Imagen de Portada

eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Guggenberger, Irma Heithoff. Marc, Kalogiannis, Sandra, Mayer, Susanne, Maag, Fabian, Schacht, Sigurd, Lanquillon, Carsten
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations
por: Donisch, Leo, et al.
Publicado: (2024)

Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models
por: Barkur, Sudarshan Kamath, et al.
Publicado: (2025)

PHOENIX: Open-Source Language Adaption for Direct Preference Optimization
por: Uhlig, Matthias, et al.
Publicado: (2024)

A Review of Common Online Speaker Diarization Methods
por: Aperdannier, Roman, et al.
Publicado: (2024)

Systematic Evaluation of Online Speaker Diarization Systems Regarding their Latency
por: Aperdannier, Roman, et al.
Publicado: (2024)

An approach to optimize inference of the DIART speaker diarization pipeline
por: Aperdannier, Roman, et al.
Publicado: (2024)

Faithful or Fabricated? A Causal Framework for Rationalization Bias in LLM Judges
por: Tapwal, Riya, et al.
Publicado: (2026)

DIF: A Framework for Benchmarking and Verifying Implicit Bias in LLMs
por: Yin, Lake, et al.
Publicado: (2025)

Finding Words Associated with DIF: Predicting Differential Item Functioning using LLMs and Explainable AI
por: Maeda, Hotaka, et al.
Publicado: (2025)

Word-Centered Semantic Graphs for Interpretable Diachronic Sense Tracking
por: Kolli, Imene, et al.
Publicado: (2026)

Self‐Assessment Instruments Related to Functional Ability for People Who Use Augmentative and Alternative Communication—A Scoping Review
por: Irina Savolainen, et al.
Publicado: (2025)

Mixture of Tunable Experts -- Behavior Modification of DeepSeek-R1 at Inference Time
por: Dahlke, Robert, et al.
Publicado: (2025)

Efficient LLM Inference with Kcache
por: He, Qiaozhi, et al.
Publicado: (2024)

Tailored Truths: Optimizing LLM Persuasion with Personalization and Fabricated Statistics
por: Timm, Jasper, et al.
Publicado: (2025)

TRACE: Training and Inference-Time Interpretability Analysis for Language Models
por: Aljaafari, Nura, et al.
Publicado: (2025)

DIF Statistical Inference without Knowing Anchoring Items
por: Chen, Yunxiao, et al.
Publicado: (2021)

Mechanistic Interpretability of Emotion Inference in Large Language Models
por: Tak, Ala N., et al.
Publicado: (2025)

Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation
por: Aljaafari, Nura, et al.
Publicado: (2026)

An Interpretable and Crosslingual Method for Evaluating Second-Language Dialogues
por: Gao, Rena, et al.
Publicado: (2024)

Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass
por: Popovič, Nicholas, et al.
Publicado: (2025)

What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation
por: Golovanevsky, Michal, et al.
Publicado: (2024)

Interpretable Differential Diagnosis with Dual-Inference Large Language Models
por: Zhou, Shuang, et al.
Publicado: (2024)

MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inference
por: Park, Jeonghyun, et al.
Publicado: (2025)

Latent Debate: A Surrogate Framework for Interpreting LLM Thinking
por: Chen, Lihu, et al.
Publicado: (2025)

Patch-Effect Graph Kernels for LLM Interpretability
por: Fernandez-Boullon, Ruben, et al.
Publicado: (2026)

Transcoders Find Interpretable LLM Feature Circuits
por: Dunefsky, Jacob, et al.
Publicado: (2024)

Interpretable LLM-based Table Question Answering
por: Nguyen, Giang, et al.
Publicado: (2024)

Designing Role Vectors to Improve LLM Inference Behaviour
por: Potertì, Daniele, et al.
Publicado: (2025)

Hierarchical Verification of Speculative Beams for Accelerating LLM Inference
por: Sen, Jaydip, et al.
Publicado: (2025)

A Survey on LLM Inference-Time Self-Improvement
por: Dong, Xiangjue, et al.
Publicado: (2024)

Improving LLM-as-a-Judge Inference with the Judgment Distribution
por: Wang, Victor, et al.
Publicado: (2025)

HAMburger: Accelerating LLM Inference via Token Smashing
por: Liu, Jingyu, et al.
Publicado: (2025)

LLM Inference Enhanced by External Knowledge: A Survey
por: Lin, Yu-Hsuan, et al.
Publicado: (2025)

Taming the Fragility of KV Cache Eviction in LLM Inference
por: Feng, Yuan, et al.
Publicado: (2025)

READER: Retrieval-Assisted Drafter for Efficient LLM Inference
por: Divilkovskiy, Maxim, et al.
Publicado: (2025)

Tutorial Proposal: Speculative Decoding for Efficient LLM Inference
por: Xia, Heming, et al.
Publicado: (2025)

Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
por: Yuan, Jiayi, et al.
Publicado: (2025)

LLM Cache Bandit Revisited: Addressing Query Heterogeneity for Cost-Effective LLM Inference
por: Yang, Hantao, et al.
Publicado: (2025)

A Survey on LLM-Assisted Clinical Trial Recruitment
por: Ghosh, Shrestha, et al.
Publicado: (2025)

GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German
por: Mewes, Fabian, et al.
Publicado: (2026)