adaptations for Dynamic Remaining Useful Life Predictions
par: Furqon, Muhammad Tanzil, et autres
Publié: (2024)

Characterising LLM-Generated Competency Questions: a Cross-Domain Empirical Study using Open and Closed Models
par: Alharbi, Reham, et autres
Publié: (2026)

Evidential Domain Adaptation for Remaining Useful Life Prediction with Incomplete Degradation
par: Hou, Yubo, et autres
Publié: (2026)

Reasoning-Driven Multimodal LLM for Domain Generalization
par: Xu, Zhipeng, et autres
Publié: (2026)

CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
par: Alabdulmohsin, Ibrahim, et autres
Publié: (2024)

Structured Decomposition for LLM Reasoning: Cross-Domain Validation and Semantic Web Integration
par: Sadowski, Albert, et autres
Publié: (2026)

Geometry over Density: Few-Shot Cross-Domain OOD Detection
par: Li, Shawn, et autres
Publié: (2026)

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
par: Nikolić, Kristina, et autres
Publié: (2025)

Read, Grep, and Synthesize: Diagnosing Cross-Domain Seed Exposure for LLM Research Ideation
par: Choi, Yunju, et autres
Publié: (2026)

Cross-Domain Content Generation with Domain-Specific Small Language Models
par: Maloo, Ankit, et autres
Publié: (2024)

Generative Multi-Target Cross-Domain Recommendation
par: Jin, Jinqiu, et autres
Publié: (2025)

Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?
par: MacDermott, Matt, et autres
Publié: (2025)

Model Spec Midtraining: Improving How Alignment Training Generalizes
par: Li, Chloe, et autres
Publié: (2026)

When is Tree Search Useful for LLM Planning? It Depends on the Discriminator
par: Chen, Ziru, et autres
Publié: (2024)

AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and Propositions
par: Li, Jianxin, et autres
Publié: (2025)

PixelBytes: Catching Unified Representation for Multimodal Generation
par: Furfaro, Fabien
Publié: (2024)

PixelBytes: Catching Unified Embedding for Multimodal Generation
par: Furfaro, Fabien
Publié: (2024)

SemaCDR: LLM-Powered Transferable Semantics for Cross-Domain Sequential Recommendation
par: Zhang, Chunxu, et autres
Publié: (2026)

Federated Cross-Training Learners for Robust Generalization under Data Heterogeneity
par: Qi, Zhuang, et autres
Publié: (2024)

How to Train Your LLM Web Agent: A Statistical Diagnosis
par: Vattikonda, Dheeraj, et autres
Publié: (2025)

PowerGraph-LLM: Novel Power Grid Graph Embedding and Optimization with Large Language Models
par: Bernier, Fabien, et autres
Publié: (2025)

Exploiting Contextual Structure to Generate Useful Auxiliary Tasks
par: Quartey, Benedict, et autres
Publié: (2023)

Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain
par: Qiu, Zhongxi, et autres
Publié: (2025)

Deep Domain Adaptation for Turbofan Engine Remaining Useful Life Prediction: Methodologies, Evaluation and Future Trends
par: Wang, Yucheng, et autres
Publié: (2025)

Personalized Medication Planning via Direct Domain Modeling and LLM-Generated Heuristics
par: Vernik, Yonatan, et autres
Publié: (2026)

Domain Fusion Controllable Generalization for Cross-Domain Time Series Forecasting from Multi-Domain Integrated Distribution
par: Ma, Xiangkai, et autres
Publié: (2024)

CoALFake: Collaborative Active Learning with Human-LLM Co-Annotation for Cross-Domain Fake News Detection
par: Aïmeur, Esma, et autres
Publié: (2026)

GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization
par: Andrews, Martin, et autres
Publié: (2025)

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
par: Xu, Yixuan Even, et autres
Publié: (2025)

OneCast: Structured Decomposition and Modular Generation for Cross-Domain Time Series Forecasting
par: Pan, Tingyue, et autres
Publié: (2025)

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
par: Guo, Shiyuan, et autres
Publié: (2025)

How Good LLM-Generated Password Policies Are?
par: Vaidya, Vivek, et autres
Publié: (2025)

Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach
par: Zhang, Huaiwu, et autres
Publié: (2024)

SynCDR : Training Cross Domain Retrieval Models with Synthetic Data
par: Mishra, Samarth, et autres
Publié: (2023)