:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autori principali:	Musil, Tomáš, Mareček, David
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	https://arxiv.org/abs/2409.19813
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exploring Interpretability of Independent Components of Word Embeddings with Automated Word Intruder Test
di: Musil, Tomáš, et al.
Pubblicazione: (2022)

Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation
di: Limisiewicz, Tomasz, et al.
Pubblicazione: (2025)

Debiasing Algorithm through Model Adaptation
di: Limisiewicz, Tomasz, et al.
Pubblicazione: (2023)

Suppressing Final Layer Hidden State Jumps in Transformer Pretraining
di: Shibata, Keigo, et al.
Pubblicazione: (2026)

States Hidden in Hidden States: LLMs Emerge Discrete State Representations Implicitly
di: Chen, Junhao, et al.
Pubblicazione: (2024)

Teaching LLMs at Charles University: Assignments and Activities
di: Helcl, Jindřich, et al.
Pubblicazione: (2024)

Mixture of Hidden-Dimensions Transformer
di: Chen, Yilong, et al.
Pubblicazione: (2024)

The Hidden Space of Transformer Language Adapters
di: Alabi, Jesujoba O., et al.
Pubblicazione: (2024)

From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
di: Schiekiera, Louis, et al.
Pubblicazione: (2026)

LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States
di: Zhang, Yeqin, et al.
Pubblicazione: (2026)

Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders
di: Chanin, David, et al.
Pubblicazione: (2025)

HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States
di: Jiang, Yilei, et al.
Pubblicazione: (2025)

AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue
di: Park, Jihyung, et al.
Pubblicazione: (2026)

Mechanistic Interpretability of Binary and Ternary Transformers
di: Li, Jason
Pubblicazione: (2024)

Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
di: Pal, Koyena, et al.
Pubblicazione: (2023)

What Am I Missing? Question-Answering as Hidden State Probing
di: Luo, Chu Fei, et al.
Pubblicazione: (2026)

Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing
di: Wei, Kai, et al.
Pubblicazione: (2026)

Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States
di: Duan, Hanyu, et al.
Pubblicazione: (2024)

CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
di: Liang, Zhenwen, et al.
Pubblicazione: (2025)

Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings
di: Sinha, Soumen, et al.
Pubblicazione: (2025)

Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models
di: Bajaj, Anooshka, et al.
Pubblicazione: (2025)

Improving Interpretability of Lexical Semantic Change with Neurobiological Features
di: Oda, Kohei, et al.
Pubblicazione: (2026)

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
di: Razzhigaev, Anton, et al.
Pubblicazione: (2025)

Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
di: Yang, Haolin, et al.
Pubblicazione: (2025)

CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks
di: Mercier, Alexandre Le, et al.
Pubblicazione: (2026)

Semformer: Transformer Language Models with Semantic Planning
di: Yin, Yongjing, et al.
Pubblicazione: (2024)

TRACE for Tracking the Emergence of Semantic Representations in Transformers
di: Aljaafari, Nura, et al.
Pubblicazione: (2025)

Explicit Grammar Semantic Feature Fusion for Robust Text Classification
di: Sultana, Azrin, et al.
Pubblicazione: (2026)

Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
di: Yang, Rui, et al.
Pubblicazione: (2024)

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
di: Chanin, David, et al.
Pubblicazione: (2024)

Monitoring Transformative Technological Convergence Through LLM-Extracted Semantic Entity Triple Graphs
di: Sternfeld, Alexander, et al.
Pubblicazione: (2025)

Inside-Out: Hidden Factual Knowledge in LLMs
di: Gekhman, Zorik, et al.
Pubblicazione: (2025)

LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signals
di: Li, Jinxin, et al.
Pubblicazione: (2025)

Semantic-Preserving Adversarial Attacks on LLMs: An Adaptive Greedy Binary Search Approach
di: Zhang, Chong, et al.
Pubblicazione: (2025)

When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?
di: Liu, Tianyu, et al.
Pubblicazione: (2026)

Comateformer: Combined Attention Transformer for Semantic Sentence Matching
di: Li, Bo, et al.
Pubblicazione: (2024)

Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features
di: Bu, Mengyu, et al.
Pubblicazione: (2024)

CSF: Contrastive Semantic Features for Direct Multilingual Sign Language Generation
di: Bao, Tran Sy
Pubblicazione: (2026)

Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language
di: Boggust, Angie, et al.
Pubblicazione: (2025)

Transformers are Multi-State RNNs
di: Oren, Matanel, et al.
Pubblicazione: (2024)