Imagen de Portada

States Hidden in Hidden States: LLMs Emerge Discrete State Representations Implicitly

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Junhao, Hu, Shengding, Liu, Zhiyuan, Sun, Maosong
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Stuffed Mamba: Oversized States Lead to the Inability to Forget
por: Chen, Yingfa, et al.
Publicado: (2024)

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

ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs
por: Zhang, Zhenliang, et al.
Publicado: (2025)

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

Transforming Hidden States into Binary Semantic Features
por: Musil, Tomáš, et al.
Publicado: (2024)

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

StateX: Enhancing RNN Recall via Post-training State Expansion
por: Shen, Xingyu, et al.
Publicado: (2025)

Evaluation of LLMs-based Hidden States as Author Representations for Psychological Human-Centered NLP Tasks
por: Soni, Nikita, et al.
Publicado: (2025)

I've got the "Answer"! Interpretation of LLMs Hidden States in Question Answering
por: Goloviznina, Valeriya, et al.
Publicado: (2024)

UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs
por: He, Chaoqun, et al.
Publicado: (2024)

Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs
por: Servedio, Giovanni, et al.
Publicado: (2025)

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

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

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

Learning to (Learn at Test Time): RNNs with Expressive Hidden States
por: Sun, Yu, et al.
Publicado: (2024)

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

A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
por: Luo, Kairong, et al.
Publicado: (2025)

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

Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models
por: Zhang, Xinrong, et al.
Publicado: (2024)

$\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens
por: Zhang, Xinrong, et al.
Publicado: (2024)

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

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

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

When Chain-of-Thought Fails, the Solution Hides in the Hidden States
por: Mehrafarin, Houman, et al.
Publicado: (2026)

Make Every Draft Count: Hidden State based Speculative Decoding
por: Chen, Yuetao, et al.
Publicado: (2026)

DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models
por: Zhao, Ranchi, et al.
Publicado: (2024)

$Δ$-AttnMask: Attention-Guided Masked Hidden States for Efficient Data Selection and Augmentation
por: Hu, Jucheng, et al.
Publicado: (2025)

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

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

On the Relation of State Space Models and Hidden Markov Models
por: Ghojogh, Aydin, et al.
Publicado: (2026)

Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
por: Sternfeld, Alexander, et al.
Publicado: (2026)

Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification
por: Zhang, Anqi, et al.
Publicado: (2025)

Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance
por: Chen, Xinzhu, et al.
Publicado: (2026)

Shiny Stories, Hidden Struggles: Investigating the Representation of Disability Through the Lens of LLMs
por: Bombieri, Marco, et al.
Publicado: (2026)

HSF: Defending against Jailbreak Attacks with Hidden State Filtering
por: Qian, Cheng, et al.
Publicado: (2024)

Hidden State Poisoning Attacks against Mamba-based Language Models
por: Mercier, Alexandre Le, et al.
Publicado: (2026)

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

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
por: He, Chaoqun, et al.
Publicado: (2024)

Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models
por: Furuya, Kotaro, et al.
Publicado: (2026)

You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
por: LeVi, Amit, et al.
Publicado: (2025)