Copertina

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ghandeharioun, Asma, Caciularu, Avi, Pearce, Adam, Dixon, Lucas, Geva, Mor
Natura:	Preprint
Pubblicazione:	2024
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

When Can Transformers Count to n?
di: Yehudai, Gilad, et al.
Pubblicazione: (2024)

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
di: Katz, Shahar, et al.
Pubblicazione: (2024)

Think Before You Lie: How Reasoning Leads to Honesty
di: Yuan, Ann, et al.
Pubblicazione: (2026)

Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance
di: Goldman, Omer, et al.
Pubblicazione: (2024)

Interpretability Illusions in the Generalization of Simplified Models
di: Friedman, Dan, et al.
Pubblicazione: (2023)

Latent Reasoning with Supervised Thinking States
di: Amos, Ido, et al.
Pubblicazione: (2026)

Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics
di: Blum, Carter, et al.
Pubblicazione: (2025)

Layer by Layer: Uncovering Hidden Representations in Language Models
di: Skean, Oscar, et al.
Pubblicazione: (2025)

Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions
di: Parmar, Mihir, et al.
Pubblicazione: (2022)

Who's asking? User personas and the mechanics of latent misalignment
di: Ghandeharioun, Asma, et al.
Pubblicazione: (2024)

DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs
di: Cattan, Arie, et al.
Pubblicazione: (2025)

RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations
di: Huang, Jing, et al.
Pubblicazione: (2024)

Aioli: A Unified Optimization Framework for Language Model Data Mixing
di: Chen, Mayee F., et al.
Pubblicazione: (2024)

UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation
di: Guo, Shuhan, et al.
Pubblicazione: (2024)

A Unified Framework for Model Editing
di: Gupta, Akshat, et al.
Pubblicazione: (2024)

Decoding-time Realignment of Language Models
di: Liu, Tianlin, et al.
Pubblicazione: (2024)

Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models
di: Yona, Itay, et al.
Pubblicazione: (2026)

From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty
di: Ivgi, Maor, et al.
Pubblicazione: (2024)

Correlated Errors in Large Language Models
di: Kim, Elliot, et al.
Pubblicazione: (2025)

A Study on Hidden Layer Distillation for Large Language Model Pre-Training
di: Guigon, Maxime, et al.
Pubblicazione: (2026)

Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
di: Luo, Haozheng, et al.
Pubblicazione: (2026)

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
di: Jin, Yiqiao, et al.
Pubblicazione: (2026)

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
di: Weng, Zixuan, et al.
Pubblicazione: (2026)

The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models
di: Flamant, Cedric, et al.
Pubblicazione: (2026)

Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models
di: Wong, Wai Tuck, et al.
Pubblicazione: (2026)

Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models
di: Messina, Alberto, et al.
Pubblicazione: (2026)

Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models
di: Sun, Shaoning, et al.
Pubblicazione: (2026)

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

AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models
di: Cheng, Jiale, et al.
Pubblicazione: (2024)

Tracing the Representation Geometry of Language Models from Pretraining to Post-training
di: Li, Melody Zixuan, et al.
Pubblicazione: (2025)

Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling
di: Amin, Adil
Pubblicazione: (2026)

RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models
di: Yang, Daniel, et al.
Pubblicazione: (2026)

Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation
di: Baumann, Joachim, et al.
Pubblicazione: (2025)

Constructing Interpretable Features from Compositional Neuron Groups
di: Shafran, Or, et al.
Pubblicazione: (2025)

Existing Large Language Model Unlearning Evaluations Are Inconclusive
di: Feng, Zhili, et al.
Pubblicazione: (2025)

PromptBench: A Unified Library for Evaluation of Large Language Models
di: Zhu, Kaijie, et al.
Pubblicazione: (2023)

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
di: Ye, Tian, et al.
Pubblicazione: (2024)

Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models
di: Ventura, Mor, et al.
Pubblicazione: (2023)

ReFT: Representation Finetuning for Language Models
di: Wu, Zhengxuan, et al.
Pubblicazione: (2024)

Affinity and Diversity: A Unified Metric for Demonstration Selection via Internal Representations
di: Kato, Mariko, et al.
Pubblicazione: (2025)