Cover Image

Structural Inference: Interpreting Small Language Models with Susceptibilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Baker, Garrett, Wang, George, Hoogland, Jesse, Murfet, Daniel
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Embryology of a Language Model
by: Wang, George, et al.
Published: (2025)

Towards Spectroscopy: Susceptibility Clusters in Language Models
by: Gordon, Andrew, et al.
Published: (2026)

Dynamics of Transient Structure in In-Context Linear Regression Transformers
by: Carroll, Liam, et al.
Published: (2025)

Patterning: The Dual of Interpretability
by: Wang, George, et al.
Published: (2026)

Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
by: Wang, George, et al.
Published: (2024)

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
by: Urdshals, Einar, et al.
Published: (2025)

Interpreting Reinforcement Learning Agents with Susceptibilities
by: Elliott, Chris, et al.
Published: (2026)

Loss Landscape Degeneracy and Stagewise Development in Transformers
by: Hoogland, Jesse, et al.
Published: (2024)

You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
by: Lehalleur, Simon Pepin, et al.
Published: (2025)

The Loss Kernel: A Geometric Probe for Deep Learning Interpretability
by: Adam, Maxwell, et al.
Published: (2025)

Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning
by: Elliott, Chris, et al.
Published: (2026)

From Global to Local: A Scalable Benchmark for Local Posterior Sampling
by: Hitchcock, Rohan, et al.
Published: (2025)

Modes of Sequence Models and Learning Coefficients
by: Chen, Zhongtian, et al.
Published: (2025)

Linear Response Estimators for Singular Statistical Models
by: Elliott, Chris, et al.
Published: (2026)

Programs as Singularities
by: Murfet, Daniel, et al.
Published: (2025)

Influence Dynamics and Stagewise Data Attribution
by: Lee, Jin Hwa, et al.
Published: (2025)

Generalization Boundaries of Fine-Tuned Small Language Models for Graph Structural Inference
by: Podstawski, Michal
Published: (2026)

Bayesian Influence Functions for Hessian-Free Data Attribution
by: Kreer, Philipp Alexander, et al.
Published: (2025)

Open Problems in Mechanistic Interpretability
by: Sharkey, Lee, et al.
Published: (2025)

The Local Learning Coefficient: A Singularity-Aware Complexity Measure
by: Lau, Edmund, et al.
Published: (2023)

Stagewise Reinforcement Learning and the Geometry of the Regret Landscape
by: Elliott, Chris, et al.
Published: (2026)

IMU-1: Sample-Efficient Pre-training of Small Language Models
by: Grigorev, George
Published: (2026)

Graph Property Inference in Small Language Models: Effects of Representation and Reasoning Strategy
by: Podstawski, Michal
Published: (2026)

Unraveling the Potential of Diffusion Models in Small Molecule Generation
by: Zhang, Peining, et al.
Published: (2025)

Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs
by: Neporozhnii, Ihor, et al.
Published: (2026)

Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference
by: García-Carrasco, Jorge, et al.
Published: (2024)

Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
by: Sun, Bian, et al.
Published: (2026)

Individual Causal Inference with Structural Causal Model
by: Chang, Daniel T.
Published: (2025)

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models
by: Leask, Patrick, et al.
Published: (2025)

Interpretable Relational Inference with LLM-Guided Symbolic Dynamics Modeling
by: Liang, Xiaoxiao, et al.
Published: (2026)

Algorithmic Accountability in Small Data: Sample-Size-Induced Bias Within Classification Metrics
by: Briscoe, Jarren, et al.
Published: (2025)

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

TinyGraphEstimator: Adapting Lightweight Language Models for Graph Structure Inference
by: Podstawski, Michal
Published: (2025)

Data Selection: A General Principle for Building Small Interpretable Models
by: Ghose, Abhishek
Published: (2022)

TinyLLM: Evaluation and Optimization of Small Language Models for Agentic Tasks on Edge Devices
by: Haque, Mohd Ariful, et al.
Published: (2025)

Large Language Models for Zero-shot Inference of Causal Structures in Biology
by: Newsham, Izzy, et al.
Published: (2025)

SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference
by: Zhao, Yi, et al.
Published: (2025)

ABROCA Distributions For Algorithmic Bias Assessment: Considerations Around Interpretation
by: Borchers, Conrad, et al.
Published: (2024)

Route Sparse Autoencoder to Interpret Large Language Models
by: Shi, Wei, et al.
Published: (2025)

Domain-Adaptive Small Language Models for Structured Tax Code Prediction
by: Nath, Souvik, et al.
Published: (2025)