Copertina

Perturbation: A simple and efficient adversarial tracer for representation learning in language models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Rozner, Joshua, Shain, Cory
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

BabyLM's First Constructions: Causal probing provides a signal of learning
di: Rozner, Joshua, et al.
Pubblicazione: (2025)

Constructions are Revealed in Word Distributions
di: Rozner, Joshua, et al.
Pubblicazione: (2025)

On the generalization of language models from in-context learning and finetuning: a controlled study
di: Lampinen, Andrew K., et al.
Pubblicazione: (2025)

Survey on reinforcement learning for language processing
di: Uc-Cetina, Victor, et al.
Pubblicazione: (2021)

Leveraging large language models for efficient representation learning for entity resolution
di: Xu, Xiaowei, et al.
Pubblicazione: (2024)

A general tensor-structured compression scheme for efficient large language models
di: Lu, Ying, et al.
Pubblicazione: (2026)

Large language models can learn and generalize steganographic chain-of-thought under process supervision
di: Skaf, Joey, et al.
Pubblicazione: (2025)

Auditing language models for hidden objectives
di: Marks, Samuel, et al.
Pubblicazione: (2025)

The language of time: a language model perspective on time-series foundation models
di: Xie, Yi, et al.
Pubblicazione: (2025)

A multimodal and temporal foundation model for virtual patient representations at healthcare system scale
di: Zhang, Andrew, et al.
Pubblicazione: (2026)

Representation in large language models
di: Yetman, Cameron
Pubblicazione: (2025)

Is Sanskrit the most token-efficient language? A quantitative study using GPT, Gemini, and SentencePiece
di: Kumar, Anshul
Pubblicazione: (2026)

Alignment faking in large language models
di: Greenblatt, Ryan, et al.
Pubblicazione: (2024)

Lightweight reranking for language model generations
di: Jain, Siddhartha, et al.
Pubblicazione: (2023)

Extracting books from production language models
di: Ahmed, Ahmed, et al.
Pubblicazione: (2026)

Long-form factuality in large language models
di: Wei, Jerry, et al.
Pubblicazione: (2024)

Can large language models explore in-context?
di: Krishnamurthy, Akshay, et al.
Pubblicazione: (2024)

Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning
di: Sclar, Melanie, et al.
Pubblicazione: (2024)

MetaGreen: Meta-Learning Inspired Transformer Selection for Green Semantic Communication
di: Mukherjee, Shubhabrata, et al.
Pubblicazione: (2024)

AI-AI Bias: large language models favor communications generated by large language models
di: Laurito, Walter, et al.
Pubblicazione: (2024)

Are aligned neural networks adversarially aligned?
di: Carlini, Nicholas, et al.
Pubblicazione: (2023)

Directional Concentration Uncertainty: A representational approach to uncertainty quantification for generative models
di: Chattopadhyay, Souradeep, et al.
Pubblicazione: (2026)

A dataset and benchmark for hospital course summarization with adapted large language models
di: Aali, Asad, et al.
Pubblicazione: (2024)

Inducing anxiety in large language models can induce bias
di: Coda-Forno, Julian, et al.
Pubblicazione: (2023)

MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
di: Huang, Kaixuan, et al.
Pubblicazione: (2025)

Post-training makes large language models less human-like
di: Binz, Marcel, et al.
Pubblicazione: (2026)

Artificial Aphasias in Lesioned Language Models
di: Roll, Nathan, et al.
Pubblicazione: (2026)

Safety and accuracy follow different scaling laws in clinical large language models
di: Wind, Sebastian, et al.
Pubblicazione: (2026)

Vocabulary shapes cross-lingual variation of word-order learnability in language models
di: Martins, Jonas Mayer, et al.
Pubblicazione: (2026)

Fresh in memory: Training-order recency is linearly encoded in language model activations
di: Krasheninnikov, Dmitrii, et al.
Pubblicazione: (2025)

Efficient semantic uncertainty quantification in language models via diversity-steered sampling
di: Park, Ji Won, et al.
Pubblicazione: (2025)

CogBench: a large language model walks into a psychology lab
di: Coda-Forno, Julian, et al.
Pubblicazione: (2024)

SteuerLLM: Local specialized large language model for German tax law analysis
di: Wind, Sebastian, et al.
Pubblicazione: (2026)

Multi-step retrieval and reasoning improves radiology question answering with large language models
di: Wind, Sebastian, et al.
Pubblicazione: (2025)

MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy
di: Yoshida, Davis, et al.
Pubblicazione: (2023)

Multimodal large language model for wheat breeding: a new exploration of smart breeding
di: Yang, Guofeng, et al.
Pubblicazione: (2024)

MedicalBERT: enhancing biomedical natural language processing using pretrained BERT-based model
di: Reddy, K. Sahit, et al.
Pubblicazione: (2025)

Linear probes rely on textual evidence: Results from leakage mitigation studies in language models
di: Boxo, Gerard, et al.
Pubblicazione: (2025)

Can large language models replace humans in the systematic review process? Evaluating GPT-4's efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages
di: Khraisha, Qusai, et al.
Pubblicazione: (2023)

Zero-shot data citation function classification using transformer-based large language models (LLMs)
di: Byers, Neil, et al.
Pubblicazione: (2025)