Imagen de Portada

Mechanistic Interpretability as Statistical Estimation: A Variance Analysis

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Méloux, Maxime, Portet, François, Peyrard, Maxime
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?
por: Méloux, Maxime, et al.
Publicado: (2025)

The Dead Salmons of AI Interpretability
por: Méloux, Maxime, et al.
Publicado: (2025)

Meta-Statistical Learning: Supervised Learning of Statistical Estimators
por: Peyrard, Maxime, et al.
Publicado: (2025)

Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
por: Geng, Saibo, et al.
Publicado: (2023)

Evaluating Language Model Agency through Negotiations
por: Davidson, Tim R., et al.
Publicado: (2024)

MIST: Mutual Information Estimation Via Supervised Training
por: Gritsai, German, et al.
Publicado: (2025)

Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning
por: Bhatia, Gagan, et al.
Publicado: (2025)

A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
por: Monea, Giovanni, et al.
Publicado: (2023)

What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
por: Zhang, Xinhao, et al.
Publicado: (2026)

MIB: A Mechanistic Interpretability Benchmark
por: Mueller, Aaron, et al.
Publicado: (2025)

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks
por: Sun, Jiuding, et al.
Publicado: (2025)

Mechanistic Interpretability of GPT-like Models on Summarization Tasks
por: Mishra, Anurag
Publicado: (2025)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
por: Cho, Hakaze, et al.
Publicado: (2025)

Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
por: Kim, Geonhee, et al.
Publicado: (2024)

Agentic AI: The Era of Semantic Decoding
por: Peyrard, Maxime, et al.
Publicado: (2024)

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
por: Song, Xiangchen, et al.
Publicado: (2025)

Iteration Head: A Mechanistic Study of Chain-of-Thought
por: Cabannes, Vivien, et al.
Publicado: (2024)

What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time?
por: Bhatia, Gagan, et al.
Publicado: (2026)

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
por: Chen, Jianhui, et al.
Publicado: (2026)

Pattern Recognition or Medical Knowledge? The Problem with Multiple-Choice Questions in Medicine
por: Griot, Maxime, et al.
Publicado: (2024)

A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i
por: Ayonrinde, Kola, et al.
Publicado: (2025)

Intrinsic Self-Correction in LLMs: Towards Explainable Prompting via Mechanistic Interpretability
por: Lee, Yu-Ting, et al.
Publicado: (2025)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
por: Wang, Xu, et al.
Publicado: (2026)

The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability Research
por: Bai, Xiaoyan, et al.
Publicado: (2026)

Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts
por: Heuillet, Maxime, et al.
Publicado: (2025)

Beyond Accuracy: Introducing a Symbolic-Mechanistic Approach to Interpretable Evaluation
por: Habibi, Reza, et al.
Publicado: (2026)

Mechanistic?
por: Saphra, Naomi, et al.
Publicado: (2024)

From Variance to Invariance: Qualitative Content Analysis for Narrative Graph Annotation
por: Huang, Junbo, et al.
Publicado: (2026)

On Efficient and Statistical Quality Estimation for Data Annotation
por: Klie, Jan-Christoph, et al.
Publicado: (2024)

Zero-Overhead Introspection for Adaptive Test-Time Compute
por: Manvi, Rohin, et al.
Publicado: (2025)

Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability
por: Nainani, Jatin, et al.
Publicado: (2024)

Novel-WD: Exploring acquisition of Novel World Knowledge in LLMs Using Prefix-Tuning
por: Méloux, Maxime, et al.
Publicado: (2024)

On the Role of Preference Variance in Preference Optimization
por: Guo, Jiacheng, et al.
Publicado: (2025)

Too Big to Fool: Resisting Deception in Language Models
por: Samsami, Mohammad Reza, et al.
Publicado: (2024)

Mechanistic Fine-tuning for In-context Learning
por: Cho, Hakaze, et al.
Publicado: (2025)

OptiHive: Ensemble Selection for LLM-Based Optimization via Statistical Modeling
por: Bouscary, Maxime, et al.
Publicado: (2025)

Towards Quantifying Commonsense Reasoning with Mechanistic Insights
por: Joshi, Abhinav, et al.
Publicado: (2025)

Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii
por: Ayonrinde, Kola, et al.
Publicado: (2025)

LOLAMEME: Logic, Language, Memory, Mechanistic Framework
por: Desai, Jay, et al.
Publicado: (2024)

Parameter Efficient Fine-tuning via Explained Variance Adaptation
por: Paischer, Fabian, et al.
Publicado: (2024)