Image de couverture de livre

MillStone: How Open-Minded Are LLMs?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Triedman, Harold, Shmatikov, Vitaly
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Multi-Agent Systems Execute Arbitrary Malicious Code
par: Triedman, Harold, et autres
Publié: (2025)

Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
par: Jha, Rishi, et autres
Publié: (2026)

Breaking and Fixing Defenses Against Control-Flow Hijacking in Multi-Agent Systems
par: Jha, Rishi, et autres
Publié: (2025)

Extracting Prompts by Inverting LLM Outputs
par: Zhang, Collin, et autres
Publié: (2024)

Adversarial Decoding: Generating Readable Documents for Adversarial Objectives
par: Zhang, Collin, et autres
Publié: (2024)

Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents
par: Shafran, Avital, et autres
Publié: (2024)

Deep-Research Agents Can Be Poisoned via User-Generated Content
par: Zhang, Tingwei, et autres
Publié: (2026)

Learning to Detect Language Model Training Data via Active Reconstruction
par: Yin, Junjie Oscar, et autres
Publié: (2026)

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
par: Ye, Jiayuan, et autres
Publié: (2026)

Reasoning Beyond Limits: Advances and Open Problems for LLMs
par: Ferrag, Mohamed Amine, et autres
Publié: (2025)

Why LLMs Cannot Think and How to Fix It
par: Jahrens, Marius, et autres
Publié: (2025)

How Does Quantization Affect Multilingual LLMs?
par: Marchisio, Kelly, et autres
Publié: (2024)

Extended Mind Transformers
par: Klett, Phoebe, et autres
Publié: (2024)

Universal Zero-shot Embedding Inversion
par: Zhang, Collin, et autres
Publié: (2025)

Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
par: Jones, Erik, et autres
Publié: (2025)

Slot Machines: How LLMs Keep Track of Multiple Entities
par: Bogdan, Paul C., et autres
Publié: (2026)

Optimization of Retrieval-Augmented Generation Context with Outlier Detection
par: Bulgakov, Vitaly
Publié: (2024)

Understanding How CodeLLMs (Mis)Predict Types with Activation Steering
par: Lucchetti, Francesca, et autres
Publié: (2024)

Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation
par: Chen, Hailin, et autres
Publié: (2023)

Reinforcing privacy reasoning in LLMs via normative simulacra from fiction
par: Franchi, Matt, et autres
Publié: (2026)

SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
par: Li, Sihang, et autres
Publié: (2024)

How Vulnerable Are Edge LLMs?
par: Ding, Ao, et autres
Publié: (2026)

Small LLMs Do Not Learn a Generalizable Theory of Mind via Reinforcement Learning
par: Sarangi, Sneheel, et autres
Publié: (2025)

Tamper-Resistant Safeguards for Open-Weight LLMs
par: Tamirisa, Rishub, et autres
Publié: (2024)

Dimensionality Reduction in Sentence Transformer Vector Databases with Fast Fourier Transform
par: Bulgakov, Vitaly, et autres
Publié: (2024)

RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?
par: Sun, Yiyou, et autres
Publié: (2025)

On Next-Token Prediction in LLMs: How End Goals Determine the Consistency of Decoding Algorithms
par: Trauger, Jacob, et autres
Publié: (2025)

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
par: Yan, Lecheng, et autres
Publié: (2026)

How Susceptible are LLMs to Influence in Prompts?
par: Anagnostidis, Sotiris, et autres
Publié: (2024)

How to Train Data-Efficient LLMs
par: Sachdeva, Noveen, et autres
Publié: (2024)

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
par: Apertus, Project, et autres
Publié: (2025)

How do LLMs Compute Verbal Confidence
par: Kumaran, Dharshan, et autres
Publié: (2026)

Teaching LLMs How to Learn with Contextual Fine-Tuning
par: Choi, Younwoo, et autres
Publié: (2025)

Harnessing the Universal Geometry of Embeddings
par: Jha, Rishi, et autres
Publié: (2025)

Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
par: Song, Yuda, et autres
Publié: (2024)

PromptMind Team at EHRSQL-2024: Improving Reliability of SQL Generation using Ensemble LLMs
par: Gundabathula, Satya K, et autres
Publié: (2024)

Rerouting LLM Routers
par: Shafran, Avital, et autres
Publié: (2025)

Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety
par: Mao, Junyu, et autres
Publié: (2025)

Mind the Gap: Data Rewriting for Stable Off-Policy Supervised Fine-Tuning
par: Zhao, Shiwan, et autres
Publié: (2025)

Many Minds from One Model: Bayesian-Inspired Transformers for Population Diversity
par: Yang, Diji, et autres
Publié: (2025)