Copertina

The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hägele, Alexander, Gema, Aryo Pradipta, Sleight, Henry, Perez, Ethan, Sohl-Dickstein, Jascha
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AI Organizations are More Effective but Less Aligned than Individual Agents
di: Shen, Judy Hanwen, et al.
Pubblicazione: (2026)

Inverse Scaling in Test-Time Compute
di: Gema, Aryo Pradipta, et al.
Pubblicazione: (2025)

The boundary of neural network trainability is fractal
di: Sohl-Dickstein, Jascha
Pubblicazione: (2024)

General-Purpose In-Context Learning by Meta-Learning Transformers
di: Kirsch, Louis, et al.
Pubblicazione: (2022)

Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs
di: Saxena, Rohit, et al.
Pubblicazione: (2025)

Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them
di: Rajani, Neel, et al.
Pubblicazione: (2025)

Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints
di: Gema, Aryo Pradipta, et al.
Pubblicazione: (2024)

Levels of AGI for Operationalizing Progress on the Path to AGI
di: Morris, Meredith Ringel, et al.
Pubblicazione: (2023)

CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning
di: Leang, Joshua Ong Jun, et al.
Pubblicazione: (2024)

Noiser: Bounded Input Perturbations for Attributing Large Language Models
di: Madani, Mohammad Reza Ghasemi, et al.
Pubblicazione: (2025)

Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
di: Du, Yilun, et al.
Pubblicazione: (2023)

An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering
di: Murphy, Alexander, et al.
Pubblicazione: (2025)

GRADA: Graph-based Reranking against Adversarial Documents Attack
di: Zheng, Jingjie, et al.
Pubblicazione: (2025)

DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations
di: Gema, Aryo Pradipta, et al.
Pubblicazione: (2024)

MessIRve: A Large-Scale Spanish Information Retrieval Dataset
di: Valentini, Francisco, et al.
Pubblicazione: (2024)

A Comparative Study on Patient Language across Therapeutic Domains for Effective Patient Voice Classification in Online Health Discussions
di: Lysandrou, Giorgos, et al.
Pubblicazione: (2024)

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
di: Guo, Shiyuan, et al.
Pubblicazione: (2025)

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models
di: Ensign, Danielle, et al.
Pubblicazione: (2025)

Agentic Misalignment: How LLMs Could Be Insider Threats
di: Lynch, Aengus, et al.
Pubblicazione: (2025)

Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning
di: Mahrooghi, Ilia, et al.
Pubblicazione: (2026)

Evaluating Control Protocols for Untrusted AI Agents
di: Kutasov, Jon, et al.
Pubblicazione: (2025)

Looking Inward: Language Models Can Learn About Themselves by Introspection
di: Binder, Felix J, et al.
Pubblicazione: (2024)

Stress-Testing Model Specs Reveals Character Differences among Language Models
di: Zhang, Jifan, et al.
Pubblicazione: (2025)

Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
di: Slocum, Stewart, et al.
Pubblicazione: (2025)

Same Answer, Different Representations: Hidden instability in VLMs
di: Wani, Farooq Ahmad, et al.
Pubblicazione: (2026)

Intelligence Analysis of Language Models
di: Galanti, Liane, et al.
Pubblicazione: (2024)

PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains
di: Leang, Joshua Ong Jun, et al.
Pubblicazione: (2025)

A Preliminary Study of Multilingual Code Language Models for Code Generation Task Using Translated Benchmarks
di: Dandamudi, Rohit, et al.
Pubblicazione: (2024)

Does Self-Evaluation Enable Wireheading in Language Models?
di: Africa, David Demitri, et al.
Pubblicazione: (2025)

Misalignment Bounty: Crowdsourcing AI Agent Misbehavior
di: Turtayev, Rustem, et al.
Pubblicazione: (2025)

How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
di: Abbe, Emmanuel, et al.
Pubblicazione: (2024)

How to Assess AI Literacy: Misalignment Between Self-Reported and Objective-Based Measures
di: Zhang, Shan, et al.
Pubblicazione: (2026)

Towards Avoiding the Data Mess: Industry Insights from Data Mesh Implementations
di: Bode, Jan, et al.
Pubblicazione: (2023)

Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler
di: Dremov, Aleksandr, et al.
Pubblicazione: (2025)

Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
di: Shilov, Igor, et al.
Pubblicazione: (2025)

A Sober Look at Agentic Misalignment in Automated Workflows
di: Ye, Wenqian, et al.
Pubblicazione: (2026)

Unsupervised Elicitation of Language Models
di: Wen, Jiaxin, et al.
Pubblicazione: (2025)

Addressing and Visualizing Misalignments in Human Task-Solving Trajectories
di: Kim, Sejin, et al.
Pubblicazione: (2024)

How Does Naming Affect LLMs on Code Analysis Tasks?
di: Wang, Zhilong, et al.
Pubblicazione: (2023)

AI Scientist via Synthetic Task Scaling
di: Cai, Ziyang, et al.
Pubblicazione: (2026)